Token | put |
Token ID | 1234 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
half | +0.081 |
Mom | +0.081 |
sticker | +0.077 |
icing | +0.075 |
ribbon | +0.074 |
Neg logit contributions | |
vill | -0.070 |
current | -0.066 |
vious | -0.066 |
challenged | -0.066 |
ot | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Mom | +0.044 |
wrist | +0.044 |
ribbon | +0.041 |
bookmark | +0.041 |
sticker | +0.040 |
Neg logit contributions | |
vill | -0.036 |
ot | -0.035 |
current | -0.033 |
ships | -0.033 |
padd | -0.032 |
Token | cheese |
Token ID | 9891 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
vill | +0.027 |
ot | +0.026 |
current | +0.025 |
crocod | +0.023 |
eagle | +0.023 |
Neg logit contributions | |
Mom | -0.019 |
ushes | -0.018 |
Her | -0.017 |
wrist | -0.017 |
etti | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Mom | +0.202 |
wrist | +0.196 |
icing | +0.191 |
bookmark | +0.187 |
Love | +0.185 |
Neg logit contributions | |
ot | -0.202 |
vill | -0.198 |
current | -0.197 |
padd | -0.184 |
ships | -0.184 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
Mom | +0.049 |
ushes | +0.048 |
wrist | +0.047 |
sticker | +0.046 |
bookmark | +0.045 |
Neg logit contributions | |
ot | -0.058 |
current | -0.058 |
vill | -0.057 |
padd | -0.055 |
challenged | -0.055 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
ot | +0.029 |
current | +0.029 |
vill | +0.029 |
eagle | +0.026 |
ranc | +0.026 |
Neg logit contributions | |
Mom | -0.018 |
ushes | -0.017 |
Her | -0.016 |
rap | -0.015 |
wrist | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Mom | +0.308 |
wrist | +0.279 |
bookmark | +0.274 |
Love | +0.273 |
icing | +0.272 |
Neg logit contributions | |
ot | -0.248 |
current | -0.242 |
vill | -0.233 |
fishermen | -0.225 |
padd | -0.220 |
Token | the |
Token ID | 262 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
wrist | +0.108 |
ushes | +0.108 |
Mom | +0.104 |
Love | +0.103 |
aps | +0.103 |
Neg logit contributions | |
ot | -0.072 |
current | -0.072 |
vill | -0.071 |
ships | -0.064 |
padd | -0.061 |
Token | bread |
Token ID | 8509 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
current | +0.027 |
vill | +0.026 |
ot | +0.026 |
ranc | +0.025 |
eagle | +0.024 |
Neg logit contributions | |
ushes | -0.023 |
Mom | -0.023 |
half | -0.020 |
Anna | -0.019 |
aps | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Mom | +0.115 |
Anna | +0.104 |
bookmark | +0.104 |
Elsa | +0.103 |
icing | +0.101 |
Neg logit contributions | |
ot | -0.111 |
current | -0.109 |
bank | -0.104 |
vill | -0.103 |
ships | -0.103 |
Token | Mom |
Token ID | 11254 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
half | +0.059 |
Mom | +0.059 |
sticker | +0.057 |
wrist | +0.056 |
ribbon | +0.056 |
Neg logit contributions | |
current | -0.049 |
ot | -0.048 |
vill | -0.048 |
challenged | -0.047 |
ships | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Mom | +0.034 |
wrist | +0.034 |
ushes | +0.033 |
scalp | +0.031 |
Her | +0.030 |
Neg logit contributions | |
ot | -0.031 |
vill | -0.031 |
ships | -0.029 |
vious | -0.028 |
padd | -0.028 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
vill | +0.034 |
ot | +0.033 |
current | +0.031 |
eagle | +0.030 |
vious | +0.030 |
Neg logit contributions | |
Mom | -0.026 |
ushes | -0.024 |
Her | -0.024 |
wrist | -0.022 |
Anna | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Mom | +0.291 |
icing | +0.261 |
ushes | +0.255 |
wrist | +0.251 |
Her | +0.250 |
Neg logit contributions | |
ot | -0.248 |
vill | -0.239 |
fishermen | -0.235 |
current | -0.229 |
vious | -0.224 |
Token | I |
Token ID | 314 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
half | +0.044 |
icing | +0.043 |
sticker | +0.041 |
ushes | +0.041 |
ribbon | +0.041 |
Neg logit contributions | |
ot | -0.025 |
vill | -0.024 |
current | -0.024 |
ranc | -0.023 |
vious | -0.022 |
Token | like |
Token ID | 588 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
half | +0.029 |
Mom | +0.029 |
sticker | +0.027 |
cookie | +0.026 |
icing | +0.026 |
Neg logit contributions | |
vill | -0.029 |
challenged | -0.027 |
current | -0.027 |
ot | -0.027 |
vious | -0.027 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.31e+00 |
Pos logit contributions | |
Mom | +0.129 |
ushes | +0.118 |
wrist | +0.116 |
ribbon | +0.110 |
half | +0.110 |
Neg logit contributions | |
vill | -0.137 |
ot | -0.136 |
ships | -0.129 |
challenged | -0.127 |
fishermen | -0.124 |
Token | ." |
Token ID | 526 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Mom | +0.307 |
bookmark | +0.282 |
wrist | +0.273 |
ribbon | +0.273 |
ushes | +0.272 |
Neg logit contributions | |
ot | -0.243 |
fishermen | -0.232 |
ranc | -0.213 |
vill | -0.211 |
ships | -0.209 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
half | +0.079 |
Mom | +0.077 |
sticker | +0.075 |
ushes | +0.074 |
icing | +0.073 |
Neg logit contributions | |
vill | -0.115 |
ot | -0.112 |
challenged | -0.111 |
current | -0.108 |
vious | -0.105 |
Token | said |
Token ID | 531 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
half | +0.075 |
Mom | +0.073 |
sticker | +0.067 |
cookie | +0.067 |
ribbon | +0.065 |
Neg logit contributions | |
vill | -0.084 |
current | -0.083 |
vious | -0.080 |
hurricane | -0.079 |
roads | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
vill | +0.025 |
challenged | +0.024 |
ot | +0.024 |
current | +0.024 |
vious | +0.023 |
Neg logit contributions | |
Mom | -0.017 |
half | -0.016 |
ribbon | -0.016 |
icing | -0.015 |
sticker | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
half | +0.048 |
icing | +0.047 |
Mom | +0.047 |
sticker | +0.047 |
wrist | +0.046 |
Neg logit contributions | |
vill | -0.062 |
challenged | -0.060 |
current | -0.059 |
ot | -0.059 |
vious | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Mom | +0.154 |
half | +0.139 |
ushes | +0.136 |
ribbon | +0.135 |
bookmark | +0.134 |
Neg logit contributions | |
vious | -0.153 |
vill | -0.153 |
ot | -0.152 |
challenged | -0.147 |
current | -0.146 |
Token | He |
Token ID | 679 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
half | +0.088 |
Mom | +0.087 |
ribbon | +0.086 |
sticker | +0.086 |
icing | +0.086 |
Neg logit contributions | |
vill | -0.030 |
current | -0.028 |
vious | -0.027 |
challenged | -0.027 |
ot | -0.027 |
Token | likes |
Token ID | 7832 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
vill | +0.009 |
current | +0.009 |
challenged | +0.009 |
ot | +0.009 |
vious | +0.009 |
Neg logit contributions | |
half | -0.007 |
Mom | -0.007 |
sticker | -0.007 |
cookie | -0.007 |
icing | -0.007 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
Mom | +0.115 |
wrist | +0.105 |
half | +0.103 |
bookmark | +0.103 |
sticker | +0.103 |
Neg logit contributions | |
vill | -0.144 |
ot | -0.142 |
challenged | -0.135 |
vious | -0.135 |
ships | -0.135 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Mom | +0.220 |
ushes | +0.200 |
bookmark | +0.199 |
wrist | +0.196 |
Elsa | +0.194 |
Neg logit contributions | |
ot | -0.191 |
vill | -0.179 |
vious | -0.175 |
current | -0.174 |
fishermen | -0.173 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
Mom | +0.048 |
ushes | +0.043 |
sticker | +0.041 |
wrist | +0.040 |
bookmark | +0.040 |
Neg logit contributions | |
vill | -0.076 |
ot | -0.076 |
current | -0.076 |
vious | -0.073 |
challenged | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Mom | +0.306 |
bookmark | +0.290 |
ribbon | +0.275 |
Elsa | +0.275 |
Anna | +0.270 |
Neg logit contributions | |
ot | -0.237 |
fishermen | -0.232 |
current | -0.217 |
vious | -0.210 |
vill | -0.208 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
Mom | +0.047 |
ushes | +0.042 |
sticker | +0.039 |
wrist | +0.039 |
half | +0.038 |
Neg logit contributions | |
ot | -0.076 |
vill | -0.075 |
current | -0.075 |
vious | -0.073 |
challenged | -0.073 |
Token | too |
Token ID | 1165 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Mom | +0.190 |
bookmark | +0.167 |
wrist | +0.165 |
icing | +0.160 |
ushes | +0.159 |
Neg logit contributions | |
ot | -0.191 |
current | -0.182 |
vious | -0.181 |
vill | -0.180 |
challenged | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Mom | +0.034 |
wrist | +0.032 |
bookmark | +0.031 |
ribbon | +0.031 |
half | +0.031 |
Neg logit contributions | |
vill | -0.037 |
vious | -0.037 |
challenged | -0.037 |
current | -0.036 |
ot | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
half | +0.084 |
ribbon | +0.083 |
icing | +0.082 |
sticker | +0.082 |
bookmark | +0.081 |
Neg logit contributions | |
vill | -0.036 |
ot | -0.033 |
current | -0.033 |
challenged | -0.033 |
vious | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Mom | +0.012 |
icing | +0.011 |
ushes | +0.010 |
ribbon | +0.010 |
mm | +0.010 |
Neg logit contributions | |
vill | -0.010 |
vious | -0.009 |
ot | -0.009 |
challenged | -0.009 |
padd | -0.009 |
Token | face |
Token ID | 1986 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
rap | +0.086 |
ushes | +0.083 |
Anna | +0.083 |
Mom | +0.081 |
icing | +0.076 |
Neg logit contributions | |
ot | -0.092 |
current | -0.090 |
en | -0.084 |
ranc | -0.083 |
vill | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Mom | +0.047 |
ushes | +0.047 |
half | +0.046 |
wrist | +0.046 |
Anna | +0.046 |
Neg logit contributions | |
vious | -0.041 |
challenged | -0.039 |
vill | -0.039 |
current | -0.039 |
ot | -0.038 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
half | +0.059 |
sticker | +0.057 |
icing | +0.056 |
ribbon | +0.056 |
wrist | +0.055 |
Neg logit contributions | |
vill | -0.046 |
challenged | -0.045 |
current | -0.044 |
ot | -0.043 |
vious | -0.041 |
Token | bl |
Token ID | 698 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Mom | +0.011 |
half | +0.010 |
ushes | +0.010 |
icing | +0.010 |
wrist | +0.010 |
Neg logit contributions | |
vill | -0.013 |
vious | -0.013 |
ot | -0.013 |
challenged | -0.013 |
padd | -0.012 |
Token | ushes |
Token ID | 17237 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
vious | +0.067 |
bust | +0.063 |
vill | +0.063 |
cient | +0.062 |
ot | +0.061 |
Neg logit contributions | |
Mom | -0.029 |
half | -0.025 |
icing | -0.023 |
ribbon | -0.023 |
cookie | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
wrist | +0.340 |
bookmark | +0.297 |
Mom | +0.296 |
ribbon | +0.285 |
ra | +0.285 |
Neg logit contributions | |
vious | -0.216 |
rified | -0.206 |
vill | -0.205 |
ships | -0.196 |
ot | -0.193 |
Token | He |
Token ID | 679 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
half | +0.067 |
sticker | +0.065 |
ribbon | +0.065 |
Mom | +0.065 |
wrist | +0.064 |
Neg logit contributions | |
vill | -0.041 |
current | -0.039 |
challenged | -0.039 |
ot | -0.039 |
vious | -0.037 |
Token | says |
Token ID | 1139 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
vill | +0.013 |
challenged | +0.013 |
vious | +0.012 |
ot | +0.012 |
current | +0.012 |
Neg logit contributions | |
Mom | -0.012 |
half | -0.012 |
sticker | -0.011 |
icing | -0.011 |
wrist | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
Mom | +0.003 |
half | +0.002 |
wrist | +0.002 |
ribbon | +0.002 |
ushes | +0.002 |
Neg logit contributions | |
vill | -0.002 |
ot | -0.002 |
challenged | -0.002 |
current | -0.002 |
ships | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
half | +0.036 |
Mom | +0.035 |
ushes | +0.034 |
icing | +0.033 |
ribbon | +0.033 |
Neg logit contributions | |
vill | -0.022 |
challenged | -0.022 |
ot | -0.021 |
current | -0.021 |
ranc | -0.020 |
Token | because |
Token ID | 780 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Mom | +0.084 |
half | +0.076 |
sticker | +0.074 |
icing | +0.074 |
ribbon | +0.072 |
Neg logit contributions | |
vill | -0.108 |
challenged | -0.107 |
current | -0.104 |
vious | -0.104 |
ot | -0.104 |
Token | I |
Token ID | 314 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
vill | +0.098 |
ot | +0.096 |
challenged | +0.095 |
current | +0.093 |
ships | +0.093 |
Neg logit contributions | |
Mom | -0.064 |
half | -0.060 |
wrist | -0.060 |
sticker | -0.060 |
ribbon | -0.058 |
Token | like |
Token ID | 588 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
half | +0.025 |
Mom | +0.025 |
sticker | +0.024 |
cookie | +0.022 |
icing | +0.022 |
Neg logit contributions | |
vill | -0.034 |
challenged | -0.032 |
current | -0.032 |
ot | -0.032 |
vious | -0.032 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
Mom | +0.102 |
ushes | +0.091 |
half | +0.089 |
sticker | +0.085 |
ribbon | +0.084 |
Neg logit contributions | |
vill | -0.155 |
ot | -0.155 |
challenged | -0.149 |
ships | -0.149 |
current | -0.148 |
Token | and |
Token ID | 290 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Mom | +0.191 |
half | +0.174 |
ushes | +0.170 |
wrist | +0.165 |
ribbon | +0.161 |
Neg logit contributions | |
ot | -0.212 |
vill | -0.212 |
vious | -0.208 |
challenged | -0.207 |
current | -0.205 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
Mom | +0.045 |
ushes | +0.044 |
half | +0.039 |
sticker | +0.039 |
wrist | +0.038 |
Neg logit contributions | |
ot | -0.063 |
vill | -0.062 |
current | -0.062 |
ships | -0.059 |
challenged | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Mom | +0.290 |
half | +0.245 |
Anna | +0.245 |
bookmark | +0.242 |
ribbon | +0.242 |
Neg logit contributions | |
ot | -0.277 |
fishermen | -0.271 |
current | -0.258 |
vill | -0.254 |
ships | -0.253 |
Token | yellow |
Token ID | 7872 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Mom | +0.043 |
ushes | +0.041 |
half | +0.036 |
wrist | +0.036 |
sticker | +0.036 |
Neg logit contributions | |
ot | -0.066 |
current | -0.065 |
vill | -0.064 |
ships | -0.062 |
challenged | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Mom | +0.118 |
Anna | +0.103 |
ushes | +0.103 |
half | +0.101 |
bookmark | +0.100 |
Neg logit contributions | |
ot | -0.144 |
current | -0.139 |
vious | -0.138 |
vill | -0.137 |
ships | -0.133 |
Token | red |
Token ID | 2266 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
Mom | +0.042 |
ushes | +0.040 |
rap | +0.037 |
wrist | +0.036 |
half | +0.035 |
Neg logit contributions | |
ot | -0.064 |
current | -0.063 |
vill | -0.063 |
challenged | -0.060 |
vious | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Mom | +0.132 |
ushes | +0.116 |
Anna | +0.116 |
bookmark | +0.114 |
half | +0.112 |
Neg logit contributions | |
ot | -0.157 |
current | -0.153 |
vious | -0.151 |
vill | -0.149 |
ships | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Mom | +0.140 |
ushes | +0.130 |
Elsa | +0.129 |
Anna | +0.126 |
bookmark | +0.125 |
Neg logit contributions | |
current | -0.106 |
ot | -0.103 |
challenged | -0.102 |
vious | -0.099 |
vill | -0.098 |
Token | It |
Token ID | 632 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
half | +0.055 |
sticker | +0.052 |
Mom | +0.051 |
icing | +0.050 |
ribbon | +0.049 |
Neg logit contributions | |
vill | -0.050 |
challenged | -0.047 |
ot | -0.046 |
current | -0.046 |
vious | -0.045 |
Token | had |
Token ID | 550 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Mom | +0.049 |
half | +0.048 |
sticker | +0.047 |
icing | +0.045 |
ushes | +0.045 |
Neg logit contributions | |
vill | -0.049 |
challenged | -0.048 |
ot | -0.047 |
current | -0.046 |
vious | -0.046 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
Mom | +0.114 |
wrist | +0.103 |
sticker | +0.101 |
half | +0.100 |
ushes | +0.099 |
Neg logit contributions | |
vill | -0.133 |
vious | -0.132 |
current | -0.130 |
challenged | -0.129 |
ot | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Mom | +0.234 |
wrist | +0.212 |
bookmark | +0.207 |
Elsa | +0.207 |
Anna | +0.205 |
Neg logit contributions | |
ot | -0.165 |
current | -0.154 |
vious | -0.149 |
vill | -0.147 |
fishermen | -0.146 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
Mom | +0.036 |
ushes | +0.034 |
wrist | +0.034 |
uggle | +0.033 |
rap | +0.032 |
Neg logit contributions | |
ot | -0.054 |
current | -0.053 |
vill | -0.052 |
ships | -0.049 |
challenged | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Mom | +0.315 |
bookmark | +0.294 |
Anna | +0.294 |
Elsa | +0.282 |
wrist | +0.278 |
Neg logit contributions | |
ot | -0.230 |
fishermen | -0.218 |
current | -0.212 |
challenged | -0.196 |
ships | -0.194 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Mom | +0.035 |
ushes | +0.034 |
wrist | +0.032 |
rap | +0.031 |
uggle | +0.030 |
Neg logit contributions | |
ot | -0.057 |
current | -0.056 |
vill | -0.054 |
challenged | -0.052 |
ships | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Mom | +0.195 |
bookmark | +0.172 |
Anna | +0.171 |
wrist | +0.169 |
Elsa | +0.164 |
Neg logit contributions | |
ot | -0.178 |
current | -0.165 |
vious | -0.164 |
challenged | -0.163 |
vill | -0.159 |
Token | She |
Token ID | 1375 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
half | +0.060 |
sticker | +0.059 |
icing | +0.056 |
Mom | +0.056 |
ribbon | +0.055 |
Neg logit contributions | |
vill | -0.051 |
vious | -0.049 |
ot | -0.049 |
challenged | -0.047 |
current | -0.047 |
Token | did |
Token ID | 750 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Mom | +0.048 |
half | +0.048 |
sticker | +0.046 |
cookie | +0.044 |
icing | +0.044 |
Neg logit contributions | |
vill | -0.031 |
challenged | -0.029 |
current | -0.029 |
ot | -0.029 |
vious | -0.029 |
Token | I |
Token ID | 314 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
half | +0.034 |
sticker | +0.034 |
icing | +0.034 |
ribbon | +0.034 |
Mom | +0.032 |
Neg logit contributions | |
ot | -0.024 |
vill | -0.023 |
cient | -0.022 |
current | -0.022 |
bust | -0.020 |
Token | want |
Token ID | 765 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
Mom | +0.026 |
half | +0.026 |
icing | +0.024 |
wrist | +0.024 |
sticker | +0.024 |
Neg logit contributions | |
vill | -0.032 |
challenged | -0.032 |
vious | -0.031 |
ot | -0.031 |
current | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ushes | +0.027 |
wrist | +0.027 |
Mom | +0.027 |
kin | +0.026 |
scalp | +0.026 |
Neg logit contributions | |
vill | -0.020 |
ot | -0.020 |
padd | -0.018 |
ships | -0.018 |
fishermen | -0.018 |
Token | put |
Token ID | 1234 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ot | +0.010 |
current | +0.009 |
challenged | +0.009 |
vill | +0.009 |
padd | +0.009 |
Neg logit contributions | |
ushes | -0.011 |
Mom | -0.010 |
half | -0.009 |
Anna | -0.009 |
icing | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Mom | +0.034 |
wrist | +0.034 |
ushes | +0.033 |
scalp | +0.031 |
Her | +0.030 |
Neg logit contributions | |
ot | -0.031 |
vill | -0.031 |
ships | -0.029 |
vious | -0.028 |
padd | -0.028 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
vill | +0.034 |
ot | +0.033 |
current | +0.031 |
eagle | +0.030 |
vious | +0.030 |
Neg logit contributions | |
Mom | -0.026 |
ushes | -0.024 |
Her | -0.024 |
wrist | -0.022 |
Anna | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Mom | +0.291 |
icing | +0.261 |
ushes | +0.255 |
wrist | +0.251 |
Her | +0.250 |
Neg logit contributions | |
ot | -0.248 |
vill | -0.239 |
fishermen | -0.235 |
current | -0.229 |
vious | -0.224 |
Token | I |
Token ID | 314 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
half | +0.044 |
icing | +0.043 |
sticker | +0.041 |
ushes | +0.041 |
ribbon | +0.041 |
Neg logit contributions | |
ot | -0.025 |
vill | -0.024 |
current | -0.024 |
ranc | -0.023 |
vious | -0.022 |
Token | like |
Token ID | 588 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
half | +0.029 |
Mom | +0.029 |
sticker | +0.027 |
cookie | +0.026 |
icing | +0.026 |
Neg logit contributions | |
vill | -0.029 |
challenged | -0.027 |
current | -0.027 |
ot | -0.027 |
vious | -0.027 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.31e+00 |
Pos logit contributions | |
Mom | +0.129 |
ushes | +0.118 |
wrist | +0.116 |
ribbon | +0.110 |
half | +0.110 |
Neg logit contributions | |
vill | -0.137 |
ot | -0.136 |
ships | -0.129 |
challenged | -0.127 |
fishermen | -0.124 |
Token | ." |
Token ID | 526 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Mom | +0.307 |
bookmark | +0.282 |
wrist | +0.273 |
ribbon | +0.273 |
ushes | +0.272 |
Neg logit contributions | |
ot | -0.243 |
fishermen | -0.232 |
ranc | -0.213 |
vill | -0.211 |
ships | -0.209 |
Token | cheeks |
Token ID | 25839 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Mom | +0.035 |
half | +0.033 |
sticker | +0.031 |
ushes | +0.030 |
cookie | +0.030 |
Neg logit contributions | |
vill | -0.048 |
current | -0.047 |
ot | -0.047 |
challenged | -0.046 |
vious | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Mom | +0.034 |
half | +0.032 |
ushes | +0.031 |
wrist | +0.031 |
sticker | +0.031 |
Neg logit contributions | |
vious | -0.044 |
challenged | -0.043 |
ot | -0.042 |
vill | -0.042 |
current | -0.041 |
Token | That |
Token ID | 1320 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
half | +0.044 |
Mom | +0.042 |
sticker | +0.042 |
icing | +0.041 |
ushes | +0.040 |
Neg logit contributions | |
ot | -0.039 |
vious | -0.038 |
vill | -0.038 |
current | -0.037 |
challenged | -0.037 |
Token | is |
Token ID | 318 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
vill | +0.035 |
challenged | +0.034 |
ot | +0.034 |
current | +0.033 |
vious | +0.033 |
Neg logit contributions | |
Mom | -0.021 |
half | -0.020 |
ushes | -0.019 |
icing | -0.019 |
sticker | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Mom | +0.041 |
wrist | +0.038 |
ushes | +0.037 |
sticker | +0.037 |
half | +0.036 |
Neg logit contributions | |
ot | -0.055 |
challenged | -0.054 |
vill | -0.054 |
current | -0.052 |
fishermen | -0.051 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
ushes | +0.063 |
Mom | +0.061 |
half | +0.060 |
herself | +0.059 |
icing | +0.058 |
Neg logit contributions | |
ot | -0.057 |
vill | -0.055 |
current | -0.053 |
harbor | -0.051 |
eagle | -0.051 |
Token | ster |
Token ID | 1706 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Mom | +0.327 |
ushes | +0.310 |
half | +0.298 |
icing | +0.292 |
herself | +0.283 |
Neg logit contributions | |
ot | -0.237 |
vill | -0.217 |
fishermen | -0.209 |
current | -0.205 |
eagle | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ot | +0.073 |
vill | +0.071 |
challenged | +0.069 |
vious | +0.069 |
current | +0.067 |
Neg logit contributions | |
Mom | -0.058 |
ushes | -0.053 |
half | -0.052 |
icing | -0.049 |
ribbon | -0.048 |
Token | A |
Token ID | 317 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
half | +0.044 |
Mom | +0.043 |
ribbon | +0.042 |
ushes | +0.042 |
sticker | +0.042 |
Neg logit contributions | |
ot | -0.039 |
vill | -0.038 |
vious | -0.038 |
challenged | -0.037 |
current | -0.036 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Mom | +0.033 |
ushes | +0.031 |
half | +0.031 |
herself | +0.030 |
icing | +0.030 |
Neg logit contributions | |
vill | -0.034 |
ot | -0.033 |
current | -0.032 |
challenged | -0.032 |
eagle | -0.031 |
Token | has |
Token ID | 468 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
vill | +0.141 |
ot | +0.137 |
challenged | +0.137 |
vious | +0.135 |
current | +0.131 |
Neg logit contributions | |
Mom | -0.104 |
half | -0.098 |
ushes | -0.091 |
sticker | -0.090 |
icing | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Mom | +0.141 |
half | +0.132 |
sticker | +0.130 |
ribbon | +0.127 |
ushes | +0.123 |
Neg logit contributions | |
vill | -0.218 |
challenged | -0.211 |
current | -0.209 |
vious | -0.209 |
ot | -0.206 |
Token | It |
Token ID | 632 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
half | +0.018 |
sticker | +0.017 |
Mom | +0.017 |
ribbon | +0.017 |
icing | +0.016 |
Neg logit contributions | |
vill | -0.025 |
challenged | -0.024 |
current | -0.024 |
ot | -0.023 |
vious | -0.023 |
Token | has |
Token ID | 468 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
Mom | +0.043 |
wrist | +0.040 |
ushes | +0.039 |
half | +0.039 |
sticker | +0.038 |
Neg logit contributions | |
vill | -0.059 |
challenged | -0.056 |
ot | -0.056 |
vious | -0.054 |
current | -0.054 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
Mom | +0.133 |
wrist | +0.130 |
ushes | +0.121 |
sticker | +0.119 |
half | +0.118 |
Neg logit contributions | |
vill | -0.171 |
ot | -0.163 |
vious | -0.163 |
current | -0.162 |
challenged | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Mom | +0.221 |
ushes | +0.202 |
wrist | +0.200 |
half | +0.194 |
Elsa | +0.192 |
Neg logit contributions | |
ot | -0.171 |
vill | -0.161 |
challenged | -0.160 |
current | -0.160 |
fishermen | -0.159 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
Mom | +0.029 |
ushes | +0.029 |
rap | +0.028 |
wrist | +0.027 |
uggle | +0.026 |
Neg logit contributions | |
ot | -0.043 |
current | -0.042 |
vill | -0.041 |
ships | -0.040 |
padd | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Mom | +0.305 |
bookmark | +0.280 |
Anna | +0.280 |
wrist | +0.277 |
Elsa | +0.273 |
Neg logit contributions | |
fishermen | -0.228 |
ot | -0.226 |
challenged | -0.204 |
current | -0.204 |
ships | -0.203 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
Mom | +0.027 |
ushes | +0.026 |
wrist | +0.024 |
rap | +0.024 |
half | +0.024 |
Neg logit contributions | |
ot | -0.046 |
current | -0.045 |
vill | -0.045 |
ships | -0.043 |
challenged | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
Mom | +0.186 |
wrist | +0.162 |
bookmark | +0.161 |
Anna | +0.160 |
sticker | +0.155 |
Neg logit contributions | |
ot | -0.180 |
challenged | -0.172 |
current | -0.168 |
fishermen | -0.167 |
vill | -0.165 |
Token | It |
Token ID | 632 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
half | +0.018 |
Mom | +0.018 |
sticker | +0.018 |
icing | +0.017 |
ribbon | +0.017 |
Neg logit contributions | |
vill | -0.032 |
challenged | -0.031 |
current | -0.031 |
ot | -0.031 |
vious | -0.030 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Mom | +0.046 |
half | +0.043 |
wrist | +0.042 |
sticker | +0.042 |
ushes | +0.041 |
Neg logit contributions | |
vill | -0.059 |
ot | -0.057 |
challenged | -0.056 |
vious | -0.055 |
current | -0.055 |
Token | to |
Token ID | 284 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
Mom | +0.039 |
icing | +0.036 |
ushes | +0.034 |
wrist | +0.034 |
mm | +0.034 |
Neg logit contributions | |
padd | -0.025 |
challenged | -0.025 |
vill | -0.024 |
ot | -0.023 |
current | -0.023 |
Token | poke |
Token ID | 22620 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ot | +0.027 |
current | +0.027 |
challenged | +0.026 |
vill | +0.026 |
padd | +0.025 |
Neg logit contributions | |
Mom | -0.024 |
ushes | -0.024 |
icing | -0.023 |
half | -0.023 |
sticker | -0.022 |
Token | him |
Token ID | 683 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
sticker | +0.001 |
Mom | +0.001 |
icing | +0.001 |
ushes | +0.001 |
wrist | +0.001 |
Neg logit contributions | |
ot | -0.001 |
vill | -0.001 |
vious | -0.001 |
current | -0.001 |
challenged | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Mom | +0.029 |
icing | +0.027 |
sticker | +0.026 |
ushes | +0.025 |
Anna | +0.025 |
Neg logit contributions | |
challenged | -0.030 |
ot | -0.029 |
current | -0.029 |
vill | -0.029 |
vious | -0.028 |
Token | The |
Token ID | 383 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
half | +0.034 |
sticker | +0.033 |
Mom | +0.032 |
icing | +0.032 |
ribbon | +0.031 |
Neg logit contributions | |
vill | -0.035 |
challenged | -0.034 |
ot | -0.033 |
current | -0.033 |
vious | -0.032 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
vill | +0.026 |
ot | +0.026 |
current | +0.026 |
challenged | +0.024 |
vious | +0.023 |
Neg logit contributions | |
Mom | -0.019 |
ushes | -0.019 |
half | -0.019 |
icing | -0.018 |
wrist | -0.017 |
Token | ster |
Token ID | 1706 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Mom | +0.260 |
half | +0.237 |
icing | +0.236 |
sticker | +0.228 |
wrist | +0.228 |
Neg logit contributions | |
current | -0.282 |
ot | -0.280 |
vill | -0.279 |
challenged | -0.274 |
vious | -0.261 |
Token | bit |
Token ID | 1643 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
vill | +0.060 |
challenged | +0.057 |
current | +0.057 |
ot | +0.056 |
vious | +0.056 |
Neg logit contributions | |
Mom | -0.065 |
half | -0.064 |
sticker | -0.062 |
icing | -0.060 |
cookie | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
vill | +0.039 |
current | +0.038 |
ot | +0.038 |
challenged | +0.038 |
vious | +0.037 |
Neg logit contributions | |
Mom | -0.031 |
half | -0.031 |
sticker | -0.030 |
wrist | -0.028 |
icing | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
Mom | +0.123 |
Anna | +0.115 |
ushes | +0.108 |
icing | +0.103 |
Love | +0.102 |
Neg logit contributions | |
ot | -0.117 |
current | -0.115 |
vill | -0.108 |
padd | -0.106 |
eagle | -0.105 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Mom | +0.032 |
ushes | +0.030 |
sticker | +0.030 |
half | +0.029 |
wrist | +0.029 |
Neg logit contributions | |
current | -0.030 |
ot | -0.029 |
vill | -0.029 |
challenged | -0.029 |
padd | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Mom | +0.040 |
ushes | +0.037 |
icing | +0.036 |
sticker | +0.035 |
half | +0.035 |
Neg logit contributions | |
ot | -0.039 |
vill | -0.039 |
challenged | -0.039 |
vious | -0.039 |
current | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
half | +0.052 |
ribbon | +0.051 |
icing | +0.051 |
Mom | +0.051 |
sticker | +0.051 |
Neg logit contributions | |
vill | -0.022 |
challenged | -0.020 |
current | -0.020 |
ot | -0.020 |
vious | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Mom | +0.045 |
half | +0.044 |
sticker | +0.043 |
icing | +0.042 |
ushes | +0.041 |
Neg logit contributions | |
vill | -0.045 |
challenged | -0.043 |
ot | -0.043 |
current | -0.042 |
vious | -0.042 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Mom | +0.107 |
wrist | +0.096 |
sticker | +0.095 |
half | +0.094 |
ushes | +0.092 |
Neg logit contributions | |
vill | -0.137 |
vious | -0.135 |
challenged | -0.135 |
current | -0.134 |
ot | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Mom | +0.227 |
wrist | +0.207 |
ushes | +0.203 |
bookmark | +0.202 |
Elsa | +0.199 |
Neg logit contributions | |
ot | -0.169 |
current | -0.159 |
vious | -0.156 |
vill | -0.154 |
fishermen | -0.152 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
Mom | +0.036 |
ushes | +0.035 |
wrist | +0.034 |
rap | +0.032 |
sticker | +0.031 |
Neg logit contributions | |
ot | -0.055 |
current | -0.055 |
vill | -0.054 |
challenged | -0.051 |
vious | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Mom | +0.308 |
bookmark | +0.284 |
Anna | +0.282 |
Elsa | +0.275 |
wrist | +0.267 |
Neg logit contributions | |
ot | -0.238 |
fishermen | -0.228 |
current | -0.221 |
challenged | -0.211 |
padd | -0.208 |
Token | bread |
Token ID | 8509 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Mom | +0.035 |
ushes | +0.033 |
wrist | +0.031 |
rap | +0.030 |
sticker | +0.029 |
Neg logit contributions | |
ot | -0.059 |
current | -0.058 |
vill | -0.057 |
challenged | -0.055 |
vious | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Mom | +0.115 |
bookmark | +0.105 |
Elsa | +0.104 |
wrist | +0.104 |
Anna | +0.104 |
Neg logit contributions | |
ot | -0.101 |
current | -0.092 |
fishermen | -0.091 |
vious | -0.090 |
challenged | -0.090 |
Token | He |
Token ID | 679 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
half | +0.060 |
ribbon | +0.059 |
Mom | +0.059 |
sticker | +0.059 |
icing | +0.058 |
Neg logit contributions | |
vill | -0.029 |
vious | -0.027 |
challenged | -0.027 |
current | -0.027 |
ot | -0.026 |
Token | also |
Token ID | 635 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
vill | +0.017 |
challenged | +0.017 |
ot | +0.016 |
current | +0.016 |
vious | +0.016 |
Neg logit contributions | |
Mom | -0.025 |
half | -0.025 |
sticker | -0.024 |
icing | -0.023 |
ushes | -0.023 |
Token | needs |
Token ID | 2476 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
vill | +0.065 |
challenged | +0.063 |
vious | +0.062 |
current | +0.062 |
ot | +0.061 |
Neg logit contributions | |
Mom | -0.063 |
half | -0.062 |
sticker | -0.059 |
icing | -0.057 |
cookie | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Mom | +0.032 |
ushes | +0.030 |
half | +0.030 |
wrist | +0.029 |
icing | +0.028 |
Neg logit contributions | |
vill | -0.035 |
ot | -0.035 |
challenged | -0.035 |
ships | -0.034 |
current | -0.034 |
Token | do |
Token ID | 466 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ot | +0.022 |
current | +0.021 |
vill | +0.021 |
challenged | +0.021 |
ships | +0.020 |
Neg logit contributions | |
Mom | -0.022 |
ushes | -0.022 |
half | -0.021 |
icing | -0.020 |
bookmark | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Mom | +0.065 |
half | +0.063 |
sticker | +0.059 |
ribbon | +0.059 |
icing | +0.058 |
Neg logit contributions | |
vill | -0.107 |
challenged | -0.104 |
vious | -0.102 |
ot | -0.101 |
current | -0.100 |
Token | fl |
Token ID | 781 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Mom | +0.045 |
half | +0.044 |
sticker | +0.042 |
icing | +0.041 |
cookie | +0.040 |
Neg logit contributions | |
vill | -0.057 |
challenged | -0.055 |
current | -0.055 |
ot | -0.055 |
vious | -0.054 |
Token | ushes |
Token ID | 17237 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
vill | +0.100 |
challenged | +0.097 |
current | +0.097 |
ot | +0.096 |
vious | +0.096 |
Neg logit contributions | |
Mom | -0.042 |
half | -0.042 |
sticker | -0.039 |
icing | -0.036 |
cookie | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
wrist | +0.298 |
Mom | +0.287 |
Elsa | +0.272 |
bookmark | +0.271 |
ribbon | +0.263 |
Neg logit contributions | |
ships | -0.243 |
ot | -0.233 |
vill | -0.228 |
current | -0.216 |
vious | -0.213 |
Token | toilet |
Token ID | 16146 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
vill | +0.042 |
current | +0.040 |
challenged | +0.039 |
ot | +0.039 |
vious | +0.039 |
Neg logit contributions | |
Mom | -0.039 |
half | -0.039 |
sticker | -0.037 |
icing | -0.036 |
ribbon | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Mom | +0.001 |
half | +0.001 |
sticker | +0.001 |
ribbon | +0.001 |
icing | +0.001 |
Neg logit contributions | |
vill | -0.002 |
challenged | -0.002 |
vious | -0.002 |
current | -0.002 |
ot | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
half | +0.059 |
Mom | +0.057 |
sticker | +0.057 |
icing | +0.056 |
ribbon | +0.056 |
Neg logit contributions | |
vill | -0.041 |
challenged | -0.039 |
current | -0.038 |
ot | -0.038 |
vious | -0.037 |
Token | hears |
Token ID | 23180 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
vill | +0.019 |
challenged | +0.018 |
current | +0.018 |
ot | +0.018 |
vious | +0.018 |
Neg logit contributions | |
half | -0.015 |
Mom | -0.014 |
sticker | -0.014 |
cookie | -0.013 |
icing | -0.013 |
Token | tasty |
Token ID | 25103 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Mom | +0.060 |
half | +0.059 |
herself | +0.058 |
ushes | +0.056 |
icing | +0.056 |
Neg logit contributions | |
vill | -0.059 |
current | -0.056 |
ot | -0.056 |
challenged | -0.054 |
ranc | -0.052 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Mom | +0.106 |
ushes | +0.103 |
half | +0.092 |
herself | +0.091 |
Her | +0.088 |
Neg logit contributions | |
vill | -0.150 |
ot | -0.150 |
current | -0.146 |
challenged | -0.136 |
eagle | -0.135 |
Token | with |
Token ID | 351 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Mom | +0.133 |
ushes | +0.130 |
wrist | +0.119 |
half | +0.119 |
Elsa | +0.118 |
Neg logit contributions | |
ot | -0.117 |
challenged | -0.115 |
vill | -0.114 |
vious | -0.112 |
current | -0.111 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
Mom | +0.019 |
wrist | +0.018 |
Anna | +0.017 |
ushes | +0.017 |
bookmark | +0.017 |
Neg logit contributions | |
ot | -0.021 |
vill | -0.020 |
vious | -0.020 |
current | -0.019 |
padd | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Mom | +0.204 |
ushes | +0.188 |
wrist | +0.178 |
half | +0.176 |
sticker | +0.172 |
Neg logit contributions | |
ot | -0.195 |
current | -0.186 |
vill | -0.186 |
challenged | -0.184 |
fishermen | -0.183 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
Mom | +0.037 |
ushes | +0.033 |
wrist | +0.031 |
half | +0.031 |
sticker | +0.031 |
Neg logit contributions | |
vill | -0.062 |
ot | -0.062 |
current | -0.061 |
challenged | -0.060 |
vious | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Mom | +0.288 |
bookmark | +0.258 |
Anna | +0.257 |
wrist | +0.257 |
ribbon | +0.246 |
Neg logit contributions | |
ot | -0.252 |
fishermen | -0.249 |
current | -0.233 |
vill | -0.226 |
challenged | -0.226 |
Token | She |
Token ID | 1375 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
half | +0.061 |
sticker | +0.059 |
icing | +0.057 |
Mom | +0.057 |
ribbon | +0.056 |
Neg logit contributions | |
vill | -0.064 |
challenged | -0.060 |
vious | -0.060 |
current | -0.058 |
ot | -0.057 |
Token | feels |
Token ID | 5300 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Mom | +0.040 |
half | +0.039 |
sticker | +0.037 |
icing | +0.036 |
cookie | +0.036 |
Neg logit contributions | |
vill | -0.040 |
challenged | -0.038 |
current | -0.038 |
vious | -0.038 |
ot | -0.038 |
Token | hungry |
Token ID | 14720 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
vill | +0.089 |
ot | +0.087 |
current | +0.085 |
vious | +0.085 |
challenged | +0.084 |
Neg logit contributions | |
Mom | -0.082 |
half | -0.079 |
ribbon | -0.076 |
sticker | -0.075 |
wrist | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
vious | +0.044 |
vill | +0.044 |
current | +0.042 |
ot | +0.042 |
challenged | +0.040 |
Neg logit contributions | |
Mom | -0.049 |
ushes | -0.048 |
half | -0.045 |
Elsa | -0.045 |
wrist | -0.045 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Mom | +0.009 |
wrist | +0.009 |
ribbon | +0.009 |
bookmark | +0.009 |
sticker | +0.009 |
Neg logit contributions | |
ot | -0.011 |
vill | -0.011 |
ships | -0.011 |
vious | -0.011 |
current | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Mom | +0.207 |
wrist | +0.202 |
bookmark | +0.189 |
ushes | +0.186 |
Elsa | +0.184 |
Neg logit contributions | |
ot | -0.184 |
current | -0.176 |
vill | -0.174 |
fishermen | -0.170 |
challenged | -0.167 |
Token | ol |
Token ID | 25776 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Mom | +0.047 |
ushes | +0.044 |
wrist | +0.042 |
bookmark | +0.042 |
sticker | +0.041 |
Neg logit contributions | |
current | -0.064 |
ot | -0.063 |
vill | -0.062 |
ships | -0.060 |
challenged | -0.060 |
Token | ives |
Token ID | 1083 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
vious | +0.016 |
ot | +0.014 |
vill | +0.013 |
fishermen | +0.013 |
ules | +0.013 |
Neg logit contributions | |
wrist | -0.027 |
Mom | -0.027 |
half | -0.025 |
sticker | -0.023 |
ribbon | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
wrist | +0.097 |
Mom | +0.096 |
bookmark | +0.089 |
Elsa | +0.089 |
Anna | +0.087 |
Neg logit contributions | |
ot | -0.084 |
fishermen | -0.078 |
vill | -0.078 |
current | -0.077 |
ships | -0.076 |
Token | ham |
Token ID | 8891 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
Mom | +0.046 |
ushes | +0.041 |
wrist | +0.040 |
half | +0.039 |
rap | +0.039 |
Neg logit contributions | |
current | -0.063 |
ot | -0.063 |
vill | -0.062 |
challenged | -0.060 |
vious | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Mom | +0.287 |
bookmark | +0.267 |
wrist | +0.263 |
Elsa | +0.261 |
Anna | +0.259 |
Neg logit contributions | |
fishermen | -0.248 |
ot | -0.246 |
ships | -0.227 |
current | -0.224 |
vill | -0.219 |
Token | They |
Token ID | 1119 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
half | +0.079 |
sticker | +0.077 |
wrist | +0.075 |
ribbon | +0.075 |
bookmark | +0.075 |
Neg logit contributions | |
ot | -0.048 |
vill | -0.045 |
current | -0.042 |
challenged | -0.041 |
vious | -0.041 |
Token | see |
Token ID | 766 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Mom | +0.013 |
half | +0.013 |
sticker | +0.013 |
ushes | +0.012 |
cookie | +0.012 |
Neg logit contributions | |
vill | -0.015 |
challenged | -0.015 |
ot | -0.015 |
current | -0.015 |
vious | -0.015 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Mom | +0.009 |
wrist | +0.009 |
ribbon | +0.008 |
sticker | +0.008 |
half | +0.008 |
Neg logit contributions | |
ot | -0.011 |
vill | -0.011 |
vious | -0.011 |
ships | -0.011 |
current | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Mom | +0.090 |
ribbon | +0.089 |
wrist | +0.086 |
sticker | +0.084 |
bookmark | +0.084 |
Neg logit contributions | |
vill | -0.098 |
ot | -0.097 |
challenged | -0.096 |
vious | -0.094 |
ships | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Mom | +0.126 |
half | +0.121 |
sticker | +0.118 |
ribbon | +0.112 |
wrist | +0.111 |
Neg logit contributions | |
vill | -0.184 |
challenged | -0.178 |
current | -0.175 |
vious | -0.175 |
ot | -0.174 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
half | +0.051 |
Mom | +0.051 |
sticker | +0.050 |
cookie | +0.047 |
icing | +0.047 |
Neg logit contributions | |
vill | -0.051 |
challenged | -0.049 |
current | -0.048 |
vious | -0.048 |
ot | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Mom | +0.100 |
half | +0.097 |
sticker | +0.090 |
ushes | +0.090 |
icing | +0.089 |
Neg logit contributions | |
vill | -0.142 |
challenged | -0.140 |
ot | -0.139 |
vious | -0.138 |
current | -0.136 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
Mom | +0.012 |
wrist | +0.012 |
sticker | +0.011 |
ushes | +0.011 |
half | +0.011 |
Neg logit contributions | |
vill | -0.015 |
vious | -0.015 |
ot | -0.015 |
challenged | -0.014 |
current | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
Mom | +0.174 |
ushes | +0.159 |
half | +0.155 |
wrist | +0.154 |
sticker | +0.149 |
Neg logit contributions | |
ot | -0.213 |
vill | -0.207 |
current | -0.203 |
challenged | -0.202 |
vious | -0.199 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
Mom | +0.022 |
half | +0.020 |
sticker | +0.020 |
ushes | +0.019 |
wrist | +0.019 |
Neg logit contributions | |
vill | -0.039 |
ot | -0.039 |
current | -0.038 |
challenged | -0.038 |
vious | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
Mom | +0.273 |
Anna | +0.248 |
wrist | +0.245 |
bookmark | +0.244 |
ribbon | +0.240 |
Neg logit contributions | |
ot | -0.264 |
fishermen | -0.258 |
vill | -0.244 |
current | -0.243 |
challenged | -0.239 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
half | +0.018 |
Mom | +0.018 |
sticker | +0.017 |
cookie | +0.017 |
icing | +0.016 |
Neg logit contributions | |
vill | -0.018 |
challenged | -0.018 |
current | -0.017 |
ot | -0.017 |
vious | -0.017 |
Token | has |
Token ID | 468 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Mom | +0.122 |
half | +0.121 |
sticker | +0.116 |
icing | +0.111 |
cookie | +0.110 |
Neg logit contributions | |
vill | -0.137 |
challenged | -0.131 |
current | -0.130 |
ot | -0.129 |
vious | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Mom | +0.151 |
wrist | +0.138 |
ushes | +0.133 |
sticker | +0.133 |
half | +0.131 |
Neg logit contributions | |
vill | -0.165 |
vious | -0.162 |
challenged | -0.160 |
ot | -0.152 |
current | -0.152 |
Token | bowl |
Token ID | 9396 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
Mom | +0.055 |
herself | +0.052 |
half | +0.050 |
ushes | +0.050 |
ourselves | +0.050 |
Neg logit contributions | |
vill | -0.055 |
ot | -0.052 |
current | -0.051 |
challenged | -0.050 |
fearful | -0.048 |
Token | He |
Token ID | 1544 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
icing | +0.029 |
sticker | +0.029 |
cookie | +0.028 |
half | +0.028 |
ribbon | +0.027 |
Neg logit contributions | |
vill | -0.046 |
challenged | -0.045 |
current | -0.044 |
ot | -0.044 |
vious | -0.042 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
half | +0.015 |
Mom | +0.015 |
sticker | +0.014 |
ribbon | +0.014 |
cookie | +0.013 |
Neg logit contributions | |
vill | -0.015 |
current | -0.014 |
vious | -0.014 |
ot | -0.014 |
roads | -0.013 |
Token | some |
Token ID | 617 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
vill | +0.096 |
challenged | +0.094 |
rated | +0.092 |
bust | +0.091 |
vious | +0.090 |
Neg logit contributions | |
half | -0.042 |
Mom | -0.038 |
sticker | -0.034 |
tape | -0.033 |
herself | -0.032 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
Mom | +0.024 |
half | +0.023 |
sticker | +0.022 |
icing | +0.021 |
wrist | +0.021 |
Neg logit contributions | |
vill | -0.029 |
current | -0.028 |
ot | -0.028 |
challenged | -0.027 |
vious | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Mom | +0.180 |
wrist | +0.161 |
half | +0.161 |
ushes | +0.160 |
sticker | +0.159 |
Neg logit contributions | |
vill | -0.208 |
ot | -0.207 |
current | -0.204 |
challenged | -0.200 |
vious | -0.196 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
Mom | +0.030 |
half | +0.030 |
sticker | +0.029 |
cookie | +0.027 |
icing | +0.027 |
Neg logit contributions | |
vill | -0.043 |
challenged | -0.042 |
current | -0.041 |
ot | -0.041 |
vious | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
Mom | +0.264 |
bookmark | +0.242 |
wrist | +0.241 |
ribbon | +0.237 |
Anna | +0.237 |
Neg logit contributions | |
ot | -0.275 |
current | -0.265 |
fishermen | -0.264 |
vill | -0.262 |
challenged | -0.258 |
Token | He |
Token ID | 679 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Mom | +0.039 |
half | +0.039 |
sticker | +0.038 |
ribbon | +0.037 |
icing | +0.037 |
Neg logit contributions | |
vill | -0.022 |
ot | -0.021 |
current | -0.021 |
challenged | -0.020 |
vious | -0.020 |
Token | took |
Token ID | 1718 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
vill | +0.019 |
challenged | +0.018 |
current | +0.018 |
ot | +0.018 |
vious | +0.018 |
Neg logit contributions | |
Mom | -0.027 |
half | -0.027 |
sticker | -0.026 |
cookie | -0.025 |
icing | -0.025 |
Token | them |
Token ID | 606 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
vill | +0.024 |
ot | +0.023 |
vious | +0.023 |
current | +0.023 |
challenged | +0.022 |
Neg logit contributions | |
Mom | -0.019 |
wrist | -0.019 |
sticker | -0.018 |
ribbon | -0.017 |
ushes | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Mom | +0.012 |
wrist | +0.011 |
icing | +0.011 |
sticker | +0.011 |
Anna | +0.011 |
Neg logit contributions | |
ot | -0.010 |
vill | -0.010 |
challenged | -0.010 |
padd | -0.009 |
ships | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Anna | +0.177 |
bookmark | +0.177 |
Mom | +0.176 |
Elsa | +0.171 |
ushes | +0.171 |
Neg logit contributions | |
current | -0.126 |
padd | -0.125 |
ot | -0.120 |
overwhelmed | -0.114 |
challenged | -0.113 |
Token | put |
Token ID | 1234 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Mom | +0.048 |
ushes | +0.045 |
rap | +0.043 |
Anna | +0.043 |
half | +0.041 |
Neg logit contributions | |
current | -0.049 |
padd | -0.048 |
ot | -0.047 |
challenged | -0.045 |
ships | -0.045 |
Token | their |
Token ID | 511 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
wrist | +0.040 |
Mom | +0.038 |
Her | +0.036 |
bookmark | +0.036 |
Anna | +0.034 |
Neg logit contributions | |
ot | -0.032 |
ships | -0.030 |
vill | -0.030 |
padd | -0.030 |
current | -0.028 |
Token | tooth |
Token ID | 16162 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Mom | +0.127 |
Anna | +0.121 |
ushes | +0.119 |
etti | +0.115 |
rap | +0.113 |
Neg logit contributions | |
vill | -0.101 |
current | -0.100 |
ot | -0.099 |
fearful | -0.096 |
lonely | -0.094 |
Token | br |
Token ID | 1671 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Mom | +0.060 |
Love | +0.057 |
mm | +0.056 |
ourselves | +0.054 |
icing | +0.054 |
Neg logit contributions | |
vious | -0.058 |
vill | -0.056 |
current | -0.056 |
ling | -0.055 |
ot | -0.055 |
Token | ushes |
Token ID | 17237 |
Feature activation | +7.94e+00 |
Pos logit contributions | |
wrist | +0.028 |
Mom | +0.028 |
cookie | +0.025 |
sticker | +0.024 |
ribbon | +0.024 |
Neg logit contributions | |
vious | -0.059 |
vill | -0.058 |
ot | -0.055 |
bust | -0.054 |
challenged | -0.054 |
Token | away |
Token ID | 1497 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
wrist | +0.334 |
bookmark | +0.299 |
Mom | +0.298 |
Love | +0.295 |
Elsa | +0.292 |
Neg logit contributions | |
ot | -0.183 |
vious | -0.178 |
vill | -0.175 |
ships | -0.172 |
padd | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Mom | +0.040 |
wrist | +0.036 |
half | +0.035 |
bookmark | +0.035 |
sticker | +0.035 |
Neg logit contributions | |
ot | -0.044 |
vill | -0.044 |
current | -0.043 |
ships | -0.042 |
vious | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
sticker | +0.053 |
half | +0.052 |
ribbon | +0.052 |
bookmark | +0.051 |
icing | +0.051 |
Neg logit contributions | |
challenged | -0.035 |
current | -0.034 |
ot | -0.033 |
vill | -0.033 |
padd | -0.031 |
Token | go |
Token ID | 467 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Mom | +0.006 |
half | +0.006 |
ushes | +0.005 |
sticker | +0.005 |
icing | +0.005 |
Neg logit contributions | |
vill | -0.007 |
ot | -0.007 |
vious | -0.007 |
current | -0.006 |
challenged | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
half | +0.055 |
icing | +0.054 |
Mom | +0.054 |
ribbon | +0.053 |
wrist | +0.051 |
Neg logit contributions | |
vill | -0.057 |
challenged | -0.055 |
padd | -0.055 |
vious | -0.053 |
ot | -0.053 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Mom | +0.038 |
half | +0.038 |
sticker | +0.037 |
wrist | +0.036 |
icing | +0.036 |
Neg logit contributions | |
vill | -0.037 |
current | -0.036 |
ot | -0.035 |
challenged | -0.035 |
bust | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Mom | +0.060 |
half | +0.059 |
sticker | +0.056 |
cookie | +0.052 |
icing | +0.052 |
Neg logit contributions | |
vill | -0.092 |
challenged | -0.089 |
current | -0.089 |
ot | -0.088 |
vious | -0.088 |
Token | had |
Token ID | 550 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Mom | +0.040 |
half | +0.040 |
sticker | +0.039 |
icing | +0.037 |
wrist | +0.037 |
Neg logit contributions | |
vill | -0.044 |
challenged | -0.043 |
current | -0.042 |
ot | -0.042 |
vious | -0.042 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Mom | +0.098 |
half | +0.089 |
sticker | +0.089 |
wrist | +0.087 |
cookie | +0.084 |
Neg logit contributions | |
vill | -0.123 |
vious | -0.120 |
challenged | -0.119 |
current | -0.118 |
ot | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Mom | +0.194 |
wrist | +0.171 |
half | +0.168 |
ushes | +0.163 |
sticker | +0.163 |
Neg logit contributions | |
ot | -0.185 |
vill | -0.181 |
vious | -0.180 |
current | -0.179 |
challenged | -0.176 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
Mom | +0.032 |
wrist | +0.029 |
ushes | +0.028 |
sticker | +0.028 |
half | +0.028 |
Neg logit contributions | |
vill | -0.047 |
ot | -0.047 |
current | -0.046 |
challenged | -0.044 |
ships | -0.044 |
Token | on |
Token ID | 319 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Mom | +0.272 |
bookmark | +0.237 |
Anna | +0.237 |
half | +0.236 |
wrist | +0.235 |
Neg logit contributions | |
ot | -0.264 |
current | -0.254 |
vill | -0.253 |
challenged | -0.252 |
fishermen | -0.252 |
Token | it |
Token ID | 340 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Mom | +0.072 |
ushes | +0.068 |
wrist | +0.068 |
sticker | +0.067 |
aps | +0.066 |
Neg logit contributions | |
vill | -0.073 |
current | -0.070 |
ot | -0.069 |
ships | -0.065 |
challenged | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Mom | +0.037 |
half | +0.034 |
sticker | +0.033 |
icing | +0.032 |
ushes | +0.032 |
Neg logit contributions | |
vill | -0.048 |
challenged | -0.047 |
vious | -0.047 |
ot | -0.046 |
current | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
half | +0.032 |
sticker | +0.032 |
ribbon | +0.031 |
icing | +0.030 |
Mom | +0.030 |
Neg logit contributions | |
vill | -0.039 |
ot | -0.037 |
challenged | -0.037 |
vious | -0.036 |
current | -0.035 |
Token | did |
Token ID | 750 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Mom | +0.154 |
half | +0.154 |
sticker | +0.149 |
icing | +0.143 |
cookie | +0.142 |
Neg logit contributions | |
vill | -0.124 |
challenged | -0.120 |
ot | -0.116 |
vious | -0.116 |
current | -0.116 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
Mom | +0.097 |
half | +0.090 |
Anna | +0.084 |
Elsa | +0.080 |
Her | +0.079 |
Neg logit contributions | |
ot | -0.126 |
vill | -0.121 |
ships | -0.118 |
current | -0.116 |
harbor | -0.114 |
Token | ster |
Token ID | 1706 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Mom | +0.283 |
Love | +0.253 |
half | +0.252 |
ushes | +0.250 |
Anna | +0.249 |
Neg logit contributions | |
ot | -0.237 |
current | -0.226 |
itive | -0.223 |
vill | -0.213 |
harbor | -0.212 |
Token | cage |
Token ID | 17186 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ot | +0.071 |
current | +0.067 |
vill | +0.067 |
challenged | +0.064 |
ships | +0.064 |
Neg logit contributions | |
Mom | -0.068 |
ushes | -0.062 |
Anna | -0.060 |
half | -0.058 |
icing | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
vill | +0.042 |
current | +0.040 |
ot | +0.040 |
challenged | +0.040 |
vious | +0.040 |
Neg logit contributions | |
Mom | -0.030 |
half | -0.029 |
sticker | -0.028 |
wrist | -0.027 |
icing | -0.026 |
Token | Their |
Token ID | 5334 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
half | +0.045 |
ribbon | +0.044 |
Mom | +0.044 |
sticker | +0.044 |
icing | +0.044 |
Neg logit contributions | |
vill | -0.040 |
ot | -0.039 |
challenged | -0.038 |
current | -0.038 |
vious | -0.037 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
Mom | +0.071 |
Anna | +0.066 |
Her | +0.064 |
half | +0.063 |
Elsa | +0.063 |
Neg logit contributions | |
ot | -0.075 |
ships | -0.074 |
current | -0.072 |
vill | -0.071 |
harbor | -0.068 |
Token | ster |
Token ID | 1706 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Mom | +0.289 |
bookmark | +0.264 |
icing | +0.261 |
half | +0.261 |
wrist | +0.260 |
Neg logit contributions | |
ot | -0.230 |
current | -0.217 |
vill | -0.215 |
challenged | -0.204 |
eagle | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
vill | +0.060 |
challenged | +0.059 |
ot | +0.059 |
current | +0.057 |
ships | +0.053 |
Neg logit contributions | |
Mom | -0.075 |
half | -0.070 |
ushes | -0.069 |
sticker | -0.069 |
icing | -0.068 |
Token | Fl |
Token ID | 1610 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Mom | +0.011 |
half | +0.011 |
sticker | +0.011 |
ushes | +0.011 |
wrist | +0.011 |
Neg logit contributions | |
vill | -0.013 |
ot | -0.012 |
current | -0.012 |
challenged | -0.012 |
ships | -0.012 |
Token | uffy |
Token ID | 15352 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Mom | +0.108 |
herself | +0.096 |
half | +0.096 |
ribbon | +0.094 |
Her | +0.093 |
Neg logit contributions | |
ot | -0.080 |
vill | -0.075 |
current | -0.074 |
fishermen | -0.072 |
padd | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Mom | +0.003 |
ushes | +0.003 |
half | +0.003 |
sticker | +0.003 |
icing | +0.003 |
Neg logit contributions | |
vill | -0.003 |
challenged | -0.003 |
ot | -0.003 |
current | -0.003 |
padd | -0.002 |
Token | Do |
Token ID | 2141 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
half | +0.043 |
Mom | +0.041 |
ribbon | +0.040 |
sticker | +0.040 |
icing | +0.040 |
Neg logit contributions | |
ot | -0.036 |
vill | -0.035 |
vious | -0.034 |
challenged | -0.033 |
current | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ushes | +0.130 |
Mom | +0.125 |
sticker | +0.124 |
half | +0.122 |
icing | +0.122 |
Neg logit contributions | |
vill | -0.242 |
challenged | -0.233 |
ot | -0.226 |
vious | -0.219 |
ships | -0.215 |
Token | like |
Token ID | 588 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
vious | +0.038 |
challenged | +0.036 |
vill | +0.035 |
ot | +0.033 |
current | +0.031 |
Neg logit contributions | |
Mom | -0.081 |
half | -0.078 |
sticker | -0.076 |
icing | -0.076 |
wrist | -0.076 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
ushes | +0.122 |
Mom | +0.121 |
wrist | +0.116 |
scalp | +0.112 |
kin | +0.104 |
Neg logit contributions | |
ot | -0.134 |
vill | -0.130 |
challenged | -0.128 |
ships | -0.128 |
eagle | -0.121 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Mom | +0.235 |
half | +0.231 |
ushes | +0.225 |
icing | +0.221 |
ribbon | +0.219 |
Neg logit contributions | |
vill | -0.143 |
challenged | -0.141 |
ot | -0.141 |
vious | -0.137 |
current | -0.131 |
Token | ham |
Token ID | 8891 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
Mom | +0.038 |
ushes | +0.036 |
wrist | +0.033 |
half | +0.032 |
sticker | +0.032 |
Neg logit contributions | |
ot | -0.059 |
vill | -0.059 |
current | -0.057 |
challenged | -0.056 |
ships | -0.055 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Mom | +0.286 |
half | +0.279 |
ribbon | +0.277 |
ushes | +0.273 |
icing | +0.273 |
Neg logit contributions | |
ot | -0.231 |
fishermen | -0.221 |
challenged | -0.214 |
vill | -0.209 |
ranc | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Mom | +0.036 |
half | +0.035 |
sticker | +0.033 |
cookie | +0.031 |
icing | +0.030 |
Neg logit contributions | |
vill | -0.074 |
challenged | -0.072 |
current | -0.072 |
vious | -0.071 |
ot | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
half | +0.049 |
icing | +0.048 |
sticker | +0.047 |
cookie | +0.046 |
Mom | +0.046 |
Neg logit contributions | |
vill | -0.074 |
challenged | -0.070 |
ot | -0.068 |
current | -0.068 |
vious | -0.067 |
Token | L |
Token ID | 43 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
icing | +0.041 |
half | +0.040 |
cookie | +0.040 |
sticker | +0.039 |
wrist | +0.037 |
Neg logit contributions | |
vill | -0.078 |
challenged | -0.074 |
ot | -0.073 |
current | -0.073 |
vious | -0.073 |
Token | ila |
Token ID | 10102 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Mom | +0.034 |
half | +0.034 |
sticker | +0.033 |
cookie | +0.031 |
icing | +0.031 |
Neg logit contributions | |
vill | -0.040 |
challenged | -0.038 |
current | -0.038 |
vious | -0.038 |
ot | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
vill | +0.038 |
current | +0.036 |
challenged | +0.036 |
ot | +0.036 |
vious | +0.036 |
Neg logit contributions | |
half | -0.025 |
Mom | -0.025 |
sticker | -0.024 |
cookie | -0.023 |
icing | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
vill | +0.031 |
challenged | +0.030 |
current | +0.030 |
vious | +0.030 |
ot | +0.029 |
Neg logit contributions | |
half | -0.021 |
Mom | -0.021 |
sticker | -0.020 |
cookie | -0.019 |
icing | -0.019 |
Token | group |
Token ID | 1448 |
Feature activation | -8.54e+00 |
Pos logit contributions | |
half | +0.028 |
Mom | +0.028 |
sticker | +0.027 |
icing | +0.026 |
ushes | +0.026 |
Neg logit contributions | |
vill | -0.023 |
challenged | -0.022 |
current | -0.022 |
ot | -0.022 |
vious | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
rated | +0.399 |
current | +0.393 |
vill | +0.384 |
bust | +0.380 |
lves | +0.378 |
Neg logit contributions | |
Mom | -0.168 |
half | -0.161 |
cookie | -0.133 |
tape | -0.132 |
sticker | -0.131 |
Token | mis |
Token ID | 2984 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
half | +0.032 |
Mom | +0.032 |
sticker | +0.030 |
cookie | +0.029 |
icing | +0.028 |
Neg logit contributions | |
vill | -0.040 |
challenged | -0.039 |
current | -0.039 |
vious | -0.039 |
ot | -0.037 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
current | +0.157 |
ot | +0.145 |
vill | +0.142 |
challenged | +0.140 |
ships | +0.135 |
Neg logit contributions | |
half | -0.278 |
Mom | -0.275 |
sticker | -0.250 |
ushes | -0.245 |
wrist | -0.242 |
Token | vous |
Token ID | 31222 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
current | +0.403 |
ot | +0.357 |
ranc | +0.352 |
harbor | +0.350 |
ships | +0.341 |
Neg logit contributions | |
half | -0.534 |
Mom | -0.528 |
sticker | -0.486 |
Anna | -0.480 |
e | -0.470 |
Token | mice |
Token ID | 10693 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
roads | +0.178 |
vill | +0.176 |
challenged | +0.175 |
current | +0.173 |
ounded | +0.170 |
Neg logit contributions | |
half | -0.160 |
sticker | -0.149 |
cookie | -0.149 |
Mom | -0.144 |
icing | -0.144 |
Token | came |
Token ID | 1625 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
vill | +0.113 |
current | +0.111 |
vious | +0.105 |
bust | +0.104 |
ot | +0.102 |
Neg logit contributions | |
half | -0.091 |
sticker | -0.085 |
Mom | -0.084 |
cookie | -0.084 |
ribbon | -0.082 |
Token | by |
Token ID | 416 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
vill | +0.176 |
current | +0.171 |
vious | +0.169 |
challenged | +0.166 |
ot | +0.164 |
Neg logit contributions | |
half | -0.102 |
Mom | -0.097 |
sticker | -0.091 |
cookie | -0.086 |
herself | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
vill | +0.084 |
vious | +0.081 |
challenged | +0.080 |
current | +0.080 |
ot | +0.079 |
Neg logit contributions | |
half | -0.058 |
Mom | -0.056 |
sticker | -0.053 |
cookie | -0.051 |
ribbon | -0.050 |
Token | so |
Token ID | 523 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Mom | +0.054 |
half | +0.054 |
sticker | +0.052 |
cookie | +0.048 |
icing | +0.047 |
Neg logit contributions | |
vill | -0.114 |
challenged | -0.110 |
vious | -0.109 |
current | -0.109 |
ot | -0.109 |
Token | that |
Token ID | 326 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
vill | +0.109 |
challenged | +0.104 |
vious | +0.104 |
ot | +0.102 |
current | +0.102 |
Neg logit contributions | |
Mom | -0.140 |
half | -0.138 |
sticker | -0.134 |
cookie | -0.127 |
icing | -0.126 |
Token | no |
Token ID | 645 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
vill | +0.068 |
challenged | +0.065 |
current | +0.064 |
ot | +0.064 |
vious | +0.063 |
Neg logit contributions | |
Mom | -0.090 |
half | -0.090 |
sticker | -0.087 |
icing | -0.084 |
cookie | -0.084 |
Token | more |
Token ID | 517 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
vill | +0.001 |
challenged | +0.001 |
ot | +0.001 |
current | +0.001 |
vious | +0.001 |
Neg logit contributions | |
Mom | -0.001 |
half | -0.001 |
sticker | -0.001 |
ushes | -0.001 |
icing | -0.001 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
half | +0.122 |
Mom | +0.120 |
sticker | +0.118 |
cookie | +0.112 |
icing | +0.111 |
Neg logit contributions | |
vill | -0.131 |
challenged | -0.125 |
vious | -0.123 |
current | -0.123 |
ot | -0.122 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
current | +0.153 |
ships | +0.150 |
harbor | +0.148 |
vill | +0.148 |
challenged | +0.147 |
Neg logit contributions | |
half | -0.250 |
Mom | -0.239 |
sticker | -0.227 |
ra | -0.216 |
ushes | -0.214 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
current | +0.344 |
ot | +0.336 |
harbor | +0.330 |
ships | +0.322 |
ranc | +0.311 |
Neg logit contributions | |
half | -0.556 |
Mom | -0.535 |
sticker | -0.524 |
Anna | -0.500 |
cookie | -0.490 |
Token | mice |
Token ID | 10693 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
vill | +0.164 |
challenged | +0.162 |
vious | +0.158 |
current | +0.153 |
ot | +0.152 |
Neg logit contributions | |
half | -0.152 |
sticker | -0.147 |
cookie | -0.143 |
Mom | -0.142 |
ribbon | -0.139 |
Token | could |
Token ID | 714 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
vill | +0.102 |
current | +0.099 |
ot | +0.095 |
vious | +0.095 |
challenged | +0.095 |
Neg logit contributions | |
half | -0.077 |
sticker | -0.075 |
Mom | -0.073 |
ribbon | -0.071 |
cookie | -0.071 |
Token | come |
Token ID | 1282 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Mom | +0.091 |
half | +0.091 |
sticker | +0.086 |
icing | +0.083 |
cookie | +0.082 |
Neg logit contributions | |
vill | -0.134 |
challenged | -0.129 |
current | -0.129 |
ot | -0.128 |
vious | -0.127 |
Token | in |
Token ID | 287 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Mom | +0.015 |
half | +0.015 |
sticker | +0.014 |
icing | +0.013 |
cookie | +0.013 |
Neg logit contributions | |
vill | -0.022 |
challenged | -0.021 |
current | -0.021 |
ot | -0.021 |
vious | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
vill | +0.010 |
ot | +0.010 |
challenged | +0.010 |
current | +0.010 |
vious | +0.010 |
Neg logit contributions | |
Mom | -0.007 |
half | -0.007 |
sticker | -0.007 |
ushes | -0.006 |
icing | -0.006 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
vill | +0.048 |
challenged | +0.047 |
vious | +0.046 |
current | +0.045 |
ot | +0.044 |
Neg logit contributions | |
Mom | -0.067 |
half | -0.067 |
sticker | -0.064 |
cookie | -0.062 |
ribbon | -0.061 |
Token | got |
Token ID | 1392 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
vill | +0.155 |
current | +0.144 |
Jon | +0.143 |
Anch | +0.140 |
ules | +0.139 |
Neg logit contributions | |
half | -0.146 |
Mom | -0.135 |
cookie | -0.129 |
gently | -0.125 |
sticker | -0.123 |
Token | a |
Token ID | 257 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
vill | +0.017 |
current | +0.017 |
challenged | +0.016 |
vious | +0.016 |
ot | +0.016 |
Neg logit contributions | |
half | -0.016 |
Mom | -0.016 |
sticker | -0.015 |
cookie | -0.015 |
icing | -0.014 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
half | +0.031 |
sticker | +0.030 |
Mom | +0.030 |
cookie | +0.029 |
ribbon | +0.028 |
Neg logit contributions | |
vill | -0.036 |
challenged | -0.035 |
vious | -0.035 |
current | -0.034 |
ot | -0.034 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
challenged | +0.130 |
ships | +0.129 |
current | +0.128 |
vill | +0.127 |
ot | +0.123 |
Neg logit contributions | |
half | -0.243 |
Mom | -0.237 |
sticker | -0.222 |
ushes | -0.215 |
wrist | -0.210 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
current | +0.335 |
harbor | +0.334 |
ships | +0.323 |
ranc | +0.320 |
ot | +0.306 |
Neg logit contributions | |
half | -0.547 |
Mom | -0.520 |
sticker | -0.499 |
cookie | -0.478 |
Anna | -0.471 |
Token | look |
Token ID | 804 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
bust | +0.147 |
cient | +0.144 |
roads | +0.144 |
vill | +0.143 |
challenged | +0.142 |
Neg logit contributions | |
half | -0.148 |
cookie | -0.142 |
sticker | -0.141 |
ribbon | -0.134 |
Mom | -0.125 |
Token | in |
Token ID | 287 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
vill | +0.125 |
current | +0.123 |
bust | +0.120 |
challenged | +0.118 |
ot | +0.115 |
Neg logit contributions | |
half | -0.059 |
sticker | -0.053 |
Mom | -0.052 |
cookie | -0.049 |
herself | -0.047 |
Token | its |
Token ID | 663 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
vill | +0.001 |
current | +0.001 |
challenged | +0.001 |
ot | +0.001 |
vious | +0.001 |
Neg logit contributions | |
Mom | -0.001 |
half | -0.001 |
sticker | -0.001 |
icing | -0.001 |
cookie | -0.001 |
Token | eye |
Token ID | 4151 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Mom | +0.071 |
half | +0.068 |
sticker | +0.067 |
icing | +0.066 |
cookie | +0.063 |
Neg logit contributions | |
vill | -0.094 |
current | -0.093 |
ot | -0.092 |
challenged | -0.089 |
vious | -0.089 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Mom | +0.023 |
half | +0.022 |
ushes | +0.021 |
sticker | +0.021 |
icing | +0.021 |
Neg logit contributions | |
vill | -0.025 |
ot | -0.024 |
current | -0.024 |
challenged | -0.023 |
vious | -0.023 |
Token | tune |
Token ID | 14009 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Mom | +0.080 |
half | +0.078 |
sticker | +0.073 |
ushes | +0.073 |
icing | +0.070 |
Neg logit contributions | |
vill | -0.094 |
ot | -0.090 |
current | -0.088 |
challenged | -0.088 |
vious | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
vill | +0.071 |
challenged | +0.068 |
current | +0.067 |
ot | +0.067 |
vious | +0.067 |
Neg logit contributions | |
Mom | -0.056 |
half | -0.056 |
sticker | -0.054 |
cookie | -0.051 |
icing | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
vill | +0.033 |
challenged | +0.031 |
current | +0.031 |
ot | +0.031 |
vious | +0.031 |
Neg logit contributions | |
Mom | -0.019 |
half | -0.019 |
sticker | -0.018 |
icing | -0.017 |
cookie | -0.016 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
Mom | +0.026 |
half | +0.026 |
sticker | +0.025 |
cookie | +0.024 |
ribbon | +0.024 |
Neg logit contributions | |
vill | -0.023 |
challenged | -0.022 |
vious | -0.022 |
current | -0.022 |
ot | -0.021 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
vill | +0.115 |
current | +0.114 |
challenged | +0.114 |
ot | +0.110 |
ships | +0.105 |
Neg logit contributions | |
Mom | -0.264 |
half | -0.262 |
sticker | -0.248 |
wrist | -0.241 |
ribbon | -0.241 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
current | +0.315 |
harbor | +0.297 |
ot | +0.293 |
ranc | +0.292 |
ships | +0.289 |
Neg logit contributions | |
Mom | -0.541 |
half | -0.529 |
sticker | -0.497 |
Anna | -0.496 |
e | -0.471 |
Token | fox |
Token ID | 21831 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
challenged | +0.135 |
vious | +0.135 |
roads | +0.132 |
vill | +0.129 |
ships | +0.126 |
Neg logit contributions | |
sticker | -0.147 |
half | -0.145 |
cookie | -0.143 |
ribbon | -0.139 |
Mom | -0.139 |
Token | appeared |
Token ID | 4120 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
vill | +0.149 |
current | +0.142 |
vious | +0.142 |
ot | +0.133 |
bust | +0.131 |
Neg logit contributions | |
half | -0.186 |
Mom | -0.182 |
sticker | -0.177 |
ribbon | -0.172 |
cookie | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
vill | +0.043 |
challenged | +0.041 |
current | +0.041 |
ot | +0.041 |
vious | +0.041 |
Neg logit contributions | |
Mom | -0.029 |
half | -0.029 |
sticker | -0.028 |
icing | -0.026 |
cookie | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
vill | +0.022 |
current | +0.021 |
challenged | +0.021 |
vious | +0.021 |
ot | +0.021 |
Neg logit contributions | |
Mom | -0.017 |
half | -0.017 |
sticker | -0.016 |
cookie | -0.016 |
icing | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Mom | +0.033 |
half | +0.032 |
sticker | +0.028 |
herself | +0.028 |
wrist | +0.026 |
Neg logit contributions | |
vill | -0.060 |
challenged | -0.059 |
vious | -0.059 |
current | -0.058 |
ot | -0.056 |
Token | replied |
Token ID | 8712 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
vill | +0.009 |
vious | +0.009 |
current | +0.009 |
enced | +0.009 |
ot | +0.008 |
Neg logit contributions | |
Mom | -0.009 |
half | -0.009 |
ribbon | -0.008 |
sticker | -0.008 |
herself | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
vious | +0.106 |
vill | +0.106 |
current | +0.104 |
challenged | +0.103 |
ot | +0.102 |
Neg logit contributions | |
half | -0.067 |
Mom | -0.066 |
sticker | -0.063 |
cookie | -0.060 |
herself | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
vill | +0.020 |
challenged | +0.019 |
current | +0.019 |
ot | +0.019 |
vious | +0.019 |
Neg logit contributions | |
half | -0.012 |
Mom | -0.012 |
sticker | -0.011 |
icing | -0.010 |
cookie | -0.010 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
half | +0.014 |
sticker | +0.014 |
Mom | +0.014 |
cookie | +0.013 |
ribbon | +0.013 |
Neg logit contributions | |
vious | -0.022 |
vill | -0.021 |
ot | -0.021 |
challenged | -0.021 |
current | -0.021 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.131 |
ot | +0.129 |
challenged | +0.128 |
ships | +0.126 |
harbor | +0.123 |
Neg logit contributions | |
half | -0.235 |
Mom | -0.232 |
sticker | -0.222 |
ushes | -0.218 |
wrist | -0.212 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
current | +0.319 |
harbor | +0.310 |
ot | +0.301 |
ships | +0.291 |
ranc | +0.288 |
Neg logit contributions | |
half | -0.541 |
Mom | -0.521 |
sticker | -0.497 |
Anna | -0.482 |
cookie | -0.474 |
Token | gl |
Token ID | 1278 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
lves | +0.169 |
challenged | +0.165 |
vious | +0.165 |
roads | +0.162 |
ships | +0.162 |
Neg logit contributions | |
half | -0.109 |
sticker | -0.109 |
cookie | -0.106 |
ribbon | -0.100 |
brush | -0.095 |
Token | int |
Token ID | 600 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
challenged | +0.165 |
vill | +0.164 |
current | +0.162 |
ot | +0.159 |
ships | +0.151 |
Neg logit contributions | |
sticker | -0.150 |
half | -0.145 |
Mom | -0.140 |
ushes | -0.140 |
ribbon | -0.136 |
Token | in |
Token ID | 287 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
vill | +0.107 |
challenged | +0.106 |
lves | +0.102 |
current | +0.101 |
ot | +0.100 |
Neg logit contributions | |
half | -0.095 |
Mom | -0.090 |
sticker | -0.090 |
ribbon | -0.084 |
icing | -0.083 |
Token | his |
Token ID | 465 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
vill | +0.001 |
challenged | +0.001 |
vious | +0.001 |
current | +0.001 |
ot | +0.001 |
Neg logit contributions | |
half | -0.001 |
Mom | -0.001 |
sticker | -0.001 |
ribbon | -0.001 |
cookie | -0.001 |
Token | But |
Token ID | 1537 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
sticker | +0.003 |
half | +0.003 |
icing | +0.003 |
cookie | +0.002 |
wrist | +0.002 |
Neg logit contributions | |
vill | -0.004 |
challenged | -0.004 |
ot | -0.004 |
vious | -0.004 |
current | -0.004 |
Token | then |
Token ID | 788 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Mom | +0.011 |
half | +0.011 |
sticker | +0.011 |
icing | +0.011 |
ushes | +0.010 |
Neg logit contributions | |
vill | -0.013 |
challenged | -0.013 |
ot | -0.012 |
current | -0.012 |
vious | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
half | +0.060 |
Mom | +0.058 |
sticker | +0.055 |
cookie | +0.052 |
ribbon | +0.051 |
Neg logit contributions | |
vill | -0.094 |
vious | -0.092 |
current | -0.091 |
challenged | -0.091 |
ot | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
vill | +0.019 |
challenged | +0.018 |
vious | +0.018 |
current | +0.018 |
ot | +0.018 |
Neg logit contributions | |
half | -0.012 |
Mom | -0.012 |
sticker | -0.012 |
cookie | -0.011 |
ribbon | -0.011 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
half | +0.033 |
Mom | +0.032 |
sticker | +0.032 |
cookie | +0.031 |
ribbon | +0.030 |
Neg logit contributions | |
challenged | -0.029 |
vill | -0.028 |
vious | -0.028 |
current | -0.027 |
ot | -0.027 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.123 |
challenged | +0.121 |
ot | +0.119 |
ships | +0.118 |
vill | +0.118 |
Neg logit contributions | |
Mom | -0.246 |
half | -0.245 |
sticker | -0.228 |
ushes | -0.224 |
wrist | -0.221 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
current | +0.331 |
ships | +0.328 |
harbor | +0.327 |
ranc | +0.319 |
ot | +0.313 |
Neg logit contributions | |
Mom | -0.510 |
half | -0.505 |
Anna | -0.470 |
sticker | -0.458 |
e | -0.439 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
challenged | +0.138 |
roads | +0.134 |
ships | +0.132 |
vious | +0.132 |
cient | +0.128 |
Neg logit contributions | |
cookie | -0.141 |
sticker | -0.141 |
half | -0.140 |
Mom | -0.132 |
ribbon | -0.132 |
Token | came |
Token ID | 1625 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
vill | +0.129 |
vious | +0.126 |
current | +0.123 |
bust | +0.122 |
ounded | +0.120 |
Neg logit contributions | |
half | -0.158 |
Mom | -0.154 |
cookie | -0.144 |
ribbon | -0.144 |
sticker | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
vill | +0.133 |
current | +0.128 |
vious | +0.127 |
challenged | +0.126 |
ot | +0.125 |
Neg logit contributions | |
half | -0.097 |
Mom | -0.096 |
sticker | -0.088 |
ribbon | -0.083 |
cookie | -0.083 |
Token | started |
Token ID | 2067 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
half | +0.006 |
Mom | +0.005 |
cookie | +0.005 |
ribbon | +0.005 |
gently | +0.005 |
Neg logit contributions | |
vious | -0.005 |
vill | -0.005 |
current | -0.005 |
harbor | -0.005 |
enced | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
vill | +0.008 |
challenged | +0.007 |
vious | +0.007 |
ot | +0.007 |
bust | +0.007 |
Neg logit contributions | |
sticker | -0.007 |
half | -0.007 |
icing | -0.006 |
ribbon | -0.006 |
Mom | -0.006 |
Token | Peter |
Token ID | 19727 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
half | +0.001 |
sticker | +0.001 |
Mom | +0.001 |
icing | +0.001 |
ribbon | +0.001 |
Neg logit contributions | |
vill | -0.001 |
challenged | -0.001 |
vious | -0.001 |
ot | -0.001 |
current | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
vill | +0.093 |
current | +0.091 |
vious | +0.088 |
ot | +0.086 |
challenged | +0.085 |
Neg logit contributions | |
half | -0.080 |
Mom | -0.079 |
sticker | -0.075 |
cookie | -0.071 |
icing | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
vill | +0.054 |
current | +0.052 |
ot | +0.050 |
challenged | +0.050 |
vious | +0.050 |
Neg logit contributions | |
Mom | -0.044 |
half | -0.044 |
sticker | -0.042 |
cookie | -0.040 |
icing | -0.040 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
Mom | +0.029 |
half | +0.028 |
sticker | +0.028 |
cookie | +0.027 |
ribbon | +0.026 |
Neg logit contributions | |
vious | -0.024 |
challenged | -0.024 |
vill | -0.024 |
current | -0.023 |
roads | -0.022 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.123 |
challenged | +0.120 |
ot | +0.115 |
vill | +0.115 |
ships | +0.110 |
Neg logit contributions | |
Mom | -0.249 |
half | -0.244 |
sticker | -0.230 |
wrist | -0.225 |
ushes | -0.222 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
current | +0.313 |
ot | +0.267 |
challenged | +0.264 |
harbor | +0.259 |
ranc | +0.256 |
Neg logit contributions | |
Mom | -0.550 |
half | -0.534 |
sticker | -0.521 |
Anna | -0.501 |
cookie | -0.496 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
roads | +0.138 |
challenged | +0.137 |
vious | +0.132 |
current | +0.131 |
vill | +0.128 |
Neg logit contributions | |
half | -0.140 |
sticker | -0.140 |
Mom | -0.139 |
cookie | -0.139 |
ribbon | -0.131 |
Token | year |
Token ID | 614 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
current | +0.220 |
bust | +0.212 |
challenged | +0.206 |
ounded | +0.203 |
cient | +0.203 |
Neg logit contributions | |
Mom | -0.152 |
half | -0.148 |
cookie | -0.138 |
sticker | -0.135 |
wrist | -0.129 |
Token | old |
Token ID | 1468 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
challenged | +0.211 |
current | +0.205 |
vill | +0.199 |
vious | +0.195 |
ot | +0.193 |
Neg logit contributions | |
Mom | -0.186 |
sticker | -0.182 |
half | -0.181 |
icing | -0.167 |
cookie | -0.165 |
Token | who |
Token ID | 508 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
vious | +0.072 |
current | +0.072 |
vill | +0.071 |
challenged | +0.069 |
bust | +0.067 |
Neg logit contributions | |
Mom | -0.060 |
half | -0.059 |
sticker | -0.059 |
wrist | -0.055 |
cookie | -0.055 |
Token | The |
Token ID | 383 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
vill | +0.004 |
challenged | +0.004 |
current | +0.004 |
vious | +0.004 |
ot | +0.004 |
Neg logit contributions | |
Mom | -0.002 |
half | -0.002 |
sticker | -0.002 |
cookie | -0.002 |
icing | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
vill | +0.040 |
challenged | +0.038 |
current | +0.038 |
vious | +0.037 |
ot | +0.037 |
Neg logit contributions | |
Mom | -0.048 |
half | -0.048 |
sticker | -0.047 |
cookie | -0.045 |
icing | -0.044 |
Token | boy |
Token ID | 2933 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
vill | +0.080 |
challenged | +0.078 |
current | +0.076 |
vious | +0.076 |
ot | +0.074 |
Neg logit contributions | |
half | -0.094 |
Mom | -0.091 |
sticker | -0.088 |
cookie | -0.087 |
ribbon | -0.085 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
vill | +0.147 |
current | +0.144 |
vious | +0.140 |
ot | +0.139 |
harbor | +0.132 |
Neg logit contributions | |
half | -0.171 |
Mom | -0.168 |
sticker | -0.159 |
cookie | -0.153 |
ribbon | -0.152 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
Mom | +0.034 |
half | +0.034 |
sticker | +0.032 |
ribbon | +0.029 |
cookie | +0.029 |
Neg logit contributions | |
vill | -0.062 |
challenged | -0.060 |
current | -0.059 |
vious | -0.059 |
ot | -0.059 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.138 |
vill | +0.136 |
ot | +0.132 |
harbor | +0.131 |
challenged | +0.131 |
Neg logit contributions | |
half | -0.231 |
Mom | -0.226 |
sticker | -0.210 |
ushes | -0.208 |
wrist | -0.204 |
Token | v |
Token ID | 85 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
harbor | +0.357 |
current | +0.354 |
ranc | +0.336 |
ot | +0.331 |
ships | +0.323 |
Neg logit contributions | |
half | -0.521 |
Mom | -0.493 |
sticker | -0.462 |
cookie | -0.442 |
Anna | -0.442 |
Token | ously |
Token ID | 3481 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
vill | +0.027 |
current | +0.026 |
challenged | +0.026 |
bust | +0.025 |
ot | +0.025 |
Neg logit contributions | |
half | -0.033 |
Mom | -0.032 |
sticker | -0.029 |
cookie | -0.028 |
herself | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
vill | +0.198 |
vious | +0.189 |
current | +0.188 |
ot | +0.186 |
challenged | +0.186 |
Neg logit contributions | |
half | -0.098 |
Mom | -0.094 |
sticker | -0.089 |
ribbon | -0.083 |
cookie | -0.083 |
Token | said |
Token ID | 531 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
vious | +0.003 |
vill | +0.003 |
current | +0.003 |
ot | +0.003 |
challenged | +0.003 |
Neg logit contributions | |
half | -0.003 |
Mom | -0.003 |
sticker | -0.003 |
ribbon | -0.003 |
cookie | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
vill | +0.058 |
challenged | +0.055 |
current | +0.054 |
ot | +0.054 |
vious | +0.054 |
Neg logit contributions | |
Mom | -0.052 |
half | -0.051 |
sticker | -0.049 |
icing | -0.047 |
ribbon | -0.047 |
Token | always |
Token ID | 1464 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
vill | +0.090 |
current | +0.087 |
ot | +0.084 |
vious | +0.084 |
challenged | +0.081 |
Neg logit contributions | |
half | -0.097 |
Mom | -0.096 |
sticker | -0.093 |
cookie | -0.089 |
ribbon | -0.087 |
Token | acted |
Token ID | 13134 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
vill | +0.007 |
current | +0.007 |
ot | +0.007 |
vious | +0.007 |
challenged | +0.007 |
Neg logit contributions | |
half | -0.009 |
Mom | -0.009 |
sticker | -0.009 |
cookie | -0.009 |
ribbon | -0.009 |
Token | silly |
Token ID | 14397 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
vill | +0.151 |
current | +0.145 |
challenged | +0.144 |
ot | +0.143 |
vious | +0.141 |
Neg logit contributions | |
half | -0.121 |
Mom | -0.119 |
sticker | -0.116 |
cookie | -0.108 |
ribbon | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
vill | +0.019 |
challenged | +0.019 |
current | +0.018 |
ot | +0.018 |
vious | +0.018 |
Neg logit contributions | |
Mom | -0.011 |
half | -0.011 |
sticker | -0.010 |
icing | -0.009 |
cookie | -0.009 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
vill | +0.002 |
current | +0.002 |
ot | +0.002 |
challenged | +0.002 |
vious | +0.002 |
Neg logit contributions | |
half | -0.002 |
Mom | -0.002 |
sticker | -0.002 |
cookie | -0.001 |
ribbon | -0.001 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.140 |
vill | +0.138 |
ot | +0.135 |
ships | +0.129 |
harbor | +0.128 |
Neg logit contributions | |
half | -0.235 |
Mom | -0.231 |
sticker | -0.215 |
ushes | -0.211 |
wrist | -0.211 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
current | +0.322 |
harbor | +0.301 |
ot | +0.296 |
ranc | +0.286 |
vill | +0.278 |
Neg logit contributions | |
half | -0.553 |
Mom | -0.535 |
sticker | -0.515 |
Anna | -0.498 |
cookie | -0.486 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
vill | +0.173 |
challenged | +0.167 |
current | +0.166 |
vious | +0.165 |
ot | +0.163 |
Neg logit contributions | |
half | -0.102 |
sticker | -0.097 |
Mom | -0.097 |
cookie | -0.092 |
ribbon | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
vill | +0.021 |
challenged | +0.020 |
current | +0.020 |
ot | +0.019 |
vious | +0.019 |
Neg logit contributions | |
half | -0.015 |
Mom | -0.015 |
sticker | -0.014 |
icing | -0.013 |
ribbon | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
half | +0.002 |
Mom | +0.002 |
sticker | +0.002 |
icing | +0.002 |
ribbon | +0.002 |
Neg logit contributions | |
vill | -0.005 |
challenged | -0.004 |
current | -0.004 |
ot | -0.004 |
vious | -0.004 |
Token | One |
Token ID | 3198 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
half | +0.001 |
Mom | +0.001 |
sticker | +0.001 |
icing | +0.001 |
cookie | +0.001 |
Neg logit contributions | |
vill | -0.002 |
challenged | -0.002 |
current | -0.002 |
ot | -0.002 |
vious | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
half | +0.000 |
Mom | +0.000 |
sticker | +0.000 |
icing | +0.000 |
ribbon | +0.000 |
Neg logit contributions | |
vill | -0.001 |
challenged | -0.000 |
current | -0.000 |
ot | -0.000 |
vious | -0.000 |
Token | One |
Token ID | 3198 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
vill | +0.000 |
challenged | +0.000 |
current | +0.000 |
ot | +0.000 |
vious | +0.000 |
Neg logit contributions | |
Mom | -0.000 |
half | -0.000 |
sticker | -0.000 |
cookie | -0.000 |
icing | -0.000 |
Token | day |
Token ID | 1110 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Mom | +0.047 |
half | +0.047 |
sticker | +0.045 |
cookie | +0.043 |
icing | +0.042 |
Neg logit contributions | |
vill | -0.055 |
challenged | -0.053 |
current | -0.053 |
vious | -0.052 |
ot | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
vill | +0.021 |
vious | +0.021 |
current | +0.020 |
challenged | +0.020 |
bust | +0.020 |
Neg logit contributions | |
half | -0.012 |
Mom | -0.012 |
sticker | -0.011 |
cookie | -0.011 |
icing | -0.010 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Mom | +0.031 |
half | +0.031 |
sticker | +0.030 |
cookie | +0.029 |
ribbon | +0.028 |
Neg logit contributions | |
vill | -0.028 |
challenged | -0.027 |
vious | -0.026 |
current | -0.026 |
ot | -0.026 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
current | +0.109 |
vill | +0.108 |
challenged | +0.106 |
ot | +0.105 |
ships | +0.099 |
Neg logit contributions | |
half | -0.258 |
Mom | -0.258 |
sticker | -0.246 |
ribbon | -0.235 |
wrist | -0.235 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
current | +0.302 |
ot | +0.283 |
harbor | +0.282 |
ships | +0.278 |
ranc | +0.273 |
Neg logit contributions | |
Mom | -0.553 |
half | -0.549 |
sticker | -0.517 |
Anna | -0.513 |
cookie | -0.493 |
Token | monkey |
Token ID | 21657 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
roads | +0.133 |
vious | +0.132 |
challenged | +0.131 |
vill | +0.126 |
ships | +0.124 |
Neg logit contributions | |
cookie | -0.146 |
sticker | -0.144 |
half | -0.142 |
ribbon | -0.134 |
Mom | -0.134 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
current | +0.035 |
vill | +0.034 |
daunting | +0.033 |
hurricane | +0.032 |
bust | +0.032 |
Neg logit contributions | |
half | -0.036 |
Mom | -0.032 |
sticker | -0.032 |
cookie | -0.031 |
tape | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
bust | +0.133 |
vill | +0.132 |
rated | +0.131 |
current | +0.131 |
vious | +0.130 |
Neg logit contributions | |
half | -0.057 |
Mom | -0.046 |
herself | -0.045 |
cookie | -0.044 |
sticker | -0.044 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
vill | +0.065 |
ot | +0.062 |
current | +0.062 |
challenged | +0.062 |
vious | +0.061 |
Neg logit contributions | |
Mom | -0.084 |
half | -0.082 |
sticker | -0.078 |
ushes | -0.078 |
icing | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
vill | +0.019 |
ot | +0.018 |
challenged | +0.018 |
current | +0.018 |
vious | +0.017 |
Neg logit contributions | |
half | -0.024 |
Mom | -0.023 |
sticker | -0.023 |
icing | -0.022 |
ushes | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
vill | +0.019 |
ot | +0.018 |
challenged | +0.018 |
current | +0.018 |
vious | +0.018 |
Neg logit contributions | |
Mom | -0.023 |
half | -0.023 |
sticker | -0.022 |
ushes | -0.022 |
ribbon | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
vill | +0.056 |
current | +0.054 |
challenged | +0.054 |
vious | +0.053 |
ot | +0.053 |
Neg logit contributions | |
Mom | -0.058 |
half | -0.058 |
sticker | -0.056 |
cookie | -0.054 |
icing | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
vill | +0.063 |
current | +0.063 |
challenged | +0.062 |
vious | +0.062 |
ot | +0.059 |
Neg logit contributions | |
half | -0.031 |
Mom | -0.030 |
sticker | -0.030 |
cookie | -0.028 |
icing | -0.026 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Mom | +0.025 |
half | +0.025 |
sticker | +0.024 |
cookie | +0.023 |
icing | +0.023 |
Neg logit contributions | |
vill | -0.024 |
challenged | -0.023 |
current | -0.022 |
vious | -0.022 |
ot | -0.022 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
challenged | +0.107 |
vill | +0.106 |
current | +0.106 |
ot | +0.098 |
vious | +0.096 |
Neg logit contributions | |
Mom | -0.255 |
half | -0.254 |
sticker | -0.242 |
wrist | -0.236 |
icing | -0.233 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
current | +0.274 |
challenged | +0.245 |
vill | +0.234 |
ot | +0.227 |
padd | +0.227 |
Neg logit contributions | |
Mom | -0.581 |
half | -0.564 |
sticker | -0.560 |
cookie | -0.541 |
Anna | -0.532 |
Token | little |
Token ID | 1310 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
roads | +0.141 |
challenged | +0.139 |
vious | +0.136 |
vill | +0.132 |
current | +0.132 |
Neg logit contributions | |
cookie | -0.136 |
Mom | -0.133 |
sticker | -0.132 |
half | -0.132 |
ribbon | -0.123 |
Token | baby |
Token ID | 5156 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
challenged | +0.089 |
vill | +0.087 |
roads | +0.083 |
vious | +0.082 |
current | +0.080 |
Neg logit contributions | |
half | -0.109 |
cookie | -0.109 |
sticker | -0.109 |
Mom | -0.107 |
ribbon | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
vill | +0.026 |
ot | +0.025 |
challenged | +0.025 |
current | +0.025 |
vious | +0.025 |
Neg logit contributions | |
half | -0.017 |
Mom | -0.017 |
sticker | -0.017 |
icing | -0.016 |
ushes | -0.016 |
Token | always |
Token ID | 1464 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
vill | +0.003 |
current | +0.003 |
vious | +0.003 |
challenged | +0.003 |
ot | +0.003 |
Neg logit contributions | |
Mom | -0.003 |
half | -0.003 |
sticker | -0.003 |
cookie | -0.003 |
herself | -0.003 |
Token | small |
Token ID | 1402 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Mom | +0.024 |
half | +0.024 |
sticker | +0.023 |
icing | +0.023 |
ushes | +0.023 |
Neg logit contributions | |
vill | -0.023 |
ot | -0.022 |
current | -0.022 |
challenged | -0.022 |
vious | -0.020 |
Token | boy |
Token ID | 2933 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
half | +0.005 |
Mom | +0.005 |
sticker | +0.005 |
cookie | +0.005 |
icing | +0.005 |
Neg logit contributions | |
vill | -0.005 |
challenged | -0.005 |
current | -0.005 |
vious | -0.005 |
ot | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
vill | +0.174 |
challenged | +0.167 |
current | +0.165 |
ot | +0.164 |
vious | +0.164 |
Neg logit contributions | |
Mom | -0.155 |
half | -0.155 |
sticker | -0.149 |
cookie | -0.141 |
icing | -0.141 |
Token | a |
Token ID | 257 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
vill | +0.009 |
challenged | +0.009 |
current | +0.009 |
ot | +0.009 |
vious | +0.009 |
Neg logit contributions | |
half | -0.005 |
Mom | -0.005 |
sticker | -0.005 |
cookie | -0.005 |
icing | -0.005 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
Mom | +0.023 |
half | +0.023 |
sticker | +0.021 |
icing | +0.021 |
ushes | +0.021 |
Neg logit contributions | |
vill | -0.025 |
challenged | -0.024 |
current | -0.024 |
ot | -0.024 |
vious | -0.023 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
vill | +0.112 |
current | +0.111 |
challenged | +0.111 |
ot | +0.108 |
ships | +0.100 |
Neg logit contributions | |
half | -0.258 |
Mom | -0.256 |
sticker | -0.245 |
ushes | -0.236 |
ribbon | -0.235 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
current | +0.306 |
harbor | +0.285 |
ships | +0.278 |
ot | +0.275 |
padd | +0.263 |
Neg logit contributions | |
half | -0.558 |
Mom | -0.537 |
sticker | -0.519 |
cookie | -0.495 |
Anna | -0.487 |
Token | tw |
Token ID | 665 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
vill | +0.160 |
challenged | +0.160 |
vious | +0.158 |
roads | +0.155 |
current | +0.152 |
Neg logit contributions | |
half | -0.118 |
sticker | -0.115 |
cookie | -0.111 |
Mom | -0.106 |
ribbon | -0.105 |
Token | inkle |
Token ID | 19894 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
vill | +0.035 |
challenged | +0.034 |
current | +0.034 |
ot | +0.034 |
vious | +0.033 |
Neg logit contributions | |
half | -0.022 |
Mom | -0.021 |
sticker | -0.021 |
ribbon | -0.020 |
wrist | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
half | +0.043 |
Mom | +0.042 |
sticker | +0.040 |
icing | +0.038 |
cookie | +0.038 |
Neg logit contributions | |
vill | -0.070 |
challenged | -0.067 |
current | -0.067 |
vious | -0.066 |
ot | -0.066 |
Token | his |
Token ID | 465 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Mom | +0.008 |
half | +0.008 |
sticker | +0.007 |
cookie | +0.007 |
icing | +0.007 |
Neg logit contributions | |
vill | -0.007 |
challenged | -0.007 |
current | -0.007 |
ot | -0.006 |
vious | -0.006 |
Token | went |
Token ID | 1816 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
vill | +0.061 |
vious | +0.059 |
current | +0.058 |
ules | +0.057 |
ot | +0.056 |
Neg logit contributions | |
half | -0.059 |
Mom | -0.058 |
ribbon | -0.056 |
sticker | -0.054 |
tape | -0.053 |
Token | on |
Token ID | 319 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
vill | +0.112 |
current | +0.108 |
vious | +0.108 |
ot | +0.107 |
challenged | +0.106 |
Neg logit contributions | |
half | -0.054 |
Mom | -0.053 |
sticker | -0.052 |
cookie | -0.048 |
ribbon | -0.047 |
Token | with |
Token ID | 351 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
half | +0.060 |
Mom | +0.059 |
sticker | +0.057 |
cookie | +0.054 |
ribbon | +0.054 |
Neg logit contributions | |
vill | -0.081 |
vious | -0.078 |
challenged | -0.078 |
ot | -0.078 |
current | -0.077 |
Token | his |
Token ID | 465 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
vill | +0.014 |
challenged | +0.013 |
vious | +0.013 |
current | +0.013 |
ot | +0.013 |
Neg logit contributions | |
half | -0.010 |
Mom | -0.009 |
sticker | -0.009 |
cookie | -0.008 |
herself | -0.008 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Mom | +0.023 |
half | +0.023 |
sticker | +0.022 |
icing | +0.021 |
ushes | +0.021 |
Neg logit contributions | |
vill | -0.031 |
current | -0.029 |
challenged | -0.029 |
ot | -0.029 |
vious | -0.028 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
vill | +0.133 |
current | +0.128 |
ot | +0.127 |
challenged | +0.126 |
vious | +0.119 |
Neg logit contributions | |
half | -0.231 |
Mom | -0.231 |
sticker | -0.217 |
ushes | -0.211 |
ribbon | -0.210 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ot | +0.312 |
current | +0.312 |
harbor | +0.298 |
ships | +0.289 |
ranc | +0.266 |
Neg logit contributions | |
half | -0.563 |
Mom | -0.546 |
sticker | -0.503 |
Anna | -0.499 |
cookie | -0.488 |
Token | ways |
Token ID | 2842 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
vill | +0.146 |
challenged | +0.144 |
vious | +0.143 |
lves | +0.142 |
roads | +0.141 |
Neg logit contributions | |
half | -0.127 |
cookie | -0.119 |
sticker | -0.119 |
Mom | -0.114 |
ribbon | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
vill | +0.094 |
current | +0.091 |
challenged | +0.091 |
vious | +0.090 |
ot | +0.090 |
Neg logit contributions | |
half | -0.054 |
Mom | -0.051 |
sticker | -0.050 |
cookie | -0.046 |
ribbon | -0.045 |
Token | causing |
Token ID | 6666 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
vill | +0.030 |
vious | +0.028 |
ot | +0.027 |
challenged | +0.027 |
current | +0.027 |
Neg logit contributions | |
half | -0.029 |
Mom | -0.028 |
sticker | -0.028 |
cookie | -0.027 |
tape | -0.026 |
Token | problems |
Token ID | 2761 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
vill | +0.204 |
challenged | +0.198 |
vious | +0.197 |
enced | +0.196 |
ot | +0.195 |
Neg logit contributions | |
half | -0.154 |
Mom | -0.137 |
sticker | -0.135 |
herself | -0.134 |
cookie | -0.127 |
Token | old |
Token ID | 1468 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
vill | +0.078 |
challenged | +0.075 |
current | +0.074 |
ot | +0.074 |
vious | +0.074 |
Neg logit contributions | |
half | -0.065 |
Mom | -0.065 |
sticker | -0.063 |
cookie | -0.060 |
ribbon | -0.059 |
Token | lady |
Token ID | 10846 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
vill | +0.072 |
challenged | +0.069 |
current | +0.069 |
ot | +0.068 |
vious | +0.068 |
Neg logit contributions | |
Mom | -0.055 |
half | -0.054 |
sticker | -0.051 |
icing | -0.050 |
ushes | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
vill | +0.065 |
challenged | +0.063 |
vious | +0.062 |
ot | +0.062 |
current | +0.061 |
Neg logit contributions | |
Mom | -0.051 |
half | -0.049 |
sticker | -0.047 |
icing | -0.045 |
ribbon | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
vill | +0.010 |
challenged | +0.010 |
current | +0.010 |
ot | +0.010 |
vious | +0.010 |
Neg logit contributions | |
Mom | -0.006 |
half | -0.006 |
sticker | -0.006 |
cookie | -0.005 |
icing | -0.005 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
half | +0.022 |
Mom | +0.022 |
sticker | +0.022 |
cookie | +0.021 |
ribbon | +0.020 |
Neg logit contributions | |
vill | -0.029 |
challenged | -0.028 |
current | -0.028 |
vious | -0.028 |
ot | -0.028 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
current | +0.119 |
ot | +0.117 |
challenged | +0.116 |
vill | +0.113 |
ships | +0.110 |
Neg logit contributions | |
half | -0.239 |
Mom | -0.236 |
sticker | -0.227 |
ushes | -0.219 |
wrist | -0.218 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
current | +0.327 |
harbor | +0.315 |
ot | +0.312 |
ships | +0.293 |
ranc | +0.284 |
Neg logit contributions | |
half | -0.532 |
Mom | -0.503 |
sticker | -0.496 |
Anna | -0.469 |
cookie | -0.467 |
Token | tw |
Token ID | 665 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
vill | +0.151 |
challenged | +0.149 |
vious | +0.147 |
lves | +0.147 |
ot | +0.146 |
Neg logit contributions | |
sticker | -0.118 |
half | -0.117 |
cookie | -0.113 |
ribbon | -0.108 |
Mom | -0.105 |
Token | inkle |
Token ID | 19894 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
vill | +0.032 |
challenged | +0.032 |
ot | +0.031 |
current | +0.031 |
vious | +0.030 |
Neg logit contributions | |
half | -0.020 |
sticker | -0.019 |
Mom | -0.019 |
ribbon | -0.019 |
wrist | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
half | +0.042 |
Mom | +0.041 |
sticker | +0.040 |
icing | +0.038 |
cookie | +0.038 |
Neg logit contributions | |
vill | -0.074 |
challenged | -0.071 |
current | -0.071 |
vious | -0.070 |
ot | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
half | +0.006 |
Mom | +0.006 |
sticker | +0.006 |
cookie | +0.006 |
icing | +0.006 |
Neg logit contributions | |
vill | -0.010 |
challenged | -0.010 |
current | -0.010 |
vious | -0.010 |
ot | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
half | +0.017 |
sticker | +0.017 |
icing | +0.016 |
Mom | +0.016 |
ribbon | +0.016 |
Neg logit contributions | |
vill | -0.026 |
challenged | -0.025 |
ot | -0.024 |
current | -0.024 |
vious | -0.024 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
sticker | +0.018 |
icing | +0.018 |
half | +0.017 |
cookie | +0.017 |
ushes | +0.016 |
Neg logit contributions | |
vill | -0.021 |
challenged | -0.021 |
vious | -0.020 |
current | -0.019 |
ot | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Mom | +0.032 |
half | +0.032 |
sticker | +0.030 |
icing | +0.029 |
cookie | +0.029 |
Neg logit contributions | |
vill | -0.035 |
challenged | -0.033 |
current | -0.033 |
ot | -0.033 |
vious | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
vill | +0.018 |
challenged | +0.017 |
ot | +0.017 |
current | +0.017 |
vious | +0.017 |
Neg logit contributions | |
Mom | -0.011 |
half | -0.011 |
sticker | -0.010 |
icing | -0.010 |
ushes | -0.010 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
Mom | +0.033 |
sticker | +0.032 |
half | +0.032 |
cookie | +0.031 |
ribbon | +0.030 |
Neg logit contributions | |
vious | -0.037 |
challenged | -0.036 |
vill | -0.035 |
current | -0.034 |
ot | -0.034 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
current | +0.111 |
challenged | +0.109 |
vill | +0.109 |
ot | +0.106 |
ships | +0.103 |
Neg logit contributions | |
Mom | -0.243 |
half | -0.241 |
sticker | -0.228 |
ribbon | -0.223 |
wrist | -0.222 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
current | +0.325 |
ranc | +0.316 |
ships | +0.314 |
ot | +0.313 |
harbor | +0.311 |
Neg logit contributions | |
Mom | -0.509 |
half | -0.499 |
Anna | -0.464 |
sticker | -0.455 |
card | -0.438 |
Token | bird |
Token ID | 6512 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
challenged | +0.135 |
roads | +0.135 |
vious | +0.131 |
ships | +0.128 |
lves | +0.125 |
Neg logit contributions | |
sticker | -0.127 |
cookie | -0.125 |
half | -0.121 |
ribbon | -0.117 |
Mom | -0.116 |
Token | flew |
Token ID | 13112 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
vill | +0.121 |
current | +0.113 |
fishermen | +0.111 |
traveller | +0.108 |
bust | +0.107 |
Neg logit contributions | |
half | -0.107 |
Mom | -0.106 |
sticker | -0.096 |
ribbon | -0.095 |
brush | -0.090 |
Token | by |
Token ID | 416 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
vill | +0.116 |
current | +0.110 |
challenged | +0.108 |
ot | +0.107 |
vious | +0.105 |
Neg logit contributions | |
half | -0.078 |
Mom | -0.078 |
sticker | -0.069 |
ribbon | -0.068 |
herself | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
vill | +0.037 |
challenged | +0.036 |
current | +0.036 |
ot | +0.035 |
vious | +0.035 |
Neg logit contributions | |
Mom | -0.029 |
half | -0.028 |
sticker | -0.028 |
icing | -0.027 |
cookie | -0.026 |
Token | modest |
Token ID | 12949 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
vious | +0.028 |
vill | +0.028 |
challenged | +0.028 |
current | +0.027 |
roads | +0.026 |
Neg logit contributions | |
Mom | -0.022 |
half | -0.021 |
sticker | -0.020 |
cookie | -0.020 |
ribbon | -0.019 |
Token | barn |
Token ID | 25203 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
vill | +0.010 |
challenged | +0.010 |
vious | +0.010 |
current | +0.009 |
ot | +0.009 |
Neg logit contributions | |
Mom | -0.011 |
half | -0.011 |
sticker | -0.010 |
cookie | -0.010 |
ribbon | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
vill | +0.081 |
vious | +0.081 |
current | +0.079 |
challenged | +0.079 |
ot | +0.076 |
Neg logit contributions | |
Mom | -0.037 |
half | -0.037 |
sticker | -0.035 |
cookie | -0.033 |
icing | -0.031 |
Token | Two |
Token ID | 4930 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
vill | +0.016 |
challenged | +0.015 |
current | +0.015 |
ot | +0.014 |
vious | +0.014 |
Neg logit contributions | |
Mom | -0.018 |
half | -0.018 |
sticker | -0.017 |
ribbon | -0.016 |
icing | -0.016 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
current | +0.097 |
vious | +0.094 |
vill | +0.092 |
challenged | +0.092 |
roads | +0.092 |
Neg logit contributions | |
half | -0.065 |
Mom | -0.065 |
cookies | -0.062 |
cookie | -0.059 |
tape | -0.056 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
current | +0.114 |
vill | +0.109 |
challenged | +0.109 |
ot | +0.105 |
vious | +0.102 |
Neg logit contributions | |
half | -0.250 |
Mom | -0.247 |
sticker | -0.232 |
ushes | -0.227 |
icing | -0.225 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
current | +0.315 |
harbor | +0.270 |
ot | +0.265 |
padd | +0.265 |
vill | +0.263 |
Neg logit contributions | |
Mom | -0.542 |
half | -0.526 |
sticker | -0.494 |
Anna | -0.489 |
cookie | -0.471 |
Token | kittens |
Token ID | 45584 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
roads | +0.146 |
ounded | +0.137 |
vious | +0.137 |
challenged | +0.134 |
current | +0.134 |
Neg logit contributions | |
cookie | -0.131 |
cookies | -0.130 |
chocolate | -0.125 |
half | -0.123 |
sticker | -0.122 |
Token | lived |
Token ID | 5615 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
current | +0.071 |
vill | +0.069 |
vious | +0.067 |
bust | +0.064 |
roads | +0.062 |
Neg logit contributions | |
half | -0.063 |
Mom | -0.063 |
cookie | -0.058 |
sticker | -0.058 |
herself | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Mom | +0.016 |
half | +0.016 |
sticker | +0.015 |
icing | +0.014 |
ribbon | +0.014 |
Neg logit contributions | |
vill | -0.021 |
challenged | -0.020 |
ot | -0.020 |
current | -0.019 |
vious | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Mom | +0.010 |
half | +0.010 |
sticker | +0.010 |
icing | +0.009 |
wrist | +0.009 |
Neg logit contributions | |
vill | -0.013 |
ot | -0.012 |
challenged | -0.012 |
current | -0.011 |
vious | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
vill | +0.128 |
current | +0.125 |
challenged | +0.120 |
ot | +0.117 |
ranc | +0.115 |
Neg logit contributions | |
half | -0.102 |
Mom | -0.093 |
sticker | -0.091 |
cookie | -0.090 |
ushes | -0.088 |
Token | him |
Token ID | 683 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
vill | +0.018 |
challenged | +0.017 |
current | +0.017 |
vious | +0.017 |
ot | +0.017 |
Neg logit contributions | |
half | -0.011 |
Mom | -0.011 |
sticker | -0.010 |
ribbon | -0.010 |
icing | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Mom | +0.006 |
ushes | +0.006 |
sticker | +0.005 |
half | +0.005 |
icing | +0.005 |
Neg logit contributions | |
vill | -0.006 |
challenged | -0.006 |
ot | -0.006 |
current | -0.005 |
padd | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
vill | +0.008 |
challenged | +0.008 |
current | +0.008 |
ot | +0.008 |
vious | +0.007 |
Neg logit contributions | |
half | -0.006 |
Mom | -0.006 |
sticker | -0.006 |
cookie | -0.005 |
icing | -0.005 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
Mom | +0.023 |
half | +0.022 |
sticker | +0.021 |
icing | +0.020 |
cookie | +0.020 |
Neg logit contributions | |
vill | -0.026 |
challenged | -0.025 |
current | -0.024 |
ot | -0.024 |
vious | -0.024 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
vill | +0.101 |
challenged | +0.096 |
current | +0.095 |
ot | +0.093 |
vious | +0.089 |
Neg logit contributions | |
half | -0.258 |
Mom | -0.256 |
sticker | -0.248 |
ribbon | -0.239 |
icing | -0.239 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
current | +0.274 |
ot | +0.262 |
harbor | +0.256 |
ships | +0.256 |
ranc | +0.245 |
Neg logit contributions | |
half | -0.581 |
Mom | -0.553 |
sticker | -0.533 |
cookie | -0.521 |
slice | -0.509 |
Token | grin |
Token ID | 16770 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
vill | +0.162 |
challenged | +0.159 |
vious | +0.157 |
ot | +0.154 |
current | +0.153 |
Neg logit contributions | |
half | -0.111 |
sticker | -0.107 |
cookie | -0.103 |
Mom | -0.102 |
ribbon | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Mom | +0.001 |
half | +0.001 |
ushes | +0.001 |
sticker | +0.001 |
icing | +0.001 |
Neg logit contributions | |
vill | -0.002 |
challenged | -0.002 |
ot | -0.002 |
current | -0.002 |
vious | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
vill | +0.016 |
current | +0.016 |
challenged | +0.016 |
ot | +0.016 |
vious | +0.016 |
Neg logit contributions | |
Mom | -0.012 |
half | -0.012 |
sticker | -0.012 |
cookie | -0.011 |
icing | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
vill | +0.006 |
current | +0.006 |
vious | +0.006 |
ot | +0.006 |
challenged | +0.006 |
Neg logit contributions | |
Mom | -0.008 |
half | -0.008 |
sticker | -0.008 |
ribbon | -0.008 |
cookie | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
vill | +0.044 |
challenged | +0.043 |
vious | +0.041 |
ot | +0.040 |
ules | +0.040 |
Neg logit contributions | |
sticker | -0.036 |
half | -0.036 |
icing | -0.035 |
ribbon | -0.035 |
cookie | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
half | +0.002 |
sticker | +0.002 |
icing | +0.002 |
cookie | +0.002 |
Mom | +0.002 |
Neg logit contributions | |
vill | -0.003 |
challenged | -0.003 |
vious | -0.003 |
current | -0.003 |
ot | -0.003 |
Token | With |
Token ID | 3152 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
half | +0.001 |
Mom | +0.001 |
sticker | +0.001 |
cookie | +0.001 |
icing | +0.001 |
Neg logit contributions | |
vill | -0.002 |
challenged | -0.002 |
vious | -0.002 |
current | -0.002 |
ot | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
vill | +0.020 |
challenged | +0.019 |
current | +0.019 |
ot | +0.019 |
vious | +0.019 |
Neg logit contributions | |
Mom | -0.010 |
half | -0.010 |
sticker | -0.009 |
cookie | -0.009 |
icing | -0.008 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Mom | +0.024 |
half | +0.024 |
sticker | +0.023 |
cookie | +0.022 |
ribbon | +0.022 |
Neg logit contributions | |
vill | -0.026 |
vious | -0.026 |
challenged | -0.025 |
ot | -0.025 |
current | -0.025 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
current | +0.119 |
challenged | +0.115 |
ot | +0.115 |
vill | +0.113 |
ships | +0.107 |
Neg logit contributions | |
half | -0.240 |
Mom | -0.237 |
sticker | -0.228 |
ushes | -0.222 |
wrist | -0.219 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
current | +0.313 |
harbor | +0.293 |
ot | +0.293 |
ships | +0.276 |
ranc | +0.272 |
Neg logit contributions | |
Mom | -0.521 |
half | -0.517 |
sticker | -0.487 |
Anna | -0.465 |
card | -0.455 |
Token | gl |
Token ID | 1278 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
challenged | +0.148 |
vious | +0.147 |
vill | +0.146 |
roads | +0.140 |
ships | +0.140 |
Neg logit contributions | |
half | -0.120 |
sticker | -0.119 |
cookie | -0.116 |
ribbon | -0.112 |
Mom | -0.110 |
Token | int |
Token ID | 600 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
vill | +0.168 |
current | +0.166 |
challenged | +0.165 |
ot | +0.162 |
ships | +0.154 |
Neg logit contributions | |
sticker | -0.135 |
half | -0.132 |
ushes | -0.128 |
Mom | -0.124 |
wrist | -0.120 |
Token | in |
Token ID | 287 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
challenged | +0.106 |
vill | +0.105 |
current | +0.104 |
lves | +0.103 |
ot | +0.102 |
Neg logit contributions | |
half | -0.085 |
sticker | -0.080 |
Mom | -0.077 |
ribbon | -0.073 |
icing | -0.072 |
Token | her |
Token ID | 607 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
sticker | +0.007 |
Mom | +0.007 |
cookie | +0.007 |
half | +0.007 |
icing | +0.007 |
Neg logit contributions | |
vill | -0.012 |
challenged | -0.011 |
current | -0.011 |
vious | -0.011 |
ot | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
half | +0.001 |
icing | +0.001 |
sticker | +0.001 |
ribbon | +0.001 |
wrist | +0.001 |
Neg logit contributions | |
vill | -0.001 |
challenged | -0.001 |
current | -0.001 |
ot | -0.001 |
vious | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
sticker | +0.001 |
half | +0.001 |
icing | +0.001 |
ribbon | +0.001 |
cookie | +0.001 |
Neg logit contributions | |
vill | -0.001 |
challenged | -0.001 |
current | -0.001 |
vious | -0.001 |
ot | -0.001 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
vill | +0.014 |
current | +0.013 |
challenged | +0.013 |
ot | +0.013 |
vious | +0.012 |
Neg logit contributions | |
Mom | -0.015 |
half | -0.015 |
sticker | -0.014 |
icing | -0.014 |
ushes | -0.014 |
Token | grinned |
Token ID | 36268 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
vill | +0.042 |
current | +0.040 |
vious | +0.040 |
ot | +0.040 |
challenged | +0.039 |
Neg logit contributions | |
half | -0.035 |
Mom | -0.035 |
sticker | -0.032 |
cookie | -0.031 |
ribbon | -0.031 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
half | +0.041 |
Mom | +0.041 |
sticker | +0.038 |
cookie | +0.036 |
ribbon | +0.036 |
Neg logit contributions | |
vill | -0.064 |
challenged | -0.062 |
current | -0.061 |
vious | -0.061 |
ot | -0.061 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
vill | +0.119 |
ships | +0.118 |
current | +0.117 |
harbor | +0.117 |
challenged | +0.117 |
Neg logit contributions | |
half | -0.237 |
Mom | -0.229 |
sticker | -0.215 |
ushes | -0.213 |
wrist | -0.208 |
Token | v |
Token ID | 85 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
harbor | +0.335 |
current | +0.317 |
ships | +0.309 |
ot | +0.305 |
ranc | +0.298 |
Neg logit contributions | |
half | -0.521 |
Mom | -0.499 |
sticker | -0.466 |
Anna | -0.452 |
cookie | -0.450 |
Token | ously |
Token ID | 3481 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
vill | +0.024 |
challenged | +0.023 |
current | +0.023 |
ot | +0.023 |
vious | +0.022 |
Neg logit contributions | |
half | -0.023 |
Mom | -0.023 |
sticker | -0.021 |
cookie | -0.021 |
icing | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
vill | +0.178 |
vious | +0.170 |
challenged | +0.169 |
current | +0.169 |
ot | +0.168 |
Neg logit contributions | |
half | -0.110 |
Mom | -0.107 |
sticker | -0.102 |
cookie | -0.097 |
ribbon | -0.096 |
Token | " |
Token ID | 366 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
vill | +0.019 |
challenged | +0.018 |
current | +0.018 |
ot | +0.017 |
vious | +0.017 |
Neg logit contributions | |
Mom | -0.018 |
half | -0.018 |
sticker | -0.017 |
icing | -0.016 |
cookie | -0.016 |
Token | Never |
Token ID | 12295 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
vill | +0.062 |
challenged | +0.060 |
vious | +0.059 |
ot | +0.059 |
current | +0.059 |
Neg logit contributions | |
half | -0.043 |
sticker | -0.042 |
Mom | -0.041 |
cookie | -0.040 |
icing | -0.040 |
Token | One |
Token ID | 3198 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Mom | +0.009 |
half | +0.008 |
sticker | +0.008 |
cookie | +0.008 |
icing | +0.008 |
Neg logit contributions | |
vill | -0.014 |
challenged | -0.014 |
current | -0.014 |
ot | -0.014 |
vious | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Mom | +0.049 |
half | +0.047 |
sticker | +0.044 |
cookie | +0.043 |
Anna | +0.040 |
Neg logit contributions | |
challenged | -0.071 |
current | -0.071 |
vill | -0.070 |
vious | -0.070 |
ot | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
vill | +0.015 |
challenged | +0.015 |
current | +0.015 |
vious | +0.015 |
ot | +0.015 |
Neg logit contributions | |
Mom | -0.013 |
half | -0.013 |
sticker | -0.012 |
cookie | -0.011 |
icing | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
vill | +0.025 |
vious | +0.024 |
challenged | +0.024 |
current | +0.024 |
ot | +0.024 |
Neg logit contributions | |
half | -0.012 |
Mom | -0.012 |
sticker | -0.011 |
cookie | -0.010 |
ribbon | -0.010 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Mom | +0.034 |
sticker | +0.033 |
cookie | +0.033 |
half | +0.033 |
ribbon | +0.031 |
Neg logit contributions | |
vious | -0.032 |
challenged | -0.030 |
current | -0.029 |
vill | -0.029 |
roads | -0.029 |
Token | chie |
Token ID | 3043 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
current | +0.106 |
challenged | +0.106 |
vill | +0.105 |
ot | +0.100 |
vious | +0.097 |
Neg logit contributions | |
Mom | -0.244 |
half | -0.241 |
sticker | -0.229 |
ribbon | -0.223 |
wrist | -0.222 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
current | +0.310 |
ot | +0.274 |
fishermen | +0.274 |
ships | +0.270 |
harbor | +0.265 |
Neg logit contributions | |
Mom | -0.533 |
half | -0.502 |
Anna | -0.481 |
sticker | -0.476 |
card | -0.451 |
Token | young |
Token ID | 1862 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
roads | +0.149 |
vious | +0.147 |
challenged | +0.144 |
ounded | +0.137 |
current | +0.135 |
Neg logit contributions | |
cookie | -0.118 |
sticker | -0.115 |
half | -0.109 |
Mom | -0.108 |
ribbon | -0.107 |
Token | boy |
Token ID | 2933 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
vious | +0.108 |
roads | +0.100 |
rated | +0.100 |
ounded | +0.098 |
enced | +0.097 |
Neg logit contributions | |
Mom | -0.084 |
half | -0.084 |
sticker | -0.084 |
cookie | -0.083 |
doll | -0.081 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
current | +0.156 |
vill | +0.151 |
bust | +0.144 |
vious | +0.142 |
daunting | +0.139 |
Neg logit contributions | |
half | -0.171 |
Mom | -0.166 |
sticker | -0.156 |
cookie | -0.151 |
tape | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
vious | +0.059 |
vill | +0.059 |
current | +0.058 |
enced | +0.058 |
bust | +0.057 |
Neg logit contributions | |
half | -0.015 |
sticker | -0.013 |
Mom | -0.012 |
herself | -0.011 |
cookie | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Mom | +0.026 |
half | +0.025 |
cookie | +0.022 |
sticker | +0.021 |
ribbon | +0.020 |
Neg logit contributions | |
vill | -0.047 |
current | -0.045 |
vious | -0.044 |
challenged | -0.044 |
ot | -0.043 |
Token | share |
Token ID | 2648 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
Mom | +0.069 |
half | +0.069 |
ushes | +0.068 |
sticker | +0.067 |
icing | +0.066 |
Neg logit contributions | |
ot | -0.076 |
challenged | -0.075 |
vill | -0.074 |
current | -0.074 |
vious | -0.070 |
Token | our |
Token ID | 674 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ushes | +0.228 |
scalp | +0.227 |
Mom | +0.226 |
Elsa | +0.218 |
bookmark | +0.210 |
Neg logit contributions | |
ot | -0.195 |
ships | -0.184 |
challenged | -0.176 |
padd | -0.170 |
fishermen | -0.170 |
Token | bread |
Token ID | 8509 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Mom | +0.106 |
Anna | +0.101 |
ushes | +0.101 |
icing | +0.100 |
scalp | +0.099 |
Neg logit contributions | |
ot | -0.105 |
current | -0.101 |
vill | -0.101 |
challenged | -0.096 |
ships | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Mom | +0.079 |
Elsa | +0.073 |
icing | +0.073 |
bookmark | +0.071 |
sticker | +0.071 |
Neg logit contributions | |
ot | -0.102 |
fishermen | -0.092 |
ships | -0.090 |
challenged | -0.088 |
oct | -0.086 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
Mom | +0.021 |
ushes | +0.020 |
icing | +0.019 |
sticker | +0.019 |
Anna | +0.019 |
Neg logit contributions | |
ot | -0.027 |
current | -0.027 |
challenged | -0.026 |
vill | -0.025 |
padd | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Mom | +0.174 |
Elsa | +0.149 |
icing | +0.147 |
bookmark | +0.146 |
ribbon | +0.145 |
Neg logit contributions | |
ot | -0.192 |
fishermen | -0.178 |
challenged | -0.174 |
current | -0.173 |
vill | -0.171 |
Token | it |
Token ID | 340 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
wrist | +0.010 |
ushes | +0.010 |
bookmark | +0.010 |
sticker | +0.010 |
Mom | +0.009 |
Neg logit contributions | |
ot | -0.012 |
ships | -0.011 |
current | -0.011 |
fishermen | -0.011 |
vill | -0.011 |
Token | instead |
Token ID | 2427 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mom | +0.032 |
sticker | +0.028 |
half | +0.028 |
wrist | +0.028 |
icing | +0.028 |
Neg logit contributions | |
challenged | -0.035 |
ot | -0.035 |
vious | -0.035 |
vill | -0.034 |
current | -0.033 |
Token | ." |
Token ID | 526 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Mom | +0.034 |
sticker | +0.033 |
ribbon | +0.032 |
wrist | +0.032 |
half | +0.032 |
Neg logit contributions | |
challenged | -0.046 |
vious | -0.045 |
vill | -0.045 |
current | -0.045 |
ot | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
half | +0.051 |
sticker | +0.050 |
Mom | +0.049 |
ribbon | +0.047 |
icing | +0.046 |
Neg logit contributions | |
vill | -0.068 |
challenged | -0.067 |
ot | -0.066 |
vious | -0.065 |
current | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
half | +0.007 |
Mom | +0.007 |
sticker | +0.007 |
cookie | +0.006 |
icing | +0.006 |
Neg logit contributions | |
vill | -0.012 |
challenged | -0.011 |
current | -0.011 |
vious | -0.011 |
ot | -0.011 |
Token | then |
Token ID | 788 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
half | +0.030 |
Mom | +0.030 |
sticker | +0.029 |
cookie | +0.027 |
icing | +0.027 |
Neg logit contributions | |
vill | -0.034 |
challenged | -0.032 |
current | -0.032 |
vious | -0.032 |
ot | -0.032 |
Token | came |
Token ID | 1625 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
half | +0.068 |
Mom | +0.066 |
sticker | +0.065 |
cookie | +0.061 |
icing | +0.061 |
Neg logit contributions | |
vill | -0.073 |
vious | -0.069 |
current | -0.069 |
challenged | -0.068 |
ot | -0.068 |
Token | back |
Token ID | 736 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
vill | +0.119 |
challenged | +0.118 |
ot | +0.114 |
current | +0.114 |
padd | +0.112 |
Neg logit contributions | |
sticker | -0.111 |
icing | -0.111 |
Mom | -0.111 |
cookie | -0.110 |
half | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Mom | +0.040 |
half | +0.039 |
sticker | +0.038 |
icing | +0.037 |
ribbon | +0.036 |
Neg logit contributions | |
vill | -0.056 |
challenged | -0.055 |
ot | -0.054 |
current | -0.053 |
vious | -0.052 |
Token | play |
Token ID | 711 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
vill | +0.045 |
challenged | +0.044 |
ot | +0.043 |
current | +0.043 |
vious | +0.041 |
Neg logit contributions | |
Mom | -0.036 |
half | -0.036 |
sticker | -0.034 |
ushes | -0.033 |
icing | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Mom | +0.086 |
half | +0.083 |
sticker | +0.079 |
icing | +0.076 |
ushes | +0.076 |
Neg logit contributions | |
vill | -0.147 |
challenged | -0.142 |
current | -0.140 |
ot | -0.140 |
vious | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
half | +0.011 |
Mom | +0.011 |
sticker | +0.011 |
icing | +0.010 |
ribbon | +0.010 |
Neg logit contributions | |
vill | -0.013 |
challenged | -0.013 |
current | -0.013 |
ot | -0.013 |
vious | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
half | +0.018 |
sticker | +0.018 |
icing | +0.018 |
ribbon | +0.018 |
wrist | +0.017 |
Neg logit contributions | |
vill | -0.026 |
challenged | -0.025 |
ot | -0.024 |
current | -0.024 |
vious | -0.024 |
Token | But |
Token ID | 1537 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
sticker | +0.018 |
icing | +0.018 |
half | +0.018 |
ribbon | +0.017 |
cookie | +0.016 |
Neg logit contributions | |
vill | -0.031 |
challenged | -0.030 |
vious | -0.029 |
ot | -0.028 |
current | -0.028 |
Token | then |
Token ID | 788 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Mom | +0.022 |
sticker | +0.022 |
ushes | +0.022 |
half | +0.022 |
icing | +0.021 |
Neg logit contributions | |
vill | -0.023 |
challenged | -0.023 |
ot | -0.023 |
current | -0.023 |
padd | -0.021 |
Token | every |
Token ID | 790 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
vill | +0.055 |
ot | +0.054 |
challenged | +0.053 |
current | +0.052 |
vious | +0.048 |
Neg logit contributions | |
Mom | -0.060 |
sticker | -0.059 |
half | -0.058 |
ushes | -0.057 |
icing | -0.057 |
Token | day |
Token ID | 1110 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
vill | +0.033 |
challenged | +0.031 |
current | +0.031 |
vious | +0.031 |
ot | +0.031 |
Neg logit contributions | |
Mom | -0.031 |
half | -0.031 |
sticker | -0.030 |
icing | -0.029 |
ushes | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
vill | +0.016 |
challenged | +0.015 |
current | +0.015 |
ot | +0.015 |
vious | +0.015 |
Neg logit contributions | |
Mom | -0.012 |
half | -0.012 |
sticker | -0.011 |
icing | -0.011 |
cookie | -0.010 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
vill | +0.004 |
ot | +0.004 |
challenged | +0.004 |
current | +0.004 |
vious | +0.004 |
Neg logit contributions | |
Mom | -0.003 |
half | -0.003 |
sticker | -0.003 |
ushes | -0.003 |
icing | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
Mom | +0.108 |
half | +0.108 |
sticker | +0.105 |
cookie | +0.099 |
ribbon | +0.099 |
Neg logit contributions | |
vill | -0.124 |
current | -0.122 |
ot | -0.117 |
vious | -0.116 |
challenged | -0.113 |
Token | her |
Token ID | 607 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Mom | +0.014 |
ushes | +0.014 |
half | +0.013 |
sticker | +0.013 |
icing | +0.013 |
Neg logit contributions | |
vill | -0.036 |
challenged | -0.035 |
ot | -0.035 |
current | -0.033 |
vious | -0.033 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ushes | +0.081 |
Mom | +0.081 |
half | +0.079 |
rap | +0.078 |
Anna | +0.077 |
Neg logit contributions | |
ot | -0.133 |
vill | -0.126 |
current | -0.121 |
vehicle | -0.120 |
ships | -0.120 |
Token | my |
Token ID | 1820 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
half | +0.067 |
Mom | +0.067 |
sticker | +0.065 |
wrist | +0.062 |
cookie | +0.062 |
Neg logit contributions | |
challenged | -0.079 |
vill | -0.078 |
ot | -0.076 |
vious | -0.076 |
bust | -0.073 |
Token | would |
Token ID | 561 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Mom | +0.123 |
half | +0.123 |
sticker | +0.118 |
cookie | +0.113 |
icing | +0.113 |
Neg logit contributions | |
vill | -0.104 |
challenged | -0.100 |
current | -0.098 |
ot | -0.098 |
vious | -0.097 |
Token | step |
Token ID | 2239 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
half | +0.080 |
Mom | +0.080 |
sticker | +0.077 |
ushes | +0.076 |
cookie | +0.074 |
Neg logit contributions | |
vill | -0.090 |
challenged | -0.089 |
ot | -0.088 |
current | -0.087 |
padd | -0.083 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
vill | +0.090 |
ot | +0.087 |
challenged | +0.086 |
vious | +0.085 |
padd | +0.085 |
Neg logit contributions | |
half | -0.091 |
Mom | -0.091 |
sticker | -0.087 |
wrist | -0.084 |
icing | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
half | +0.002 |
Mom | +0.002 |
sticker | +0.002 |
cookie | +0.002 |
wrist | +0.002 |
Neg logit contributions | |
vill | -0.005 |
current | -0.005 |
vious | -0.005 |
challenged | -0.005 |
ot | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
vill | +0.025 |
vious | +0.024 |
current | +0.024 |
ot | +0.023 |
challenged | +0.023 |
Neg logit contributions | |
Mom | -0.017 |
half | -0.017 |
sticker | -0.016 |
ribbon | -0.015 |
icing | -0.015 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
vill | +0.070 |
vious | +0.069 |
current | +0.069 |
roads | +0.068 |
ican | +0.067 |
Neg logit contributions | |
Mom | -0.062 |
half | -0.056 |
love | -0.051 |
icing | -0.050 |
ribbon | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
vill | +0.183 |
challenged | +0.179 |
current | +0.175 |
ican | +0.172 |
itive | +0.170 |
Neg logit contributions | |
herself | -0.103 |
half | -0.102 |
Mom | -0.101 |
sticker | -0.101 |
cookie | -0.093 |
Token | warm |
Token ID | 5814 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
vill | +0.078 |
challenged | +0.075 |
vious | +0.074 |
current | +0.074 |
ot | +0.073 |
Neg logit contributions | |
Mom | -0.056 |
half | -0.055 |
sticker | -0.053 |
ribbon | -0.050 |
icing | -0.050 |
Token | sand |
Token ID | 6450 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Mom | +0.109 |
half | +0.108 |
sticker | +0.103 |
icing | +0.098 |
cookie | +0.098 |
Neg logit contributions | |
vill | -0.158 |
challenged | -0.152 |
vious | -0.149 |
current | -0.148 |
ot | -0.146 |
Token | under |
Token ID | 739 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Mom | +0.139 |
half | +0.135 |
sticker | +0.128 |
ushes | +0.122 |
cookie | +0.121 |
Neg logit contributions | |
vill | -0.165 |
ot | -0.161 |
current | -0.161 |
challenged | -0.158 |
ships | -0.154 |
Token | their |
Token ID | 511 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
sticker | +0.045 |
half | +0.045 |
Mom | +0.045 |
ushes | +0.044 |
cookie | +0.043 |
Neg logit contributions | |
vill | -0.061 |
ot | -0.060 |
current | -0.059 |
challenged | -0.058 |
ships | -0.057 |
Token | feet |
Token ID | 3625 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
half | +0.074 |
Mom | +0.073 |
sticker | +0.072 |
cookie | +0.069 |
icing | +0.068 |
Neg logit contributions | |
vill | -0.075 |
current | -0.073 |
ot | -0.072 |
ships | -0.071 |
challenged | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
vill | +0.023 |
challenged | +0.022 |
current | +0.022 |
vious | +0.022 |
ot | +0.022 |
Neg logit contributions | |
half | -0.013 |
Mom | -0.013 |
sticker | -0.013 |
cookie | -0.012 |
icing | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
vill | +0.021 |
current | +0.020 |
vious | +0.020 |
ot | +0.020 |
challenged | +0.020 |
Neg logit contributions | |
Mom | -0.013 |
half | -0.013 |
sticker | -0.013 |
cookie | -0.012 |
icing | -0.012 |
Token | flour |
Token ID | 10601 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Mom | +0.007 |
wrist | +0.007 |
half | +0.007 |
sticker | +0.006 |
Anna | +0.006 |
Neg logit contributions | |
ot | -0.010 |
vill | -0.010 |
vious | -0.009 |
current | -0.009 |
ships | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
wrist | +0.113 |
Mom | +0.112 |
bookmark | +0.110 |
Anna | +0.109 |
sticker | +0.108 |
Neg logit contributions | |
ot | -0.121 |
current | -0.110 |
vill | -0.110 |
ships | -0.108 |
padd | -0.108 |
Token | sugar |
Token ID | 7543 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
vill | +0.025 |
ot | +0.024 |
challenged | +0.024 |
current | +0.024 |
vious | +0.024 |
Neg logit contributions | |
Mom | -0.011 |
half | -0.011 |
sticker | -0.011 |
wrist | -0.010 |
ushes | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
wrist | +0.156 |
Mom | +0.152 |
bookmark | +0.152 |
sticker | +0.151 |
Love | +0.150 |
Neg logit contributions | |
ot | -0.151 |
vill | -0.140 |
padd | -0.137 |
current | -0.137 |
challenged | -0.136 |
Token | eggs |
Token ID | 9653 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
wrist | +0.004 |
sticker | +0.004 |
Mom | +0.004 |
half | +0.004 |
ushes | +0.004 |
Neg logit contributions | |
vill | -0.008 |
ot | -0.008 |
challenged | -0.008 |
current | -0.007 |
vious | -0.007 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
Mom | +0.025 |
sticker | +0.023 |
half | +0.023 |
bookmark | +0.023 |
wrist | +0.023 |
Neg logit contributions | |
ot | -0.030 |
challenged | -0.028 |
vill | -0.028 |
current | -0.028 |
padd | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
wrist | +0.120 |
Elsa | +0.119 |
Mom | +0.118 |
bookmark | +0.117 |
sticker | +0.117 |
Neg logit contributions | |
vill | -0.099 |
vious | -0.095 |
challenged | -0.093 |
ot | -0.093 |
overwhelmed | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Mom | +0.017 |
sticker | +0.017 |
half | +0.016 |
bookmark | +0.016 |
wrist | +0.016 |
Neg logit contributions | |
vill | -0.019 |
challenged | -0.019 |
ot | -0.019 |
current | -0.018 |
vious | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
vill | +0.009 |
challenged | +0.009 |
Int | +0.009 |
vious | +0.009 |
Curious | +0.008 |
Neg logit contributions | |
sticker | -0.011 |
ribbon | -0.011 |
half | -0.010 |
bookmark | -0.010 |
Mom | -0.010 |
Token | began |
Token ID | 2540 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
vill | +0.001 |
challenged | +0.001 |
ot | +0.001 |
current | +0.001 |
vious | +0.001 |
Neg logit contributions | |
Mom | -0.001 |
half | -0.001 |
sticker | -0.001 |
cookie | -0.001 |
ribbon | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Mom | +0.026 |
half | +0.024 |
sticker | +0.024 |
wrist | +0.023 |
ribbon | +0.023 |
Neg logit contributions | |
vill | -0.029 |
challenged | -0.028 |
ot | -0.027 |
padd | -0.027 |
current | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Mom | +0.086 |
half | +0.086 |
sticker | +0.083 |
icing | +0.080 |
cookie | +0.079 |
Neg logit contributions | |
vill | -0.082 |
challenged | -0.079 |
current | -0.077 |
ot | -0.076 |
vious | -0.076 |
Token | amazed |
Token ID | 24562 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
vill | +0.043 |
current | +0.041 |
challenged | +0.040 |
ot | +0.040 |
vious | +0.039 |
Neg logit contributions | |
half | -0.056 |
Mom | -0.055 |
sticker | -0.053 |
cookie | -0.051 |
icing | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
vill | +0.176 |
current | +0.169 |
challenged | +0.169 |
ot | +0.166 |
vious | +0.166 |
Neg logit contributions | |
Mom | -0.119 |
half | -0.119 |
sticker | -0.112 |
icing | -0.106 |
cookie | -0.105 |
Token | |
Token ID | 220 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
vill | +0.016 |
challenged | +0.015 |
ot | +0.014 |
vious | +0.014 |
Int | +0.014 |
Neg logit contributions | |
sticker | -0.015 |
half | -0.015 |
ribbon | -0.014 |
icing | -0.014 |
Mom | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
vill | +0.043 |
challenged | +0.042 |
vious | +0.040 |
ot | +0.039 |
Int | +0.038 |
Neg logit contributions | |
sticker | -0.040 |
ribbon | -0.040 |
half | -0.040 |
icing | -0.039 |
Mom | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
vill | +0.003 |
challenged | +0.003 |
Int | +0.003 |
ules | +0.003 |
Jon | +0.003 |
Neg logit contributions | |
sticker | -0.003 |
icing | -0.003 |
half | -0.003 |
ribbon | -0.003 |
cookie | -0.003 |
Token | After |
Token ID | 3260 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
vill | +0.004 |
challenged | +0.004 |
roads | +0.004 |
vious | +0.004 |
bust | +0.004 |
Neg logit contributions | |
sticker | -0.003 |
half | -0.003 |
icing | -0.003 |
cookie | -0.003 |
card | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Mom | +0.185 |
half | +0.180 |
ushes | +0.179 |
sticker | +0.175 |
wrist | +0.170 |
Neg logit contributions | |
vill | -0.198 |
ot | -0.185 |
challenged | -0.184 |
current | -0.180 |
padd | -0.176 |
Token | while |
Token ID | 981 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
half | +0.028 |
Mom | +0.028 |
ushes | +0.027 |
icing | +0.027 |
sticker | +0.026 |
Neg logit contributions | |
vill | -0.023 |
challenged | -0.022 |
current | -0.021 |
ot | -0.021 |
bust | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Mom | +0.045 |
half | +0.045 |
sticker | +0.044 |
wrist | +0.042 |
ushes | +0.042 |
Neg logit contributions | |
vill | -0.045 |
current | -0.043 |
challenged | -0.043 |
ot | -0.043 |
vious | -0.042 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
vill | +0.028 |
ot | +0.027 |
challenged | +0.027 |
current | +0.026 |
vious | +0.025 |
Neg logit contributions | |
Mom | -0.024 |
half | -0.023 |
sticker | -0.023 |
ushes | -0.022 |
wrist | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Mom | +0.155 |
half | +0.150 |
sticker | +0.143 |
ushes | +0.134 |
icing | +0.134 |
Neg logit contributions | |
vill | -0.228 |
ot | -0.219 |
challenged | -0.219 |
current | -0.217 |
vious | -0.215 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
vill | +0.026 |
challenged | +0.025 |
current | +0.025 |
ot | +0.025 |
vious | +0.025 |
Neg logit contributions | |
half | -0.018 |
Mom | -0.018 |
sticker | -0.018 |
ribbon | -0.016 |
icing | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
vill | +0.004 |
challenged | +0.003 |
ot | +0.003 |
current | +0.003 |
vious | +0.003 |
Neg logit contributions | |
half | -0.004 |
Mom | -0.004 |
sticker | -0.004 |
icing | -0.004 |
ribbon | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
half | +0.029 |
Mom | +0.028 |
sticker | +0.026 |
cookie | +0.026 |
ushes | +0.026 |
Neg logit contributions | |
vill | -0.027 |
current | -0.026 |
challenged | -0.026 |
vious | -0.026 |
ot | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Mom | +0.005 |
sticker | +0.005 |
ushes | +0.005 |
half | +0.005 |
wrist | +0.005 |
Neg logit contributions | |
vill | -0.006 |
challenged | -0.006 |
vious | -0.005 |
ot | -0.005 |
padd | -0.005 |
Token | time |
Token ID | 640 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
half | +0.017 |
Mom | +0.017 |
sticker | +0.016 |
icing | +0.015 |
ribbon | +0.015 |
Neg logit contributions | |
vill | -0.019 |
challenged | -0.018 |
current | -0.018 |
vious | -0.018 |
ot | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
half | +0.015 |
Mom | +0.015 |
sticker | +0.013 |
cookie | +0.013 |
icing | +0.012 |
Neg logit contributions | |
vill | -0.024 |
current | -0.023 |
vious | -0.023 |
challenged | -0.023 |
ot | -0.023 |
Token | there |
Token ID | 612 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
vill | +0.023 |
challenged | +0.022 |
current | +0.021 |
ot | +0.021 |
vious | +0.021 |
Neg logit contributions | |
Mom | -0.029 |
half | -0.029 |
sticker | -0.028 |
cookie | -0.027 |
icing | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
vill | +0.066 |
challenged | +0.064 |
ot | +0.063 |
current | +0.062 |
vious | +0.061 |
Neg logit contributions | |
Mom | -0.060 |
half | -0.060 |
sticker | -0.059 |
icing | -0.056 |
ribbon | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ot | +0.053 |
vill | +0.052 |
vious | +0.050 |
challenged | +0.050 |
current | +0.048 |
Neg logit contributions | |
sticker | -0.047 |
wrist | -0.047 |
ushes | -0.046 |
Mom | -0.045 |
half | -0.045 |
Token | little |
Token ID | 1310 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Mom | +0.023 |
half | +0.023 |
sticker | +0.022 |
cookie | +0.021 |
icing | +0.021 |
Neg logit contributions | |
vill | -0.016 |
challenged | -0.015 |
current | -0.015 |
ot | -0.015 |
vious | -0.015 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
vill | +0.040 |
current | +0.038 |
challenged | +0.037 |
ot | +0.037 |
vious | +0.036 |
Neg logit contributions | |
half | -0.048 |
Mom | -0.048 |
sticker | -0.046 |
icing | -0.045 |
cookie | -0.044 |
Token | said |
Token ID | 531 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
vill | +0.143 |
current | +0.142 |
hurricane | +0.138 |
harbor | +0.137 |
ot | +0.136 |
Neg logit contributions | |
half | -0.143 |
Mom | -0.136 |
sticker | -0.126 |
cookie | -0.123 |
ribbon | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
vill | +0.051 |
challenged | +0.049 |
current | +0.049 |
ot | +0.049 |
vious | +0.048 |
Neg logit contributions | |
Mom | -0.024 |
half | -0.024 |
sticker | -0.023 |
cookie | -0.021 |
icing | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Mom | +0.041 |
half | +0.041 |
sticker | +0.039 |
icing | +0.038 |
cookie | +0.037 |
Neg logit contributions | |
vill | -0.042 |
challenged | -0.040 |
current | -0.040 |
ot | -0.039 |
vious | -0.039 |
Token | It |
Token ID | 1026 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
vill | +0.019 |
vious | +0.017 |
current | +0.017 |
challenged | +0.017 |
ot | +0.017 |
Neg logit contributions | |
icing | -0.014 |
ribbon | -0.013 |
half | -0.013 |
sticker | -0.013 |
bookmark | -0.013 |
Token | is |
Token ID | 318 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
half | +0.018 |
Mom | +0.017 |
sticker | +0.017 |
cookie | +0.016 |
icing | +0.015 |
Neg logit contributions | |
vill | -0.040 |
current | -0.039 |
challenged | -0.039 |
ot | -0.038 |
vious | -0.038 |
Token | my |
Token ID | 616 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Mom | +0.038 |
wrist | +0.037 |
sticker | +0.036 |
icing | +0.035 |
half | +0.035 |
Neg logit contributions | |
ot | -0.041 |
vill | -0.040 |
current | -0.040 |
challenged | -0.039 |
fishermen | -0.038 |
Token | home |
Token ID | 1363 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mom | +0.124 |
half | +0.113 |
icing | +0.110 |
sticker | +0.110 |
Anna | +0.109 |
Neg logit contributions | |
vill | -0.129 |
ot | -0.127 |
current | -0.125 |
challenged | -0.119 |
vious | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
Mom | +0.035 |
ribbon | +0.035 |
icing | +0.033 |
half | +0.033 |
sticker | +0.032 |
Neg logit contributions | |
vill | -0.044 |
vious | -0.044 |
ot | -0.042 |
current | -0.042 |
challenged | -0.041 |
Token | I |
Token ID | 314 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
half | +0.030 |
ribbon | +0.030 |
sticker | +0.030 |
Mom | +0.029 |
icing | +0.029 |
Neg logit contributions | |
vill | -0.033 |
ot | -0.032 |
vious | -0.031 |
current | -0.031 |
challenged | -0.031 |
Token | have |
Token ID | 423 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
half | +0.020 |
Mom | +0.020 |
sticker | +0.019 |
cookie | +0.018 |
ribbon | +0.018 |
Neg logit contributions | |
vill | -0.027 |
current | -0.026 |
challenged | -0.026 |
ot | -0.026 |
vious | -0.026 |
Token | world |
Token ID | 995 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
Mom | +0.079 |
half | +0.077 |
sticker | +0.074 |
icing | +0.072 |
ushes | +0.072 |
Neg logit contributions | |
vill | -0.089 |
ot | -0.085 |
current | -0.084 |
challenged | -0.084 |
vious | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
vill | +0.195 |
challenged | +0.188 |
current | +0.187 |
ot | +0.185 |
vious | +0.185 |
Neg logit contributions | |
half | -0.133 |
Mom | -0.132 |
sticker | -0.126 |
cookie | -0.119 |
icing | -0.119 |
Token | just |
Token ID | 655 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
vill | +0.025 |
challenged | +0.024 |
current | +0.023 |
vious | +0.023 |
ot | +0.023 |
Neg logit contributions | |
half | -0.020 |
Mom | -0.020 |
sticker | -0.019 |
icing | -0.018 |
cookie | -0.018 |
Token | waiting |
Token ID | 4953 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
vill | +0.033 |
challenged | +0.031 |
current | +0.031 |
vious | +0.031 |
ot | +0.030 |
Neg logit contributions | |
half | -0.027 |
Mom | -0.025 |
sticker | -0.025 |
icing | -0.024 |
ribbon | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
vill | +0.013 |
challenged | +0.012 |
current | +0.012 |
ot | +0.012 |
vious | +0.012 |
Neg logit contributions | |
Mom | -0.010 |
half | -0.010 |
sticker | -0.010 |
cookie | -0.009 |
icing | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
vill | +0.060 |
challenged | +0.058 |
current | +0.058 |
ot | +0.057 |
vious | +0.056 |
Neg logit contributions | |
Mom | -0.045 |
half | -0.043 |
sticker | -0.042 |
cookie | -0.040 |
icing | -0.040 |
Token | explored |
Token ID | 18782 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
vill | +0.034 |
current | +0.032 |
challenged | +0.032 |
vious | +0.032 |
ot | +0.032 |
Neg logit contributions | |
half | -0.027 |
Mom | -0.026 |
sticker | -0.025 |
icing | -0.024 |
cookie | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
vill | +0.028 |
challenged | +0.027 |
current | +0.027 |
ot | +0.027 |
vious | +0.026 |
Neg logit contributions | |
Mom | -0.019 |
half | -0.019 |
sticker | -0.018 |
cookie | -0.017 |
icing | -0.017 |
Token | And |
Token ID | 843 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
vill | +0.024 |
challenged | +0.023 |
current | +0.023 |
ot | +0.022 |
vious | +0.022 |
Neg logit contributions | |
Mom | -0.014 |
half | -0.014 |
sticker | -0.014 |
icing | -0.013 |
cookie | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
vill | +0.008 |
vious | +0.008 |
current | +0.008 |
challenged | +0.008 |
ot | +0.007 |
Neg logit contributions | |
half | -0.006 |
Mom | -0.006 |
sticker | -0.005 |
ribbon | -0.005 |
cookie | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
vill | +0.136 |
vious | +0.134 |
challenged | +0.132 |
current | +0.131 |
ot | +0.131 |
Neg logit contributions | |
half | -0.096 |
Mom | -0.094 |
sticker | -0.088 |
cookie | -0.084 |
ribbon | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
vill | +0.254 |
challenged | +0.244 |
current | +0.243 |
ot | +0.239 |
vious | +0.233 |
Neg logit contributions | |
Mom | -0.157 |
half | -0.157 |
sticker | -0.143 |
cookie | -0.136 |
icing | -0.132 |
Token | did |
Token ID | 750 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
half | +0.043 |
Mom | +0.042 |
sticker | +0.041 |
herself | +0.041 |
cookie | +0.040 |
Neg logit contributions | |
vill | -0.036 |
ot | -0.033 |
ules | -0.032 |
current | -0.032 |
ican | -0.032 |
Token | not |
Token ID | 407 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Mom | +0.084 |
icing | +0.078 |
half | +0.076 |
sticker | +0.072 |
cookie | +0.072 |
Neg logit contributions | |
challenged | -0.137 |
vill | -0.136 |
vious | -0.132 |
current | -0.130 |
padd | -0.129 |
Token | want |
Token ID | 765 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
half | +0.027 |
sticker | +0.026 |
Mom | +0.026 |
cookie | +0.025 |
ribbon | +0.024 |
Neg logit contributions | |
vill | -0.025 |
current | -0.024 |
ot | -0.023 |
challenged | -0.023 |
vious | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Mom | +0.020 |
wrist | +0.018 |
half | +0.018 |
sticker | +0.018 |
icing | +0.017 |
Neg logit contributions | |
vill | -0.022 |
current | -0.020 |
challenged | -0.020 |
vious | -0.020 |
ot | -0.020 |
Token | touch |
Token ID | 3638 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
vill | +0.027 |
challenged | +0.026 |
ot | +0.026 |
current | +0.026 |
vious | +0.025 |
Neg logit contributions | |
Mom | -0.027 |
half | -0.026 |
sticker | -0.025 |
icing | -0.025 |
ushes | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Mom | +0.042 |
sticker | +0.039 |
half | +0.039 |
icing | +0.038 |
ushes | +0.038 |
Neg logit contributions | |
vill | -0.058 |
ot | -0.056 |
current | -0.056 |
vious | -0.055 |
challenged | -0.054 |
Token | chest |
Token ID | 7721 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
current | +0.039 |
ot | +0.038 |
vill | +0.037 |
eagle | +0.036 |
wolf | +0.035 |
Neg logit contributions | |
Mom | -0.045 |
ushes | -0.045 |
Her | -0.041 |
icing | -0.041 |
half | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Mom | +0.012 |
half | +0.011 |
sticker | +0.011 |
icing | +0.010 |
cookie | +0.010 |
Neg logit contributions | |
vill | -0.021 |
current | -0.020 |
challenged | -0.020 |
ot | -0.020 |
vious | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
half | +0.028 |
Mom | +0.027 |
sticker | +0.027 |
icing | +0.025 |
ribbon | +0.025 |
Neg logit contributions | |
vill | -0.045 |
challenged | -0.044 |
current | -0.043 |
ot | -0.043 |
vious | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
half | +0.045 |
sticker | +0.044 |
icing | +0.044 |
ribbon | +0.043 |
cookie | +0.043 |
Neg logit contributions | |
vill | -0.064 |
challenged | -0.061 |
current | -0.060 |
ot | -0.060 |
vious | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
vill | +0.004 |
challenged | +0.004 |
vious | +0.004 |
ot | +0.004 |
current | +0.004 |
Neg logit contributions | |
Mom | -0.003 |
half | -0.003 |
sticker | -0.003 |
ushes | -0.003 |
icing | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Mom | +0.026 |
half | +0.026 |
sticker | +0.024 |
cookie | +0.023 |
icing | +0.023 |
Neg logit contributions | |
vill | -0.034 |
challenged | -0.033 |
current | -0.033 |
ot | -0.033 |
vious | -0.033 |
Token | there |
Token ID | 612 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
half | +0.019 |
Mom | +0.019 |
sticker | +0.017 |
cookie | +0.017 |
icing | +0.016 |
Neg logit contributions | |
vill | -0.029 |
current | -0.028 |
vious | -0.028 |
challenged | -0.028 |
ot | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
vill | +0.067 |
challenged | +0.064 |
current | +0.064 |
ot | +0.063 |
vious | +0.063 |
Neg logit contributions | |
Mom | -0.056 |
half | -0.056 |
sticker | -0.054 |
icing | -0.052 |
cookie | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
ot | +0.052 |
vill | +0.051 |
challenged | +0.049 |
vious | +0.049 |
current | +0.048 |
Neg logit contributions | |
sticker | -0.040 |
half | -0.039 |
wrist | -0.039 |
ushes | -0.038 |
Mom | -0.038 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
Mom | +0.036 |
half | +0.036 |
sticker | +0.035 |
cookie | +0.033 |
icing | +0.033 |
Neg logit contributions | |
vill | -0.025 |
challenged | -0.024 |
current | -0.024 |
vious | -0.024 |
ot | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
vill | +0.170 |
current | +0.168 |
vious | +0.162 |
bust | +0.161 |
challenged | +0.159 |
Neg logit contributions | |
Mom | -0.150 |
half | -0.146 |
sticker | -0.140 |
cookie | -0.134 |
Anna | -0.127 |
Token | It |
Token ID | 632 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
vill | +0.017 |
challenged | +0.016 |
current | +0.016 |
vious | +0.016 |
ot | +0.016 |
Neg logit contributions | |
half | -0.017 |
Mom | -0.017 |
sticker | -0.016 |
cookie | -0.016 |
icing | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Mom | +0.028 |
half | +0.027 |
sticker | +0.026 |
cookie | +0.025 |
ribbon | +0.024 |
Neg logit contributions | |
vill | -0.039 |
current | -0.038 |
vious | -0.037 |
challenged | -0.037 |
fishermen | -0.036 |
Token | very |
Token ID | 845 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
vill | +0.048 |
challenged | +0.047 |
ot | +0.046 |
current | +0.046 |
vious | +0.046 |
Neg logit contributions | |
Mom | -0.036 |
half | -0.035 |
sticker | -0.034 |
icing | -0.032 |
ribbon | -0.032 |
Token | small |
Token ID | 1402 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
vill | +0.026 |
challenged | +0.025 |
current | +0.025 |
ot | +0.025 |
vious | +0.025 |
Neg logit contributions | |
Mom | -0.025 |
half | -0.025 |
sticker | -0.024 |
cookie | -0.023 |
icing | -0.023 |
Token | over |
Token ID | 625 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
vill | +0.107 |
challenged | +0.103 |
vious | +0.100 |
ot | +0.100 |
current | +0.099 |
Neg logit contributions | |
half | -0.112 |
sticker | -0.112 |
Mom | -0.111 |
icing | -0.109 |
wrist | -0.107 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Mom | +0.026 |
sticker | +0.025 |
half | +0.024 |
ushes | +0.024 |
scalp | +0.024 |
Neg logit contributions | |
vill | -0.027 |
challenged | -0.025 |
ot | -0.024 |
padd | -0.024 |
current | -0.024 |
Token | take |
Token ID | 1011 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
vill | +0.060 |
challenged | +0.058 |
ot | +0.057 |
current | +0.057 |
vious | +0.056 |
Neg logit contributions | |
Mom | -0.040 |
half | -0.039 |
sticker | -0.038 |
ushes | -0.037 |
cookie | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
vill | +0.030 |
challenged | +0.027 |
vious | +0.027 |
ot | +0.027 |
padd | +0.026 |
Neg logit contributions | |
Mom | -0.031 |
wrist | -0.029 |
ushes | -0.028 |
Anna | -0.027 |
half | -0.027 |
Token | closer |
Token ID | 5699 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Mom | +0.028 |
half | +0.027 |
sticker | +0.025 |
icing | +0.025 |
ushes | +0.025 |
Neg logit contributions | |
vill | -0.025 |
challenged | -0.024 |
ot | -0.024 |
vious | -0.023 |
current | -0.023 |
Token | look |
Token ID | 804 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
half | +0.010 |
sticker | +0.010 |
Mom | +0.010 |
ribbon | +0.009 |
cookie | +0.009 |
Neg logit contributions | |
vill | -0.014 |
challenged | -0.013 |
current | -0.013 |
vious | -0.013 |
ot | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
vill | +0.118 |
current | +0.114 |
challenged | +0.114 |
ot | +0.112 |
vious | +0.112 |
Neg logit contributions | |
half | -0.054 |
Mom | -0.053 |
sticker | -0.050 |
icing | -0.046 |
cookie | -0.046 |
Token | But |
Token ID | 887 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
vill | +0.011 |
challenged | +0.011 |
current | +0.010 |
ot | +0.010 |
vious | +0.010 |
Neg logit contributions | |
half | -0.011 |
sticker | -0.010 |
Mom | -0.010 |
icing | -0.010 |
ribbon | -0.010 |
Token | when |
Token ID | 618 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
vill | +0.073 |
challenged | +0.071 |
current | +0.070 |
ot | +0.070 |
vious | +0.068 |
Neg logit contributions | |
Mom | -0.059 |
half | -0.058 |
sticker | -0.057 |
icing | -0.054 |
cookie | -0.054 |
Token | Molly |
Token ID | 30236 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
vill | +0.006 |
current | +0.006 |
challenged | +0.006 |
ot | +0.006 |
vious | +0.005 |
Neg logit contributions | |
Mom | -0.004 |
half | -0.004 |
sticker | -0.004 |
ushes | -0.004 |
icing | -0.004 |
Token | got |
Token ID | 1392 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
half | +0.032 |
Mom | +0.032 |
sticker | +0.030 |
ribbon | +0.030 |
cookie | +0.030 |
Neg logit contributions | |
vill | -0.025 |
current | -0.024 |
ot | -0.024 |
vious | -0.024 |
challenged | -0.023 |
Token | Bob |
Token ID | 5811 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
vill | +0.010 |
challenged | +0.009 |
current | +0.009 |
ot | +0.009 |
vious | +0.009 |
Neg logit contributions | |
half | -0.013 |
sticker | -0.013 |
Mom | -0.013 |
ribbon | -0.012 |
icing | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
vill | +0.014 |
challenged | +0.014 |
ot | +0.013 |
current | +0.013 |
vious | +0.013 |
Neg logit contributions | |
Mom | -0.016 |
half | -0.016 |
sticker | -0.016 |
icing | -0.015 |
ushes | -0.015 |
Token | so |
Token ID | 523 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
vill | +0.036 |
challenged | +0.034 |
current | +0.034 |
vious | +0.033 |
ot | +0.033 |
Neg logit contributions | |
Mom | -0.053 |
half | -0.053 |
sticker | -0.052 |
cookie | -0.050 |
ribbon | -0.050 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
vill | +0.112 |
challenged | +0.107 |
current | +0.105 |
vious | +0.105 |
ot | +0.105 |
Neg logit contributions | |
Mom | -0.113 |
half | -0.112 |
sticker | -0.108 |
ribbon | -0.104 |
icing | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Mom | +0.052 |
half | +0.052 |
sticker | +0.049 |
cookie | +0.047 |
icing | +0.047 |
Neg logit contributions | |
vill | -0.066 |
challenged | -0.063 |
current | -0.063 |
ot | -0.063 |
vious | -0.062 |
Token | he |
Token ID | 339 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Mom | +0.013 |
half | +0.013 |
sticker | +0.012 |
cookie | +0.012 |
icing | +0.012 |
Neg logit contributions | |
vill | -0.010 |
challenged | -0.009 |
current | -0.009 |
vious | -0.009 |
ot | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
vill | +0.079 |
challenged | +0.076 |
current | +0.075 |
ot | +0.074 |
vious | +0.074 |
Neg logit contributions | |
Mom | -0.096 |
half | -0.095 |
sticker | -0.092 |
cookie | -0.088 |
icing | -0.088 |
Token | for |
Token ID | 329 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Mom | +0.036 |
half | +0.036 |
sticker | +0.034 |
icing | +0.033 |
cookie | +0.033 |
Neg logit contributions | |
vill | -0.054 |
challenged | -0.052 |
current | -0.052 |
ot | -0.051 |
vious | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Mom | +0.021 |
ushes | +0.020 |
half | +0.019 |
sticker | +0.019 |
icing | +0.019 |
Neg logit contributions | |
vill | -0.018 |
challenged | -0.017 |
ot | -0.017 |
current | -0.017 |
padd | -0.016 |
Token | first |
Token ID | 717 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
vill | +0.079 |
ot | +0.073 |
current | +0.072 |
vious | +0.071 |
challenged | +0.071 |
Neg logit contributions | |
Mom | -0.062 |
ushes | -0.058 |
half | -0.057 |
sticker | -0.054 |
wrist | -0.054 |
Token | time |
Token ID | 640 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
vill | +0.020 |
challenged | +0.019 |
current | +0.019 |
vious | +0.018 |
ot | +0.018 |
Neg logit contributions | |
Mom | -0.016 |
ushes | -0.015 |
half | -0.015 |
sticker | -0.014 |
icing | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
vill | +0.021 |
challenged | +0.020 |
current | +0.020 |
ot | +0.020 |
vious | +0.020 |
Neg logit contributions | |
Mom | -0.010 |
half | -0.010 |
sticker | -0.010 |
cookie | -0.009 |
icing | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
vill | +0.019 |
current | +0.018 |
vious | +0.018 |
ot | +0.018 |
challenged | +0.018 |
Neg logit contributions | |
Mom | -0.010 |
half | -0.009 |
sticker | -0.008 |
ribbon | -0.008 |
cookie | -0.008 |
Token | old |
Token ID | 1468 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
vious | +0.023 |
challenged | +0.023 |
vill | +0.022 |
ules | +0.022 |
bust | +0.022 |
Neg logit contributions | |
half | -0.026 |
Mom | -0.026 |
sticker | -0.025 |
cookie | -0.024 |
ribbon | -0.023 |
Token | man |
Token ID | 582 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
vious | +0.075 |
bust | +0.069 |
rified | +0.067 |
challenged | +0.066 |
lves | +0.066 |
Neg logit contributions | |
Mom | -0.062 |
half | -0.062 |
sticker | -0.061 |
cookie | -0.056 |
card | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
vill | +0.183 |
current | +0.181 |
vious | +0.178 |
ot | +0.175 |
challenged | +0.169 |
Neg logit contributions | |
half | -0.163 |
Mom | -0.157 |
sticker | -0.145 |
cookie | -0.138 |
ribbon | -0.137 |
Token | disappointed |
Token ID | 11679 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
vill | +0.056 |
current | +0.054 |
ot | +0.054 |
vious | +0.053 |
challenged | +0.052 |
Neg logit contributions | |
half | -0.056 |
Mom | -0.055 |
sticker | -0.052 |
cookie | -0.049 |
herself | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
vill | +0.183 |
vious | +0.178 |
challenged | +0.177 |
current | +0.175 |
ot | +0.174 |
Neg logit contributions | |
half | -0.110 |
Mom | -0.108 |
sticker | -0.101 |
cookie | -0.094 |
herself | -0.094 |
Token | he |
Token ID | 339 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
vious | +0.036 |
vill | +0.035 |
ot | +0.033 |
enced | +0.033 |
current | +0.033 |
Neg logit contributions | |
Mom | -0.034 |
half | -0.034 |
herself | -0.031 |
sticker | -0.031 |
ribbon | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
vill | +0.095 |
current | +0.092 |
vious | +0.091 |
ot | +0.091 |
ships | +0.086 |
Neg logit contributions | |
Mom | -0.099 |
half | -0.098 |
sticker | -0.093 |
ribbon | -0.090 |
cookie | -0.087 |
Token | hoped |
Token ID | 10719 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
half | +0.076 |
Mom | +0.068 |
sticker | +0.065 |
cookie | +0.060 |
icing | +0.060 |
Neg logit contributions | |
vill | -0.106 |
ot | -0.104 |
current | -0.103 |
vious | -0.101 |
bust | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
vill | +0.174 |
vious | +0.172 |
challenged | +0.171 |
current | +0.169 |
ot | +0.168 |
Neg logit contributions | |
half | -0.127 |
Mom | -0.122 |
sticker | -0.122 |
cookie | -0.112 |
ribbon | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
Mom | +0.005 |
half | +0.005 |
sticker | +0.005 |
Anna | +0.005 |
ushes | +0.005 |
Neg logit contributions | |
vill | -0.005 |
ot | -0.005 |
current | -0.005 |
challenged | -0.005 |
padd | -0.005 |
Token | walked |
Token ID | 6807 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
vill | +0.002 |
challenged | +0.001 |
current | +0.001 |
ot | +0.001 |
vious | +0.001 |
Neg logit contributions | |
Mom | -0.002 |
half | -0.002 |
sticker | -0.002 |
icing | -0.002 |
cookie | -0.002 |
Token | back |
Token ID | 736 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
vill | +0.196 |
challenged | +0.190 |
current | +0.187 |
ot | +0.185 |
vious | +0.182 |
Neg logit contributions | |
half | -0.177 |
Mom | -0.175 |
sticker | -0.174 |
cookie | -0.169 |
icing | -0.168 |
Token | home |
Token ID | 1363 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Mom | +0.055 |
half | +0.053 |
sticker | +0.051 |
icing | +0.050 |
cookie | +0.049 |
Neg logit contributions | |
vill | -0.071 |
challenged | -0.069 |
current | -0.067 |
ot | -0.067 |
vious | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Mom | +0.013 |
half | +0.012 |
sticker | +0.012 |
icing | +0.011 |
ribbon | +0.011 |
Neg logit contributions | |
vill | -0.024 |
challenged | -0.023 |
current | -0.023 |
ot | -0.023 |
vious | -0.022 |
Token | show |
Token ID | 905 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
vill | +0.057 |
challenged | +0.055 |
ot | +0.054 |
current | +0.054 |
vious | +0.052 |
Neg logit contributions | |
Mom | -0.053 |
half | -0.051 |
sticker | -0.049 |
ushes | -0.048 |
icing | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
vill | +0.100 |
challenged | +0.096 |
ot | +0.094 |
current | +0.093 |
vious | +0.092 |
Neg logit contributions | |
Mom | -0.101 |
half | -0.097 |
sticker | -0.094 |
icing | -0.092 |
cookie | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Mom | +0.012 |
half | +0.012 |
sticker | +0.011 |
icing | +0.011 |
cookie | +0.011 |
Neg logit contributions | |
vill | -0.016 |
challenged | -0.016 |
current | -0.016 |
ot | -0.016 |
vious | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
vill | +0.052 |
challenged | +0.049 |
ot | +0.049 |
current | +0.049 |
vious | +0.047 |
Neg logit contributions | |
Mom | -0.055 |
half | -0.054 |
sticker | -0.052 |
icing | -0.050 |
cookie | -0.050 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Mom | +0.025 |
half | +0.024 |
icing | +0.023 |
sticker | +0.023 |
ushes | +0.023 |
Neg logit contributions | |
vill | -0.036 |
ot | -0.036 |
current | -0.034 |
challenged | -0.033 |
padd | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Mom | +0.052 |
half | +0.051 |
sticker | +0.049 |
ribbon | +0.046 |
icing | +0.046 |
Neg logit contributions | |
vill | -0.092 |
challenged | -0.089 |
ot | -0.088 |
vious | -0.088 |
current | -0.087 |
Token | he |
Token ID | 339 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Mom | +0.134 |
half | +0.133 |
sticker | +0.128 |
cookie | +0.124 |
ribbon | +0.122 |
Neg logit contributions | |
vill | -0.103 |
vious | -0.097 |
challenged | -0.097 |
ot | -0.096 |
current | -0.096 |
Token | got |
Token ID | 1392 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
itive | +0.105 |
current | +0.100 |
ships | +0.098 |
vious | +0.097 |
ot | +0.097 |
Neg logit contributions | |
half | -0.099 |
Mom | -0.094 |
sticker | -0.085 |
Anna | -0.081 |
cookie | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
vill | +0.033 |
ot | +0.031 |
vious | +0.031 |
current | +0.031 |
challenged | +0.031 |
Neg logit contributions | |
Mom | -0.021 |
half | -0.021 |
sticker | -0.019 |
cookie | -0.017 |
ushes | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
vious | +0.082 |
vill | +0.079 |
challenged | +0.077 |
ules | +0.076 |
enced | +0.076 |
Neg logit contributions | |
half | -0.038 |
sticker | -0.034 |
Mom | -0.033 |
herself | -0.031 |
ribbon | -0.030 |
Token | river |
Token ID | 7850 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
ules | +0.082 |
itive | +0.080 |
vious | +0.077 |
oke | +0.075 |
challenged | +0.074 |
Neg logit contributions | |
Mom | -0.079 |
half | -0.076 |
sticker | -0.068 |
tape | -0.062 |
ourselves | -0.062 |
Token | bank |
Token ID | 17796 |
Feature activation | -9.80e+00 |
Pos logit contributions | |
vious | +0.212 |
itive | +0.204 |
vill | +0.200 |
lves | +0.198 |
ranc | +0.195 |
Neg logit contributions | |
half | -0.065 |
sticker | -0.043 |
herself | -0.043 |
Mom | -0.040 |
with | -0.039 |
Token | he |
Token ID | 339 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
vious | +0.526 |
vill | +0.523 |
ranc | +0.507 |
bust | +0.504 |
ican | +0.502 |
Neg logit contributions | |
half | -0.137 |
herself | -0.123 |
Mom | -0.096 |
with | -0.082 |
ourselves | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
itive | +0.107 |
vill | +0.100 |
vious | +0.099 |
current | +0.096 |
obstacle | +0.095 |
Neg logit contributions | |
half | -0.095 |
Mom | -0.088 |
sticker | -0.085 |
tape | -0.079 |
ribbon | -0.077 |
Token | very |
Token ID | 845 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
vill | +0.056 |
vious | +0.051 |
ot | +0.051 |
current | +0.051 |
challenged | +0.048 |
Neg logit contributions | |
half | -0.053 |
Mom | -0.051 |
sticker | -0.049 |
cookie | -0.046 |
icing | -0.046 |
Token | amazed |
Token ID | 24562 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
vill | +0.038 |
vious | +0.037 |
ican | +0.036 |
rified | +0.034 |
challenged | +0.034 |
Neg logit contributions | |
Mom | -0.031 |
half | -0.029 |
ushes | -0.027 |
sticker | -0.026 |
herself | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
vill | +0.213 |
current | +0.209 |
bust | +0.205 |
ranc | +0.204 |
challenged | +0.201 |
Neg logit contributions | |
half | -0.079 |
Mom | -0.073 |
sticker | -0.062 |
herself | -0.061 |
ribbon | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
vill | +0.121 |
challenged | +0.116 |
ot | +0.114 |
current | +0.112 |
vious | +0.112 |
Neg logit contributions | |
Mom | -0.085 |
half | -0.079 |
sticker | -0.076 |
icing | -0.073 |
ushes | -0.071 |
Token | They |
Token ID | 1119 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
vill | +0.012 |
challenged | +0.012 |
current | +0.011 |
bust | +0.011 |
ot | +0.011 |
Neg logit contributions | |
half | -0.009 |
sticker | -0.009 |
Mom | -0.009 |
icing | -0.009 |
ribbon | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
vill | +0.038 |
challenged | +0.037 |
current | +0.036 |
ot | +0.036 |
vious | +0.036 |
Neg logit contributions | |
Mom | -0.041 |
half | -0.041 |
sticker | -0.040 |
cookie | -0.038 |
icing | -0.038 |
Token | no |
Token ID | 645 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Mom | +0.007 |
half | +0.007 |
sticker | +0.007 |
ribbon | +0.006 |
cookie | +0.006 |
Neg logit contributions | |
vill | -0.007 |
challenged | -0.007 |
ot | -0.007 |
vious | -0.007 |
current | -0.007 |
Token | longer |
Token ID | 2392 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
vill | +0.004 |
challenged | +0.004 |
current | +0.004 |
ot | +0.004 |
vious | +0.004 |
Neg logit contributions | |
half | -0.003 |
Mom | -0.003 |
sticker | -0.003 |
icing | -0.003 |
cookie | -0.003 |
Token | en |
Token ID | 551 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
half | +0.011 |
sticker | +0.011 |
icing | +0.010 |
cookie | +0.010 |
Mom | +0.010 |
Neg logit contributions | |
vill | -0.007 |
ican | -0.007 |
current | -0.007 |
cient | -0.007 |
roads | -0.007 |
Token | vious |
Token ID | 1442 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
current | +0.123 |
ranc | +0.113 |
ships | +0.102 |
ot | +0.102 |
padd | +0.101 |
Neg logit contributions | |
half | -0.452 |
Mom | -0.419 |
sticker | -0.415 |
cookie | -0.409 |
ushes | -0.409 |
Token | of |
Token ID | 286 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
vill | +0.143 |
current | +0.137 |
challenged | +0.137 |
bust | +0.133 |
vious | +0.132 |
Neg logit contributions | |
half | -0.084 |
Mom | -0.078 |
sticker | -0.076 |
cookie | -0.073 |
icing | -0.072 |
Token | each |
Token ID | 1123 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Mom | +0.052 |
half | +0.049 |
sticker | +0.048 |
cookie | +0.045 |
icing | +0.045 |
Neg logit contributions | |
vill | -0.063 |
ot | -0.059 |
challenged | -0.059 |
current | -0.058 |
ships | -0.057 |
Token | other |
Token ID | 584 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
vill | +0.139 |
challenged | +0.134 |
current | +0.133 |
ot | +0.132 |
vious | +0.132 |
Neg logit contributions | |
Mom | -0.092 |
half | -0.092 |
sticker | -0.087 |
cookie | -0.082 |
icing | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Mom | +0.056 |
half | +0.054 |
sticker | +0.052 |
icing | +0.049 |
cookie | +0.048 |
Neg logit contributions | |
vill | -0.083 |
challenged | -0.080 |
ot | -0.079 |
current | -0.079 |
vious | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
half | +0.002 |
Mom | +0.002 |
sticker | +0.002 |
icing | +0.002 |
ribbon | +0.002 |
Neg logit contributions | |
vill | -0.004 |
challenged | -0.003 |
current | -0.003 |
ot | -0.003 |
vious | -0.003 |
Token | Standing |
Token ID | 44196 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Mom | +0.001 |
half | +0.001 |
sticker | +0.001 |
cookie | +0.001 |
ribbon | +0.001 |
Neg logit contributions | |
vill | -0.003 |
current | -0.002 |
ot | -0.002 |
challenged | -0.002 |
vious | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
vill | +0.074 |
challenged | +0.071 |
current | +0.070 |
vious | +0.070 |
ot | +0.070 |
Neg logit contributions | |
Mom | -0.049 |
half | -0.047 |
sticker | -0.045 |
icing | -0.042 |
ribbon | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
half | +0.053 |
Mom | +0.051 |
sticker | +0.048 |
cookie | +0.045 |
ribbon | +0.045 |
Neg logit contributions | |
vious | -0.090 |
vill | -0.090 |
challenged | -0.089 |
ot | -0.087 |
current | -0.087 |
Token | river |
Token ID | 7850 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
vious | +0.069 |
ules | +0.067 |
vill | +0.066 |
challenged | +0.065 |
itive | +0.063 |
Neg logit contributions | |
half | -0.075 |
Mom | -0.071 |
sticker | -0.071 |
cookie | -0.067 |
card | -0.067 |
Token | bank |
Token ID | 17796 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
vious | +0.160 |
vill | +0.153 |
lves | +0.150 |
ranc | +0.149 |
itive | +0.148 |
Neg logit contributions | |
half | -0.108 |
Mom | -0.093 |
sticker | -0.089 |
cookie | -0.082 |
card | -0.082 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
vill | +0.439 |
ranc | +0.430 |
vious | +0.428 |
current | +0.422 |
lves | +0.418 |
Neg logit contributions | |
half | -0.228 |
Mom | -0.190 |
herself | -0.184 |
sticker | -0.173 |
icing | -0.156 |
Token | a |
Token ID | 257 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
vill | +0.054 |
challenged | +0.052 |
current | +0.051 |
ot | +0.051 |
vious | +0.051 |
Neg logit contributions | |
half | -0.043 |
Mom | -0.043 |
sticker | -0.041 |
cookie | -0.039 |
icing | -0.039 |
Token | duck |
Token ID | 22045 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Mom | +0.022 |
half | +0.022 |
sticker | +0.022 |
cookie | +0.021 |
ribbon | +0.021 |
Neg logit contributions | |
vill | -0.020 |
challenged | -0.019 |
vious | -0.019 |
current | -0.018 |
ot | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
vill | +0.169 |
vious | +0.163 |
current | +0.161 |
challenged | +0.160 |
bust | +0.156 |
Neg logit contributions | |
half | -0.110 |
Mom | -0.107 |
sticker | -0.102 |
cookie | -0.098 |
ribbon | -0.095 |
Token | The |
Token ID | 383 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
vill | +0.025 |
vious | +0.024 |
itive | +0.024 |
challenged | +0.024 |
roads | +0.023 |
Neg logit contributions | |
half | -0.015 |
Mom | -0.015 |
cookie | -0.014 |
sticker | -0.014 |
icing | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
vill | +0.095 |
challenged | +0.095 |
ot | +0.092 |
vious | +0.091 |
current | +0.090 |
Neg logit contributions | |
Mom | -0.067 |
half | -0.067 |
sticker | -0.065 |
icing | -0.063 |
ribbon | -0.061 |
Token | but |
Token ID | 475 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
vill | +0.011 |
current | +0.011 |
vious | +0.011 |
challenged | +0.010 |
bust | +0.010 |
Neg logit contributions | |
half | -0.009 |
Mom | -0.008 |
sticker | -0.008 |
cookie | -0.008 |
ribbon | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
vill | +0.127 |
vious | +0.124 |
current | +0.120 |
challenged | +0.120 |
ot | +0.116 |
Neg logit contributions | |
half | -0.089 |
Mom | -0.089 |
sticker | -0.082 |
cookie | -0.079 |
ribbon | -0.076 |
Token | turtle |
Token ID | 28699 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
vious | +0.048 |
vill | +0.048 |
challenged | +0.047 |
current | +0.046 |
bust | +0.045 |
Neg logit contributions | |
Mom | -0.066 |
half | -0.065 |
sticker | -0.062 |
cookie | -0.061 |
ribbon | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
vill | +0.217 |
current | +0.217 |
vious | +0.202 |
bust | +0.199 |
ot | +0.196 |
Neg logit contributions | |
half | -0.184 |
Mom | -0.180 |
sticker | -0.176 |
cookie | -0.170 |
ribbon | -0.163 |
Token | en |
Token ID | 551 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
vill | +0.043 |
current | +0.041 |
vious | +0.041 |
ot | +0.040 |
challenged | +0.039 |
Neg logit contributions | |
half | -0.026 |
sticker | -0.024 |
Mom | -0.024 |
cookie | -0.023 |
Anna | -0.020 |
Token | vious |
Token ID | 1442 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
current | +0.107 |
vill | +0.093 |
ot | +0.087 |
padd | +0.085 |
ships | +0.084 |
Neg logit contributions | |
half | -0.456 |
Mom | -0.444 |
sticker | -0.434 |
Anna | -0.425 |
ushes | -0.425 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
vill | +0.165 |
current | +0.161 |
bust | +0.159 |
challenged | +0.158 |
ot | +0.154 |
Neg logit contributions | |
half | -0.058 |
Mom | -0.054 |
sticker | -0.051 |
cookie | -0.048 |
ribbon | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Mom | +0.059 |
half | +0.058 |
sticker | +0.056 |
icing | +0.053 |
cookie | +0.053 |
Neg logit contributions | |
vill | -0.080 |
challenged | -0.077 |
current | -0.076 |
ot | -0.076 |
vious | -0.075 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
vill | +0.055 |
challenged | +0.052 |
vious | +0.052 |
current | +0.052 |
bust | +0.051 |
Neg logit contributions | |
half | -0.064 |
Mom | -0.063 |
sticker | -0.061 |
cookie | -0.060 |
ribbon | -0.059 |
Token | 's |
Token ID | 338 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
vill | +0.187 |
challenged | +0.181 |
ot | +0.180 |
current | +0.179 |
vious | +0.178 |
Neg logit contributions | |
Mom | -0.105 |
half | -0.101 |
sticker | -0.096 |
icing | -0.091 |
ribbon | -0.089 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
vill | +0.064 |
challenged | +0.062 |
vious | +0.060 |
current | +0.059 |
ot | +0.058 |
Neg logit contributions | |
half | -0.083 |
Mom | -0.082 |
sticker | -0.078 |
cookie | -0.077 |
ribbon | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
vill | +0.091 |
challenged | +0.088 |
current | +0.087 |
ot | +0.087 |
vious | +0.087 |
Neg logit contributions | |
half | -0.041 |
Mom | -0.041 |
sticker | -0.039 |
cookie | -0.036 |
icing | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
vious | +0.011 |
itive | +0.011 |
vill | +0.011 |
challenged | +0.011 |
roads | +0.011 |
Neg logit contributions | |
half | -0.007 |
cookie | -0.007 |
Mom | -0.007 |
sticker | -0.007 |
icing | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
half | +0.016 |
Mom | +0.016 |
ribbon | +0.013 |
sticker | +0.012 |
cookie | +0.012 |
Neg logit contributions | |
vious | -0.033 |
vill | -0.033 |
ules | -0.031 |
fishermen | -0.031 |
current | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
vill | +0.051 |
current | +0.050 |
ot | +0.050 |
challenged | +0.049 |
vious | +0.048 |
Neg logit contributions | |
Mom | -0.034 |
half | -0.033 |
sticker | -0.032 |
wrist | -0.031 |
icing | -0.031 |
Token | tort |
Token ID | 7619 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
Mom | +0.028 |
half | +0.027 |
ushes | +0.026 |
icing | +0.026 |
sticker | +0.026 |
Neg logit contributions | |
vill | -0.026 |
ot | -0.025 |
current | -0.025 |
challenged | -0.024 |
padd | -0.022 |
Token | oise |
Token ID | 25678 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
vill | +0.173 |
current | +0.173 |
ot | +0.159 |
challenged | +0.157 |
vious | +0.150 |
Neg logit contributions | |
half | -0.403 |
Mom | -0.402 |
sticker | -0.371 |
wrist | -0.366 |
ribbon | -0.360 |
Token | ! |
Token ID | 0 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
vill | +0.203 |
challenged | +0.195 |
current | +0.194 |
vious | +0.193 |
ot | +0.193 |
Neg logit contributions | |
half | -0.140 |
Mom | -0.140 |
sticker | -0.133 |
cookie | -0.126 |
icing | -0.125 |
Token | The |
Token ID | 383 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
itive | +0.068 |
rated | +0.068 |
vious | +0.066 |
vill | +0.065 |
current | +0.065 |
Neg logit contributions | |
half | -0.038 |
Mom | -0.036 |
cookie | -0.036 |
sticker | -0.033 |
tape | -0.032 |
Token | all |
Token ID | 477 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ules | +0.038 |
enced | +0.038 |
vious | +0.037 |
vill | +0.036 |
challenged | +0.036 |
Neg logit contributions | |
half | -0.043 |
Mom | -0.042 |
cookie | -0.041 |
ribbon | -0.037 |
cookies | -0.037 |
Token | igator |
Token ID | 23823 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
ranc | +0.120 |
Pole | +0.120 |
harbor | +0.116 |
fishermen | +0.116 |
current | +0.114 |
Neg logit contributions | |
half | -0.171 |
her | -0.153 |
Mom | -0.151 |
cookie | -0.147 |
herself | -0.147 |