Token | first |
Token ID | 717 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
emo | +0.096 |
eer | +0.080 |
sailor | +0.077 |
ba | +0.077 |
cker | +0.077 |
Neg logit contributions | |
oph | -0.071 |
cake | -0.069 |
cakes | -0.068 |
board | -0.062 |
amusement | -0.061 |
Token | ." |
Token ID | 526 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
oph | +0.109 |
cake | +0.106 |
cakes | +0.104 |
board | +0.095 |
amusement | +0.094 |
Neg logit contributions | |
emo | -0.125 |
eer | -0.103 |
sailor | -0.102 |
ba | -0.100 |
cker | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
emo | +0.309 |
eer | +0.252 |
sailor | +0.250 |
ba | +0.246 |
cker | +0.243 |
Neg logit contributions | |
oph | -0.258 |
cake | -0.250 |
cakes | -0.245 |
board | -0.226 |
amusement | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
emo | +0.192 |
eer | +0.159 |
sailor | +0.156 |
ba | +0.154 |
cker | +0.153 |
Neg logit contributions | |
oph | -0.171 |
cake | -0.166 |
cakes | -0.162 |
board | -0.150 |
amusement | -0.148 |
Token | N |
Token ID | 45 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
emo | +0.232 |
ba | +0.194 |
sailor | +0.192 |
eer | +0.188 |
cker | +0.186 |
Neg logit contributions | |
oph | -0.132 |
cake | -0.128 |
cakes | -0.128 |
board | -0.115 |
amusement | -0.110 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
emo | +0.254 |
sailor | +0.226 |
eer | +0.224 |
rito | +0.221 |
crew | +0.218 |
Neg logit contributions | |
oph | -0.268 |
cake | -0.256 |
board | -0.240 |
cakes | -0.234 |
aw | -0.216 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
emo | +1.334 |
eer | +1.121 |
sailor | +1.102 |
ba | +1.090 |
rito | +1.087 |
Neg logit contributions | |
oph | -0.895 |
cake | -0.861 |
cakes | -0.837 |
board | -0.770 |
amusement | -0.748 |
Token | , |
Token ID | 11 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
emo | +0.308 |
cker | +0.261 |
eer | +0.259 |
rito | +0.253 |
ba | +0.251 |
Neg logit contributions | |
oph | -0.234 |
cake | -0.223 |
cakes | -0.216 |
board | -0.203 |
amusement | -0.200 |
Token | " |
Token ID | 366 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
emo | +0.094 |
eer | +0.086 |
cker | +0.081 |
rito | +0.081 |
fish | +0.079 |
Neg logit contributions | |
cake | -0.033 |
oph | -0.030 |
cakes | -0.027 |
That | -0.024 |
Meg | -0.023 |
Token | What |
Token ID | 2061 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
oph | +0.108 |
cake | +0.105 |
cakes | +0.099 |
board | +0.091 |
amusement | +0.090 |
Neg logit contributions | |
emo | -0.199 |
eer | -0.172 |
sailor | -0.165 |
rito | -0.164 |
cker | -0.164 |
Token | do |
Token ID | 466 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
oph | +0.128 |
cake | +0.124 |
cakes | +0.121 |
board | +0.114 |
amusement | +0.109 |
Neg logit contributions | |
emo | -0.249 |
rito | -0.222 |
ba | -0.214 |
cker | -0.212 |
eer | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +6.28e-03 |
Pos logit contributions | |
oph | +0.161 |
cake | +0.155 |
cakes | +0.152 |
amusement | +0.139 |
board | +0.138 |
Neg logit contributions | |
emo | -0.172 |
eer | -0.143 |
sailor | -0.139 |
ba | -0.137 |
cker | -0.135 |
Token | |
Token ID | 220 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
emo | +0.001 |
eer | +0.000 |
ba | +0.000 |
cker | +0.000 |
rito | +0.000 |
Neg logit contributions | |
oph | -0.000 |
cake | -0.000 |
cakes | -0.000 |
board | -0.000 |
amusement | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
cake | +0.080 |
cakes | +0.080 |
oph | +0.078 |
ue | +0.069 |
uct | +0.068 |
Neg logit contributions | |
emo | -0.154 |
sailor | -0.148 |
eer | -0.146 |
cker | -0.145 |
fish | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
emo | +0.190 |
eer | +0.180 |
cker | +0.175 |
sailor | +0.171 |
rito | +0.169 |
Neg logit contributions | |
oph | -0.126 |
cake | -0.119 |
cakes | -0.114 |
That | -0.109 |
board | -0.105 |
Token | N |
Token ID | 45 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
emo | +0.184 |
eer | +0.155 |
sailor | +0.151 |
ba | +0.149 |
cker | +0.149 |
Neg logit contributions | |
oph | -0.146 |
cake | -0.141 |
cakes | -0.137 |
board | -0.127 |
amusement | -0.125 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Albert | +0.037 |
Albert | +0.032 |
exc | +0.032 |
sailor | +0.032 |
crew | +0.029 |
Neg logit contributions | |
oph | -0.443 |
board | -0.422 |
cake | -0.410 |
aw | -0.409 |
ue | -0.387 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
emo | +1.313 |
eer | +1.102 |
sailor | +1.083 |
ba | +1.069 |
rito | +1.066 |
Neg logit contributions | |
oph | -0.909 |
cake | -0.875 |
cakes | -0.849 |
board | -0.783 |
amusement | -0.767 |
Token | his |
Token ID | 465 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
emo | +0.232 |
cker | +0.207 |
rito | +0.197 |
fish | +0.194 |
ba | +0.190 |
Neg logit contributions | |
oph | -0.244 |
cake | -0.224 |
amusement | -0.224 |
cakes | -0.218 |
board | -0.216 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
emo | +0.258 |
eer | +0.215 |
ba | +0.212 |
rito | +0.211 |
sailor | +0.209 |
Neg logit contributions | |
oph | -0.185 |
cake | -0.181 |
cakes | -0.175 |
amusement | -0.165 |
board | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
emo | +0.211 |
eer | +0.175 |
sailor | +0.172 |
ba | +0.170 |
cker | +0.168 |
Neg logit contributions | |
oph | -0.171 |
cake | -0.167 |
cakes | -0.163 |
board | -0.150 |
amusement | -0.148 |
Token | a |
Token ID | 257 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
emo | +0.055 |
eer | +0.049 |
cker | +0.047 |
rito | +0.047 |
fish | +0.045 |
Neg logit contributions | |
oph | -0.028 |
cake | -0.028 |
cakes | -0.025 |
amusement | -0.024 |
Meg | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
emo | +0.067 |
eer | +0.055 |
rito | +0.055 |
cker | +0.054 |
ba | +0.053 |
Neg logit contributions | |
cake | -0.047 |
oph | -0.047 |
cakes | -0.046 |
amusement | -0.044 |
board | -0.043 |
Token | |
Token ID | 220 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
oph | +0.003 |
cake | +0.002 |
cakes | +0.002 |
board | +0.002 |
ue | +0.002 |
Neg logit contributions | |
emo | -0.004 |
eer | -0.004 |
cker | -0.004 |
rito | -0.004 |
ba | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
cake | +0.080 |
oph | +0.080 |
cakes | +0.078 |
ue | +0.071 |
That | +0.069 |
Neg logit contributions | |
emo | -0.154 |
sailor | -0.147 |
eer | -0.146 |
cker | -0.145 |
rito | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
emo | +0.195 |
eer | +0.177 |
cker | +0.176 |
sailor | +0.172 |
rito | +0.170 |
Neg logit contributions | |
oph | -0.124 |
cake | -0.116 |
cakes | -0.113 |
ue | -0.106 |
board | -0.105 |
Token | N |
Token ID | 45 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
emo | +0.194 |
eer | +0.163 |
sailor | +0.160 |
ba | +0.159 |
cker | +0.158 |
Neg logit contributions | |
oph | -0.137 |
cake | -0.132 |
cakes | -0.129 |
board | -0.118 |
amusement | -0.116 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Albert | +0.044 |
Albert | +0.038 |
cker | +0.028 |
rito | +0.028 |
sailor | +0.024 |
Neg logit contributions | |
oph | -0.429 |
board | -0.415 |
aw | -0.402 |
cake | -0.396 |
ue | -0.378 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
emo | +1.454 |
rito | +1.298 |
eer | +1.278 |
sailor | +1.241 |
ba | +1.204 |
Neg logit contributions | |
oph | -0.704 |
cake | -0.612 |
board | -0.588 |
cakes | -0.580 |
ue | -0.554 |
Token | a |
Token ID | 257 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
oph | +0.027 |
cake | +0.026 |
cakes | +0.026 |
amusement | +0.025 |
aw | +0.025 |
Neg logit contributions | |
emo | -0.038 |
rito | -0.035 |
cker | -0.035 |
eer | -0.034 |
ba | -0.033 |
Token | big |
Token ID | 1263 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
emo | +0.029 |
eer | +0.027 |
rito | +0.026 |
cker | +0.025 |
eers | +0.024 |
Neg logit contributions | |
oph | -0.023 |
cake | -0.022 |
amusement | -0.022 |
board | -0.021 |
cakes | -0.021 |
Token | jet |
Token ID | 12644 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
oph | +0.073 |
cake | +0.071 |
cakes | +0.069 |
amusement | +0.067 |
board | +0.067 |
Neg logit contributions | |
emo | -0.051 |
eer | -0.038 |
ba | -0.038 |
rito | -0.037 |
cker | -0.036 |
Token | flying |
Token ID | 7348 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
emo | +0.050 |
sailor | +0.041 |
eer | +0.041 |
fish | +0.040 |
cker | +0.040 |
Neg logit contributions | |
oph | -0.060 |
cake | -0.058 |
cakes | -0.057 |
board | -0.051 |
amusement | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
emo | +0.493 |
eer | +0.417 |
sailor | +0.410 |
ba | +0.407 |
cker | +0.403 |
Neg logit contributions | |
oph | -0.315 |
cake | -0.305 |
cakes | -0.297 |
board | -0.269 |
amusement | -0.266 |
Token | |
Token ID | 220 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
emo | +0.003 |
eer | +0.003 |
cker | +0.003 |
sailor | +0.003 |
ba | +0.002 |
Neg logit contributions | |
oph | -0.002 |
cake | -0.002 |
cakes | -0.002 |
board | -0.002 |
amusement | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
cake | +0.081 |
oph | +0.081 |
cakes | +0.080 |
That | +0.070 |
ue | +0.070 |
Neg logit contributions | |
sailor | -0.156 |
emo | -0.155 |
eer | -0.155 |
cker | -0.152 |
rito | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
emo | +0.189 |
eer | +0.185 |
cker | +0.182 |
sailor | +0.176 |
rito | +0.173 |
Neg logit contributions | |
oph | -0.121 |
cake | -0.114 |
cakes | -0.112 |
That | -0.105 |
ue | -0.100 |
Token | N |
Token ID | 45 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
emo | +0.170 |
eer | +0.135 |
sailor | +0.134 |
ba | +0.134 |
cker | +0.130 |
Neg logit contributions | |
oph | -0.160 |
cake | -0.157 |
cakes | -0.154 |
board | -0.142 |
amusement | -0.141 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
emo | +0.013 |
rito | +0.011 |
cker | +0.011 |
sailor | +0.009 |
Albert | +0.007 |
Neg logit contributions | |
oph | -0.470 |
cake | -0.436 |
board | -0.429 |
cakes | -0.419 |
aw | -0.415 |
Token | said |
Token ID | 531 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
emo | +1.313 |
eer | +1.097 |
sailor | +1.082 |
ba | +1.080 |
cker | +1.068 |
Neg logit contributions | |
oph | -0.892 |
cake | -0.874 |
cakes | -0.856 |
board | -0.770 |
amusement | -0.768 |
Token | , |
Token ID | 11 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
cake | +0.121 |
oph | +0.118 |
cakes | +0.116 |
board | +0.103 |
Meg | +0.098 |
Neg logit contributions | |
emo | -0.225 |
eer | -0.199 |
rito | -0.195 |
cker | -0.195 |
ba | -0.192 |
Token | " |
Token ID | 366 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
emo | +0.061 |
eer | +0.053 |
cker | +0.052 |
rito | +0.052 |
sailor | +0.051 |
Neg logit contributions | |
cake | -0.031 |
oph | -0.031 |
cakes | -0.029 |
board | -0.026 |
That | -0.024 |
Token | Please |
Token ID | 5492 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
oph | +0.108 |
cake | +0.099 |
cakes | +0.093 |
That | +0.087 |
amusement | +0.084 |
Neg logit contributions | |
emo | -0.219 |
eer | -0.193 |
sailor | -0.187 |
rito | -0.187 |
cker | -0.184 |
Token | give |
Token ID | 1577 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
cake | +0.052 |
oph | +0.051 |
ue | +0.051 |
board | +0.050 |
cakes | +0.048 |
Neg logit contributions | |
emo | -0.086 |
eer | -0.074 |
cker | -0.073 |
rito | -0.070 |
eers | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
cake | +0.068 |
oph | +0.066 |
cakes | +0.065 |
board | +0.061 |
amusement | +0.058 |
Neg logit contributions | |
emo | -0.096 |
eer | -0.078 |
sailor | -0.077 |
cker | -0.077 |
ba | -0.076 |
Token | |
Token ID | 220 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
oph | +0.016 |
cake | +0.015 |
cakes | +0.014 |
board | +0.013 |
amusement | +0.013 |
Neg logit contributions | |
emo | -0.022 |
eer | -0.020 |
rito | -0.019 |
ba | -0.019 |
cker | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
cake | +0.068 |
cakes | +0.068 |
oph | +0.066 |
ue | +0.059 |
board | +0.058 |
Neg logit contributions | |
emo | -0.132 |
sailor | -0.131 |
eer | -0.126 |
cker | -0.126 |
rito | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
emo | +0.199 |
eer | +0.175 |
sailor | +0.171 |
cker | +0.168 |
rito | +0.166 |
Neg logit contributions | |
oph | -0.158 |
cake | -0.152 |
cakes | -0.147 |
board | -0.135 |
amusement | -0.134 |
Token | N |
Token ID | 45 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
emo | +0.218 |
ba | +0.178 |
sailor | +0.178 |
eer | +0.178 |
cker | +0.174 |
Neg logit contributions | |
oph | -0.142 |
cake | -0.139 |
cakes | -0.137 |
board | -0.124 |
amusement | -0.120 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
exc | +0.037 |
Albert | +0.034 |
sword | +0.034 |
sailor | +0.033 |
rito | +0.031 |
Neg logit contributions | |
oph | -0.433 |
board | -0.411 |
cake | -0.409 |
aw | -0.395 |
cakes | -0.379 |
Token | 's |
Token ID | 338 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
emo | +1.312 |
eer | +1.101 |
rito | +1.084 |
sailor | +1.076 |
cker | +1.049 |
Neg logit contributions | |
oph | -0.891 |
cake | -0.828 |
cakes | -0.797 |
board | -0.763 |
amusement | -0.738 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
oph | +0.133 |
cake | +0.129 |
cakes | +0.125 |
amusement | +0.123 |
board | +0.121 |
Neg logit contributions | |
emo | -0.145 |
eer | -0.118 |
ba | -0.117 |
rito | -0.117 |
cker | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
emo | +0.234 |
eer | +0.196 |
sailor | +0.191 |
rito | +0.190 |
ba | +0.190 |
Neg logit contributions | |
oph | -0.170 |
cake | -0.163 |
cakes | -0.158 |
board | -0.146 |
amusement | -0.144 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
emo | +0.057 |
eer | +0.049 |
rito | +0.048 |
cker | +0.047 |
sailor | +0.047 |
Neg logit contributions | |
oph | -0.040 |
cake | -0.038 |
cakes | -0.036 |
amusement | -0.034 |
board | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
oph | +0.054 |
cake | +0.048 |
board | +0.044 |
cakes | +0.044 |
ue | +0.044 |
Neg logit contributions | |
emo | -0.106 |
rito | -0.090 |
eer | -0.089 |
sailor | -0.086 |
ba | -0.085 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
emo | +0.241 |
rito | +0.229 |
cker | +0.226 |
Albert | +0.222 |
eer | +0.221 |
Neg logit contributions | |
amusement | -0.158 |
board | -0.156 |
oph | -0.146 |
ue | -0.145 |
Meg | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
emo | +0.146 |
eer | +0.122 |
sailor | +0.122 |
ba | +0.118 |
fish | +0.118 |
Neg logit contributions | |
oph | -0.162 |
cakes | -0.156 |
cake | -0.156 |
board | -0.137 |
ue | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
emo | +0.004 |
eer | +0.004 |
sailor | +0.004 |
ba | +0.004 |
cker | +0.004 |
Neg logit contributions | |
oph | -0.004 |
cake | -0.003 |
cakes | -0.003 |
board | -0.003 |
amusement | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
emo | +0.194 |
eer | +0.183 |
cker | +0.179 |
sailor | +0.179 |
rito | +0.176 |
Neg logit contributions | |
oph | -0.118 |
cake | -0.111 |
cakes | -0.107 |
ue | -0.103 |
board | -0.101 |
Token | N |
Token ID | 45 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
emo | +0.207 |
eer | +0.172 |
sailor | +0.170 |
ba | +0.170 |
cker | +0.167 |
Neg logit contributions | |
oph | -0.129 |
cake | -0.125 |
cakes | -0.122 |
board | -0.110 |
amusement | -0.109 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Albert | +0.037 |
Albert | +0.036 |
rito | +0.026 |
cker | +0.021 |
sailor | +0.020 |
Neg logit contributions | |
oph | -0.439 |
board | -0.422 |
aw | -0.410 |
cake | -0.403 |
ue | -0.386 |
Token | tried |
Token ID | 3088 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
emo | +1.338 |
eer | +1.117 |
sailor | +1.109 |
ba | +1.106 |
cker | +1.091 |
Neg logit contributions | |
oph | -0.872 |
cake | -0.858 |
cakes | -0.840 |
amusement | -0.746 |
board | -0.746 |
Token | to |
Token ID | 284 |
Feature activation | +6.16e-04 |
Pos logit contributions | |
emo | +0.253 |
eer | +0.212 |
sailor | +0.207 |
ba | +0.204 |
cker | +0.204 |
Neg logit contributions | |
oph | -0.207 |
cake | -0.201 |
cakes | -0.196 |
board | -0.181 |
amusement | -0.181 |
Token | swim |
Token ID | 9422 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
emo | +0.000 |
eer | +0.000 |
rito | +0.000 |
cker | +0.000 |
sailor | +0.000 |
Neg logit contributions | |
oph | -0.000 |
cake | -0.000 |
amusement | -0.000 |
cakes | -0.000 |
ue | -0.000 |
Token | away |
Token ID | 1497 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
emo | +0.558 |
eer | +0.462 |
sailor | +0.453 |
ba | +0.449 |
cker | +0.445 |
Neg logit contributions | |
oph | -0.455 |
cake | -0.443 |
cakes | -0.433 |
board | -0.399 |
amusement | -0.393 |
Token | , |
Token ID | 11 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
oph | +0.059 |
cake | +0.057 |
cakes | +0.055 |
board | +0.052 |
amusement | +0.050 |
Neg logit contributions | |
emo | -0.093 |
eer | -0.080 |
cker | -0.077 |
sailor | -0.077 |
rito | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
emo | +0.264 |
eer | +0.216 |
rito | +0.213 |
sailor | +0.210 |
ba | +0.209 |
Neg logit contributions | |
cake | -0.151 |
cakes | -0.147 |
oph | -0.140 |
amusement | -0.140 |
board | -0.135 |
Token | |
Token ID | 220 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
oph | +0.006 |
cake | +0.006 |
cakes | +0.006 |
board | +0.005 |
amusement | +0.005 |
Neg logit contributions | |
emo | -0.004 |
eer | -0.003 |
ba | -0.003 |
rito | -0.003 |
sailor | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
cake | +0.082 |
oph | +0.081 |
cakes | +0.080 |
ue | +0.072 |
uct | +0.071 |
Neg logit contributions | |
emo | -0.166 |
sailor | -0.164 |
eer | -0.161 |
cker | -0.158 |
fish | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
emo | +0.180 |
eer | +0.171 |
cker | +0.165 |
rito | +0.164 |
sailor | +0.164 |
Neg logit contributions | |
oph | -0.121 |
cake | -0.114 |
cakes | -0.108 |
That | -0.100 |
ue | -0.099 |
Token | N |
Token ID | 45 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
emo | +0.164 |
eer | +0.133 |
sailor | +0.131 |
ba | +0.130 |
cker | +0.128 |
Neg logit contributions | |
oph | -0.149 |
cake | -0.146 |
cakes | -0.142 |
board | -0.132 |
amusement | -0.130 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
rito | +0.027 |
Albert | +0.021 |
sailor | +0.021 |
Albert | +0.021 |
paddle | +0.020 |
Neg logit contributions | |
oph | -0.460 |
cake | -0.417 |
board | -0.414 |
aw | -0.401 |
ue | -0.384 |
Token | was |
Token ID | 373 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
emo | +1.293 |
eer | +1.081 |
sailor | +1.064 |
ba | +1.057 |
cker | +1.046 |
Neg logit contributions | |
oph | -0.910 |
cake | -0.885 |
cakes | -0.863 |
board | -0.786 |
amusement | -0.776 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
oph | +0.037 |
cake | +0.036 |
amusement | +0.033 |
cakes | +0.033 |
uct | +0.032 |
Neg logit contributions | |
emo | -0.057 |
eer | -0.049 |
fish | -0.048 |
sailor | -0.047 |
rito | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
emo | +0.103 |
eer | +0.087 |
sailor | +0.085 |
ba | +0.084 |
cker | +0.083 |
Neg logit contributions | |
oph | -0.069 |
cake | -0.066 |
cakes | -0.065 |
board | -0.059 |
amusement | -0.058 |
Token | didn |
Token ID | 1422 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.017 |
uct | +0.017 |
cakes | +0.017 |
board | +0.016 |
Neg logit contributions | |
emo | -0.029 |
rito | -0.025 |
eer | -0.025 |
ba | -0.024 |
sailor | -0.023 |
Token | 't |
Token ID | 470 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
oph | +0.030 |
cake | +0.029 |
cakes | +0.028 |
board | +0.026 |
amusement | +0.026 |
Neg logit contributions | |
emo | -0.037 |
eer | -0.030 |
sailor | -0.030 |
ba | -0.030 |
cker | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
emo | +0.001 |
eer | +0.000 |
ba | +0.000 |
sailor | +0.000 |
cker | +0.000 |
Neg logit contributions | |
oph | -0.000 |
cake | -0.000 |
cakes | -0.000 |
board | -0.000 |
amusement | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
emo | +0.141 |
eer | +0.120 |
rito | +0.120 |
sailor | +0.116 |
ba | +0.115 |
Neg logit contributions | |
oph | -0.096 |
cake | -0.091 |
cakes | -0.089 |
board | -0.082 |
amusement | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
cake | +0.135 |
oph | +0.132 |
cakes | +0.131 |
board | +0.115 |
aw | +0.111 |
Neg logit contributions | |
emo | -0.224 |
eer | -0.193 |
rito | -0.192 |
cker | -0.189 |
ba | -0.188 |
Token | " |
Token ID | 366 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
emo | +0.065 |
eer | +0.056 |
cker | +0.054 |
rito | +0.054 |
ba | +0.054 |
Neg logit contributions | |
cake | -0.030 |
oph | -0.029 |
cakes | -0.028 |
board | -0.025 |
That | -0.023 |
Token | N |
Token ID | 45 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
oph | +0.110 |
cake | +0.105 |
cakes | +0.100 |
board | +0.090 |
amusement | +0.088 |
Neg logit contributions | |
emo | -0.216 |
eer | -0.186 |
sailor | -0.183 |
ba | -0.180 |
rito | -0.180 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
emo | +0.155 |
sailor | +0.141 |
Albert | +0.138 |
Albert | +0.135 |
rito | +0.133 |
Neg logit contributions | |
oph | -0.334 |
cake | -0.322 |
board | -0.312 |
cakes | -0.306 |
aw | -0.304 |
Token | , |
Token ID | 11 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
emo | +1.387 |
rito | +1.178 |
ba | +1.164 |
sailor | +1.161 |
eer | +1.157 |
Neg logit contributions | |
oph | -0.772 |
cake | -0.738 |
cakes | -0.692 |
board | -0.691 |
ue | -0.649 |
Token | you |
Token ID | 345 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
emo | +0.055 |
eer | +0.046 |
cker | +0.045 |
rito | +0.045 |
ba | +0.044 |
Neg logit contributions | |
oph | -0.042 |
cake | -0.041 |
cakes | -0.040 |
board | -0.037 |
amusement | -0.037 |
Token | must |
Token ID | 1276 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
emo | +0.152 |
rito | +0.129 |
cker | +0.127 |
eer | +0.124 |
ba | +0.122 |
Neg logit contributions | |
oph | -0.081 |
cake | -0.079 |
cakes | -0.077 |
board | -0.076 |
amusement | -0.074 |
Token | keep |
Token ID | 1394 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
oph | +0.016 |
cake | +0.015 |
amusement | +0.014 |
ue | +0.014 |
cakes | +0.014 |
Neg logit contributions | |
emo | -0.019 |
eer | -0.017 |
sailor | -0.016 |
fish | -0.016 |
rito | -0.016 |
Token | swimming |
Token ID | 14899 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
emo | +0.399 |
rito | +0.356 |
fish | +0.348 |
ba | +0.333 |
oster | +0.330 |
Neg logit contributions | |
course | -0.177 |
amusement | -0.166 |
aw | -0.153 |
Meg | -0.152 |
uct | -0.152 |
Token | far |
Token ID | 1290 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
cakes | +0.231 |
cake | +0.226 |
oph | +0.223 |
amusement | +0.221 |
That | +0.216 |
Neg logit contributions | |
emo | -0.292 |
rito | -0.280 |
eer | -0.272 |
cker | -0.271 |
ba | -0.251 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
emo | +0.150 |
eer | +0.116 |
cker | +0.114 |
ba | +0.113 |
rito | +0.113 |
Neg logit contributions | |
oph | -0.196 |
cake | -0.187 |
amusement | -0.180 |
board | -0.179 |
cakes | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
emo | +0.307 |
eer | +0.297 |
rito | +0.293 |
cker | +0.291 |
ba | +0.271 |
Neg logit contributions | |
oph | -0.274 |
cake | -0.249 |
cakes | -0.241 |
board | -0.233 |
That | -0.227 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
eer | +0.205 |
cker | +0.204 |
emo | +0.201 |
rito | +0.198 |
sailor | +0.191 |
Neg logit contributions | |
oph | -0.103 |
cake | -0.088 |
cakes | -0.085 |
ue | -0.084 |
That | -0.081 |
Token | N |
Token ID | 45 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
emo | +0.153 |
eer | +0.133 |
cker | +0.125 |
rito | +0.125 |
sailor | +0.124 |
Neg logit contributions | |
oph | -0.169 |
cake | -0.162 |
cakes | -0.158 |
board | -0.149 |
amusement | -0.147 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
rito | +0.006 |
sailor | +0.006 |
cker | +0.005 |
emo | +0.004 |
Albert | +0.004 |
Neg logit contributions | |
oph | -0.478 |
cake | -0.448 |
board | -0.442 |
cakes | -0.429 |
aw | -0.422 |
Token | replied |
Token ID | 8712 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
emo | +1.418 |
eer | +1.217 |
sailor | +1.198 |
rito | +1.188 |
ba | +1.180 |
Neg logit contributions | |
oph | -0.779 |
cake | -0.735 |
cakes | -0.707 |
board | -0.650 |
amusement | -0.622 |
Token | , |
Token ID | 11 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
cake | +0.304 |
oph | +0.304 |
cakes | +0.294 |
board | +0.268 |
ue | +0.249 |
Neg logit contributions | |
emo | -0.496 |
eer | -0.429 |
cker | -0.418 |
rito | -0.418 |
ba | -0.414 |
Token | " |
Token ID | 366 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
emo | +0.061 |
eer | +0.052 |
sailor | +0.051 |
rito | +0.051 |
ba | +0.050 |
Neg logit contributions | |
oph | -0.035 |
cake | -0.035 |
cakes | -0.033 |
board | -0.030 |
amusement | -0.029 |
Token | I |
Token ID | 40 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
oph | +0.108 |
cake | +0.104 |
cakes | +0.100 |
board | +0.091 |
amusement | +0.087 |
Neg logit contributions | |
emo | -0.214 |
eer | -0.187 |
sailor | -0.183 |
rito | -0.183 |
cker | -0.180 |
Token | want |
Token ID | 765 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
oph | +0.026 |
� | +0.025 |
amusement | +0.025 |
board | +0.025 |
cake | +0.024 |
Neg logit contributions | |
emo | -0.047 |
Albert | -0.040 |
rito | -0.040 |
eer | -0.040 |
Albert | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
emo | +0.165 |
cker | +0.152 |
rito | +0.149 |
oster | +0.146 |
ba | +0.144 |
Neg logit contributions | |
aw | -0.062 |
course | -0.057 |
oph | -0.053 |
That | -0.051 |
amusement | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
emo | +0.196 |
eer | +0.164 |
sailor | +0.160 |
cker | +0.158 |
rito | +0.157 |
Neg logit contributions | |
oph | -0.144 |
cake | -0.141 |
cakes | -0.137 |
board | -0.128 |
amusement | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
emo | +0.004 |
eer | +0.004 |
cker | +0.004 |
rito | +0.004 |
ba | +0.004 |
Neg logit contributions | |
oph | -0.003 |
cakes | -0.002 |
cake | -0.002 |
board | -0.002 |
ue | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
emo | +0.203 |
cker | +0.190 |
eer | +0.189 |
rito | +0.184 |
sailor | +0.183 |
Neg logit contributions | |
oph | -0.116 |
cake | -0.106 |
cakes | -0.104 |
ue | -0.100 |
board | -0.097 |
Token | N |
Token ID | 45 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
emo | +0.167 |
eer | +0.135 |
sailor | +0.133 |
ba | +0.131 |
cker | +0.130 |
Neg logit contributions | |
oph | -0.169 |
cake | -0.164 |
cakes | -0.161 |
board | -0.150 |
amusement | -0.148 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
Albert | +0.043 |
Albert | +0.039 |
cker | +0.027 |
rito | +0.025 |
sailor | +0.023 |
Neg logit contributions | |
oph | -0.432 |
board | -0.416 |
cake | -0.398 |
aw | -0.392 |
ue | -0.378 |
Token | 's |
Token ID | 338 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
emo | +1.297 |
rito | +1.136 |
eer | +1.131 |
sailor | +1.100 |
ba | +1.043 |
Neg logit contributions | |
oph | -0.836 |
cake | -0.754 |
cakes | -0.723 |
board | -0.717 |
ue | -0.690 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
oph | +0.123 |
cake | +0.117 |
board | +0.116 |
cakes | +0.115 |
amusement | +0.114 |
Neg logit contributions | |
emo | -0.141 |
rito | -0.132 |
cker | -0.127 |
eer | -0.126 |
ba | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
emo | +0.219 |
eer | +0.183 |
sailor | +0.180 |
ba | +0.178 |
cker | +0.177 |
Neg logit contributions | |
oph | -0.162 |
cake | -0.157 |
cakes | -0.153 |
board | -0.140 |
amusement | -0.138 |
Token | D |
Token ID | 360 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
emo | +0.060 |
eer | +0.050 |
sailor | +0.050 |
ba | +0.049 |
cker | +0.049 |
Neg logit contributions | |
oph | -0.043 |
cake | -0.041 |
cakes | -0.040 |
board | -0.037 |
amusement | -0.036 |
Token | ory |
Token ID | 652 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
emo | +0.200 |
cker | +0.192 |
rito | +0.190 |
eer | +0.187 |
Albert | +0.185 |
Neg logit contributions | |
oph | -0.193 |
board | -0.170 |
cake | -0.169 |
cakes | -0.157 |
ue | -0.151 |
Token | fish |
Token ID | 5916 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
cakes | +0.019 |
cake | +0.019 |
oph | +0.018 |
board | +0.018 |
amusement | +0.018 |
Neg logit contributions | |
emo | -0.026 |
ba | -0.022 |
cker | -0.022 |
rito | -0.021 |
eer | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
emo | +0.483 |
eer | +0.398 |
sailor | +0.394 |
ba | +0.391 |
rito | +0.386 |
Neg logit contributions | |
oph | -0.369 |
cake | -0.365 |
cakes | -0.354 |
board | -0.327 |
amusement | -0.317 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
oph | +0.014 |
cake | +0.014 |
cakes | +0.013 |
amusement | +0.012 |
board | +0.012 |
Neg logit contributions | |
emo | -0.016 |
eer | -0.013 |
sailor | -0.013 |
ba | -0.013 |
cker | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
emo | +0.160 |
eer | +0.137 |
sailor | +0.134 |
cker | +0.132 |
ba | +0.130 |
Neg logit contributions | |
oph | -0.132 |
cake | -0.129 |
cakes | -0.125 |
board | -0.115 |
ue | -0.113 |
Token | N |
Token ID | 45 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
emo | +0.177 |
ba | +0.146 |
sailor | +0.142 |
oster | +0.139 |
Albert | +0.139 |
Neg logit contributions | |
oph | -0.130 |
cakes | -0.125 |
cake | -0.125 |
board | -0.111 |
amusement | -0.108 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
emo | +0.104 |
rito | +0.101 |
cker | +0.100 |
exc | +0.097 |
sword | +0.092 |
Neg logit contributions | |
oph | -0.346 |
board | -0.330 |
cake | -0.319 |
aw | -0.317 |
cakes | -0.300 |
Token | and |
Token ID | 290 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
emo | +1.262 |
eer | +1.053 |
sailor | +1.035 |
ba | +1.022 |
rito | +1.018 |
Neg logit contributions | |
oph | -0.924 |
cake | -0.892 |
cakes | -0.867 |
board | -0.803 |
amusement | -0.784 |
Token | his |
Token ID | 465 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.017 |
Meg | +0.016 |
amusement | +0.016 |
cakes | +0.016 |
Neg logit contributions | |
emo | -0.020 |
rito | -0.018 |
cker | -0.017 |
eer | -0.017 |
fish | -0.017 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
emo | +0.227 |
rito | +0.197 |
ba | +0.190 |
cker | +0.187 |
eer | +0.181 |
Neg logit contributions | |
oph | -0.184 |
cake | -0.183 |
cakes | -0.181 |
amusement | -0.179 |
board | -0.176 |
Token | tried |
Token ID | 3088 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
emo | +0.144 |
eer | +0.123 |
sailor | +0.123 |
ba | +0.122 |
cker | +0.120 |
Neg logit contributions | |
oph | -0.128 |
cake | -0.127 |
cakes | -0.125 |
board | -0.109 |
amusement | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
emo | +0.220 |
eer | +0.185 |
sailor | +0.180 |
ba | +0.180 |
rito | +0.178 |
Neg logit contributions | |
oph | -0.172 |
cake | -0.169 |
cakes | -0.165 |
amusement | -0.152 |
board | -0.150 |
Token | ocean |
Token ID | 9151 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
oph | +0.015 |
cake | +0.014 |
cakes | +0.014 |
board | +0.013 |
amusement | +0.013 |
Neg logit contributions | |
emo | -0.020 |
eer | -0.016 |
sailor | -0.016 |
ba | -0.016 |
cker | -0.016 |
Token | ." |
Token ID | 526 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
emo | +0.008 |
eer | +0.007 |
sailor | +0.007 |
ba | +0.007 |
fish | +0.007 |
Neg logit contributions | |
oph | -0.008 |
cake | -0.008 |
cakes | -0.008 |
amusement | -0.007 |
board | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
emo | +0.302 |
eer | +0.242 |
sailor | +0.240 |
ba | +0.236 |
cker | +0.231 |
Neg logit contributions | |
oph | -0.286 |
cake | -0.281 |
cakes | -0.276 |
board | -0.255 |
amusement | -0.252 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
emo | +0.171 |
eer | +0.140 |
sailor | +0.138 |
ba | +0.136 |
cker | +0.135 |
Neg logit contributions | |
oph | -0.157 |
cake | -0.152 |
cakes | -0.149 |
board | -0.138 |
amusement | -0.136 |
Token | N |
Token ID | 45 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
emo | +0.212 |
ba | +0.178 |
sailor | +0.176 |
Albert | +0.171 |
cker | +0.171 |
Neg logit contributions | |
oph | -0.121 |
cakes | -0.121 |
cake | -0.120 |
board | -0.108 |
amusement | -0.101 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
emo | +0.221 |
sailor | +0.204 |
crew | +0.200 |
sail | +0.199 |
sword | +0.198 |
Neg logit contributions | |
oph | -0.264 |
cake | -0.245 |
board | -0.236 |
cakes | -0.225 |
aw | -0.219 |
Token | was |
Token ID | 373 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
emo | +1.291 |
eer | +1.078 |
sailor | +1.061 |
rito | +1.056 |
ba | +1.044 |
Neg logit contributions | |
oph | -0.892 |
cake | -0.853 |
cakes | -0.828 |
board | -0.774 |
amusement | -0.747 |
Token | curious |
Token ID | 11040 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
oph | +0.031 |
cake | +0.031 |
cakes | +0.029 |
amusement | +0.028 |
uct | +0.028 |
Neg logit contributions | |
emo | -0.043 |
eer | -0.036 |
fish | -0.035 |
sailor | -0.035 |
ba | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
emo | +0.060 |
eer | +0.054 |
sailor | +0.053 |
fish | +0.050 |
cker | +0.048 |
Neg logit contributions | |
oph | -0.063 |
cakes | -0.060 |
cake | -0.060 |
liv | -0.056 |
Tam | -0.054 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
oph | +0.004 |
cake | +0.004 |
cakes | +0.004 |
uct | +0.004 |
That | +0.004 |
Neg logit contributions | |
emo | -0.007 |
rito | -0.006 |
eer | -0.006 |
ba | -0.005 |
sailor | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
cake | +0.011 |
oph | +0.011 |
cakes | +0.010 |
amusement | +0.010 |
board | +0.009 |
Neg logit contributions | |
emo | -0.017 |
eer | -0.014 |
ba | -0.014 |
rito | -0.014 |
cker | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
emo | +0.143 |
eer | +0.119 |
sailor | +0.116 |
ba | +0.115 |
cker | +0.114 |
Neg logit contributions | |
oph | -0.120 |
cake | -0.117 |
cakes | -0.113 |
board | -0.105 |
amusement | -0.104 |
Token | |
Token ID | 220 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
oph | +0.011 |
cake | +0.011 |
cakes | +0.010 |
board | +0.010 |
amusement | +0.009 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.011 |
sailor | -0.011 |
ba | -0.011 |
cker | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
cake | +0.094 |
oph | +0.094 |
cakes | +0.093 |
ue | +0.084 |
uct | +0.081 |
Neg logit contributions | |
emo | -0.172 |
sailor | -0.167 |
eer | -0.165 |
cker | -0.162 |
fish | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
emo | +0.177 |
eer | +0.168 |
cker | +0.163 |
sailor | +0.162 |
rito | +0.155 |
Neg logit contributions | |
oph | -0.116 |
cake | -0.112 |
cakes | -0.107 |
That | -0.102 |
ue | -0.100 |
Token | N |
Token ID | 45 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
emo | +0.177 |
eer | +0.146 |
sailor | +0.144 |
ba | +0.143 |
cker | +0.141 |
Neg logit contributions | |
oph | -0.134 |
cake | -0.130 |
cakes | -0.127 |
board | -0.117 |
amusement | -0.115 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
Albert | +0.040 |
Albert | +0.039 |
sailor | +0.034 |
crew | +0.031 |
exc | +0.031 |
Neg logit contributions | |
oph | -0.400 |
board | -0.388 |
aw | -0.384 |
cake | -0.370 |
ue | -0.355 |
Token | finally |
Token ID | 3443 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
emo | +1.232 |
eer | +1.024 |
sailor | +1.006 |
ba | +0.997 |
cker | +0.986 |
Neg logit contributions | |
oph | -0.955 |
cake | -0.927 |
cakes | -0.903 |
board | -0.831 |
amusement | -0.818 |
Token | reached |
Token ID | 4251 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
emo | +0.063 |
fish | +0.051 |
sailor | +0.050 |
ba | +0.050 |
eer | +0.048 |
Neg logit contributions | |
cake | -0.052 |
cakes | -0.052 |
oph | -0.051 |
amusement | -0.048 |
board | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
emo | +0.065 |
eer | +0.057 |
cker | +0.057 |
ba | +0.057 |
oster | +0.055 |
Neg logit contributions | |
Meg | -0.024 |
amusement | -0.024 |
oph | -0.023 |
Tom | -0.022 |
cake | -0.022 |
Token | other |
Token ID | 584 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
oph | +0.033 |
cake | +0.032 |
cakes | +0.032 |
board | +0.029 |
amusement | +0.029 |
Neg logit contributions | |
emo | -0.036 |
eer | -0.030 |
sailor | -0.029 |
ba | -0.029 |
cker | -0.028 |
Token | side |
Token ID | 1735 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
oph | +0.056 |
cake | +0.054 |
cakes | +0.053 |
board | +0.047 |
uct | +0.046 |
Neg logit contributions | |
emo | -0.081 |
eer | -0.069 |
sailor | -0.068 |
ba | -0.067 |
cker | -0.066 |
Token | you |
Token ID | 345 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
emo | +0.139 |
ba | +0.115 |
cker | +0.115 |
eer | +0.114 |
rito | +0.113 |
Neg logit contributions | |
oph | -0.099 |
cakes | -0.094 |
cake | -0.093 |
amusement | -0.088 |
aw | -0.086 |
Token | ." |
Token ID | 526 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
emo | +0.153 |
eer | +0.129 |
rito | +0.127 |
ba | +0.125 |
cker | +0.124 |
Neg logit contributions | |
cake | -0.080 |
cakes | -0.077 |
oph | -0.076 |
amusement | -0.074 |
board | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
emo | +0.306 |
eer | +0.247 |
sailor | +0.246 |
ba | +0.241 |
cker | +0.236 |
Neg logit contributions | |
oph | -0.257 |
cake | -0.251 |
cakes | -0.246 |
board | -0.227 |
amusement | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
emo | +0.180 |
eer | +0.146 |
sailor | +0.144 |
ba | +0.142 |
cker | +0.141 |
Neg logit contributions | |
oph | -0.168 |
cake | -0.164 |
cakes | -0.160 |
board | -0.148 |
amusement | -0.146 |
Token | N |
Token ID | 45 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
emo | +0.221 |
ba | +0.187 |
sailor | +0.184 |
Albert | +0.179 |
cker | +0.178 |
Neg logit contributions | |
oph | -0.136 |
cake | -0.133 |
cakes | -0.132 |
board | -0.120 |
amusement | -0.110 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
emo | +0.237 |
sailor | +0.212 |
rito | +0.210 |
crew | +0.205 |
eer | +0.204 |
Neg logit contributions | |
oph | -0.245 |
cake | -0.234 |
board | -0.225 |
cakes | -0.218 |
aw | -0.205 |
Token | was |
Token ID | 373 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
emo | +1.304 |
eer | +1.093 |
sailor | +1.076 |
rito | +1.064 |
ba | +1.064 |
Neg logit contributions | |
oph | -0.879 |
cake | -0.845 |
cakes | -0.822 |
board | -0.762 |
amusement | -0.736 |
Token | grateful |
Token ID | 14066 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
oph | +0.021 |
cake | +0.021 |
cakes | +0.020 |
amusement | +0.019 |
uct | +0.019 |
Neg logit contributions | |
emo | -0.030 |
eer | -0.026 |
sailor | -0.025 |
fish | -0.025 |
ba | -0.025 |
Token | for |
Token ID | 329 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
emo | +0.210 |
eer | +0.173 |
sailor | +0.173 |
fish | +0.169 |
ba | +0.167 |
Neg logit contributions | |
oph | -0.174 |
cake | -0.167 |
cakes | -0.166 |
amusement | -0.149 |
board | -0.149 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
oph | +0.213 |
cake | +0.208 |
cakes | +0.203 |
amusement | +0.193 |
board | +0.187 |
Neg logit contributions | |
emo | -0.199 |
eer | -0.162 |
cker | -0.160 |
rito | -0.155 |
sailor | -0.154 |
Token | my |
Token ID | 1820 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
oph | +0.138 |
cake | +0.133 |
cakes | +0.131 |
amusement | +0.116 |
board | +0.116 |
Neg logit contributions | |
emo | -0.216 |
eer | -0.186 |
sailor | -0.181 |
ba | -0.179 |
cker | -0.178 |
Token | anxious |
Token ID | 18116 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
emo | +0.061 |
ba | +0.054 |
cker | +0.054 |
Albert | +0.053 |
eer | +0.052 |
Neg logit contributions | |
That | -0.028 |
aw | -0.027 |
awful | -0.026 |
amusement | -0.026 |
so | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
emo | +0.137 |
sailor | +0.113 |
eer | +0.113 |
cker | +0.113 |
ba | +0.112 |
Neg logit contributions | |
cake | -0.089 |
oph | -0.088 |
cakes | -0.086 |
board | -0.082 |
amusement | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
oph | +0.008 |
cake | +0.007 |
cakes | +0.007 |
board | +0.007 |
uct | +0.006 |
Neg logit contributions | |
emo | -0.012 |
eer | -0.012 |
cker | -0.012 |
rito | -0.011 |
sailor | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
emo | +0.185 |
cker | +0.176 |
eer | +0.176 |
rito | +0.170 |
sailor | +0.170 |
Neg logit contributions | |
oph | -0.103 |
cake | -0.092 |
cakes | -0.089 |
ue | -0.087 |
board | -0.084 |
Token | N |
Token ID | 45 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
emo | +0.161 |
eer | +0.136 |
sailor | +0.132 |
cker | +0.131 |
rito | +0.130 |
Neg logit contributions | |
oph | -0.142 |
cake | -0.137 |
cakes | -0.134 |
board | -0.126 |
amusement | -0.123 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
Albert | +0.042 |
Albert | +0.039 |
cker | +0.030 |
rito | +0.027 |
sailor | +0.022 |
Neg logit contributions | |
oph | -0.406 |
board | -0.391 |
aw | -0.376 |
cake | -0.369 |
ue | -0.351 |
Token | sw |
Token ID | 1509 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
emo | +1.305 |
eer | +1.125 |
rito | +1.120 |
sailor | +1.098 |
ba | +1.061 |
Neg logit contributions | |
oph | -0.837 |
cake | -0.771 |
cakes | -0.739 |
board | -0.722 |
ue | -0.684 |
Token | am |
Token ID | 321 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
emo | +0.051 |
sailor | +0.046 |
eer | +0.045 |
rito | +0.045 |
ba | +0.044 |
Neg logit contributions | |
oph | -0.040 |
aw | -0.036 |
board | -0.036 |
cakes | -0.036 |
cake | -0.035 |
Token | away |
Token ID | 1497 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
emo | +0.300 |
eer | +0.244 |
sailor | +0.241 |
ba | +0.240 |
cker | +0.235 |
Neg logit contributions | |
oph | -0.259 |
cake | -0.251 |
cakes | -0.245 |
board | -0.226 |
amusement | -0.223 |
Token | from |
Token ID | 422 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
cake | +0.066 |
oph | +0.065 |
cakes | +0.060 |
board | +0.057 |
amusement | +0.053 |
Neg logit contributions | |
emo | -0.118 |
eer | -0.105 |
rito | -0.100 |
sailor | -0.100 |
cker | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
amusement | +0.051 |
Tom | +0.046 |
course | +0.042 |
Meg | +0.040 |
Sophia | +0.038 |
Neg logit contributions | |
emo | -0.115 |
rito | -0.111 |
Albert | -0.109 |
ba | -0.109 |
cker | -0.107 |
Token | mouths |
Token ID | 28552 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
emo | +0.246 |
ba | +0.207 |
rito | +0.199 |
cker | +0.198 |
eer | +0.195 |
Neg logit contributions | |
oph | -0.210 |
cake | -0.202 |
cakes | -0.201 |
amusement | -0.201 |
board | -0.200 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
emo | +0.080 |
eer | +0.063 |
sailor | +0.062 |
ba | +0.061 |
cker | +0.060 |
Neg logit contributions | |
oph | -0.103 |
cake | -0.100 |
cakes | -0.098 |
board | -0.092 |
amusement | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
oph | +0.124 |
cake | +0.122 |
cakes | +0.120 |
board | +0.112 |
amusement | +0.105 |
Neg logit contributions | |
emo | -0.148 |
eer | -0.126 |
cker | -0.124 |
sailor | -0.122 |
ba | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
emo | +0.173 |
eer | +0.154 |
cker | +0.153 |
sailor | +0.149 |
rito | +0.149 |
Neg logit contributions | |
oph | -0.131 |
cake | -0.127 |
cakes | -0.125 |
board | -0.117 |
ue | -0.111 |
Token | N |
Token ID | 45 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
emo | +0.196 |
ba | +0.163 |
sailor | +0.161 |
fish | +0.158 |
eer | +0.157 |
Neg logit contributions | |
oph | -0.123 |
cake | -0.120 |
cakes | -0.117 |
board | -0.105 |
amusement | -0.103 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
emo | +0.047 |
cker | +0.046 |
sailor | +0.044 |
Albert | +0.040 |
Albert | +0.036 |
Neg logit contributions | |
oph | -0.404 |
board | -0.388 |
cake | -0.384 |
aw | -0.375 |
cakes | -0.366 |
Token | tried |
Token ID | 3088 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
emo | +1.221 |
eer | +1.008 |
sailor | +0.992 |
ba | +0.989 |
cker | +0.974 |
Neg logit contributions | |
oph | -0.965 |
cake | -0.939 |
cakes | -0.917 |
board | -0.837 |
amusement | -0.834 |
Token | his |
Token ID | 465 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
emo | +0.248 |
eer | +0.211 |
sailor | +0.205 |
cker | +0.204 |
ba | +0.202 |
Neg logit contributions | |
oph | -0.169 |
cake | -0.164 |
cakes | -0.159 |
amusement | -0.146 |
board | -0.145 |
Token | best |
Token ID | 1266 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
emo | +0.248 |
cker | +0.225 |
rito | +0.224 |
eer | +0.215 |
sailor | +0.204 |
Neg logit contributions | |
oph | -0.165 |
cakes | -0.155 |
cake | -0.155 |
board | -0.149 |
oga | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
emo | +0.207 |
cker | +0.184 |
rito | +0.182 |
eer | +0.181 |
Albert | +0.181 |
Neg logit contributions | |
oph | -0.104 |
cake | -0.095 |
board | -0.095 |
amusement | -0.090 |
ue | -0.087 |
Token | but |
Token ID | 475 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
emo | +0.048 |
eer | +0.041 |
ba | +0.040 |
sailor | +0.040 |
cker | +0.039 |
Neg logit contributions | |
oph | -0.033 |
cake | -0.032 |
cakes | -0.031 |
board | -0.029 |
amusement | -0.028 |
Token | o |
Token ID | 78 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
emo | +0.551 |
sailor | +0.464 |
eer | +0.445 |
rito | +0.428 |
fish | +0.425 |
Neg logit contributions | |
cake | -0.510 |
oph | -0.498 |
cakes | -0.478 |
board | -0.457 |
ue | -0.437 |
Token | . |
Token ID | 13 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
emo | +0.358 |
eer | +0.296 |
sailor | +0.294 |
cker | +0.282 |
rito | +0.281 |
Neg logit contributions | |
cake | -0.270 |
oph | -0.269 |
cakes | -0.258 |
board | -0.242 |
ue | -0.227 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
cake | +0.004 |
oph | +0.004 |
cakes | +0.004 |
board | +0.004 |
ue | +0.003 |
Neg logit contributions | |
emo | -0.008 |
eer | -0.007 |
ba | -0.007 |
cker | -0.007 |
sailor | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
emo | +0.177 |
eer | +0.165 |
cker | +0.161 |
sailor | +0.160 |
rito | +0.158 |
Neg logit contributions | |
oph | -0.116 |
cake | -0.111 |
cakes | -0.109 |
board | -0.101 |
ue | -0.101 |
Token | N |
Token ID | 45 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
emo | +0.188 |
sailor | +0.155 |
ba | +0.154 |
eer | +0.154 |
cker | +0.151 |
Neg logit contributions | |
oph | -0.122 |
cake | -0.119 |
cakes | -0.117 |
board | -0.105 |
amusement | -0.104 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
Albert | +0.029 |
Albert | +0.028 |
sailor | +0.025 |
crew | +0.018 |
rito | +0.015 |
Neg logit contributions | |
oph | -0.422 |
board | -0.411 |
cake | -0.406 |
aw | -0.393 |
cakes | -0.380 |
Token | sw |
Token ID | 1509 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
emo | +1.252 |
eer | +1.054 |
sailor | +1.035 |
rito | +1.021 |
ba | +1.008 |
Neg logit contributions | |
oph | -0.900 |
cake | -0.872 |
cakes | -0.840 |
board | -0.804 |
ue | -0.753 |
Token | am |
Token ID | 321 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
emo | +0.051 |
sailor | +0.044 |
eer | +0.043 |
ba | +0.042 |
rito | +0.042 |
Neg logit contributions | |
oph | -0.046 |
cake | -0.043 |
cakes | -0.043 |
board | -0.041 |
aw | -0.040 |
Token | under |
Token ID | 739 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
emo | +0.304 |
eer | +0.248 |
ba | +0.245 |
sailor | +0.245 |
cker | +0.238 |
Neg logit contributions | |
oph | -0.258 |
cake | -0.248 |
cakes | -0.242 |
board | -0.223 |
amusement | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
emo | +0.304 |
ba | +0.288 |
cker | +0.287 |
eer | +0.283 |
rito | +0.279 |
Neg logit contributions | |
amusement | -0.099 |
oph | -0.097 |
cake | -0.090 |
Tom | -0.084 |
board | -0.082 |
Token | blanket |
Token ID | 18447 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
oph | +0.023 |
cake | +0.022 |
cakes | +0.022 |
board | +0.021 |
amusement | +0.020 |
Neg logit contributions | |
emo | -0.015 |
eer | -0.011 |
sailor | -0.011 |
ba | -0.011 |
cker | -0.011 |
Token | ." |
Token ID | 526 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
emo | +0.165 |
eer | +0.135 |
sailor | +0.134 |
cker | +0.131 |
rito | +0.129 |
Neg logit contributions | |
cake | -0.137 |
cakes | -0.135 |
oph | -0.131 |
board | -0.125 |
ue | -0.114 |
Token | |
Token ID | 220 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
emo | +0.326 |
eer | +0.274 |
sailor | +0.269 |
ba | +0.267 |
cker | +0.265 |
Neg logit contributions | |
oph | -0.231 |
cake | -0.224 |
cakes | -0.218 |
board | -0.200 |
amusement | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
oph | +0.099 |
cake | +0.095 |
cakes | +0.093 |
ue | +0.087 |
uct | +0.083 |
Neg logit contributions | |
emo | -0.169 |
sailor | -0.161 |
eer | -0.159 |
cker | -0.158 |
rito | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
emo | +0.178 |
eer | +0.169 |
cker | +0.165 |
sailor | +0.162 |
rito | +0.161 |
Neg logit contributions | |
oph | -0.119 |
cake | -0.111 |
cakes | -0.109 |
ue | -0.098 |
board | -0.097 |
Token | N |
Token ID | 45 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
emo | +0.166 |
ba | +0.132 |
sailor | +0.132 |
eer | +0.131 |
fish | +0.128 |
Neg logit contributions | |
oph | -0.145 |
cake | -0.143 |
cakes | -0.140 |
board | -0.129 |
amusement | -0.127 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
Albert | +0.013 |
sailor | +0.013 |
rito | +0.012 |
Albert | +0.010 |
cker | +0.009 |
Neg logit contributions | |
oph | -0.445 |
cake | -0.415 |
board | -0.413 |
cakes | -0.396 |
aw | -0.396 |
Token | and |
Token ID | 290 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
emo | +1.275 |
eer | +1.065 |
sailor | +1.048 |
ba | +1.043 |
cker | +1.032 |
Neg logit contributions | |
oph | -0.906 |
cake | -0.882 |
cakes | -0.860 |
board | -0.782 |
amusement | -0.775 |
Token | D |
Token ID | 360 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
oph | +0.022 |
cake | +0.019 |
amusement | +0.019 |
Meg | +0.018 |
That | +0.018 |
Neg logit contributions | |
emo | -0.021 |
rito | -0.020 |
eer | -0.020 |
cker | -0.019 |
ery | -0.018 |
Token | ory |
Token ID | 652 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
emo | +0.163 |
eer | +0.145 |
cker | +0.143 |
rito | +0.143 |
sailor | +0.142 |
Neg logit contributions | |
oph | -0.204 |
cake | -0.189 |
cakes | -0.180 |
board | -0.179 |
ue | -0.166 |
Token | dove |
Token ID | 38862 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
emo | +0.429 |
eer | +0.356 |
ba | +0.351 |
sailor | +0.351 |
cker | +0.345 |
Neg logit contributions | |
oph | -0.359 |
cake | -0.351 |
cakes | -0.340 |
amusement | -0.311 |
board | -0.309 |
Token | deep |
Token ID | 2769 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
emo | +0.323 |
eer | +0.260 |
rito | +0.255 |
sailor | +0.253 |
cker | +0.246 |
Neg logit contributions | |
cakes | -0.272 |
oph | -0.269 |
cake | -0.266 |
board | -0.254 |
amusement | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
emo | +0.144 |
eer | +0.117 |
sailor | +0.115 |
ba | +0.114 |
fish | +0.112 |
Neg logit contributions | |
oph | -0.140 |
cake | -0.137 |
cakes | -0.134 |
board | -0.123 |
amusement | -0.120 |
Token | |
Token ID | 220 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
oph | +0.007 |
cakes | +0.006 |
cake | +0.006 |
board | +0.006 |
ue | +0.005 |
Neg logit contributions | |
emo | -0.010 |
eer | -0.009 |
rito | -0.009 |
cker | -0.009 |
ba | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
oph | +0.095 |
cake | +0.093 |
cakes | +0.091 |
ue | +0.084 |
That | +0.082 |
Neg logit contributions | |
emo | -0.171 |
sailor | -0.161 |
eer | -0.160 |
cker | -0.158 |
rito | -0.156 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
emo | +0.181 |
cker | +0.166 |
eer | +0.166 |
sailor | +0.161 |
rito | +0.161 |
Neg logit contributions | |
oph | -0.111 |
cake | -0.102 |
cakes | -0.100 |
ue | -0.094 |
board | -0.092 |
Token | N |
Token ID | 45 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
emo | +0.144 |
eer | +0.117 |
sailor | +0.114 |
cker | +0.112 |
ba | +0.112 |
Neg logit contributions | |
oph | -0.157 |
cake | -0.152 |
cakes | -0.149 |
board | -0.140 |
amusement | -0.138 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
Albert | +0.047 |
Albert | +0.043 |
rito | +0.032 |
crew | +0.030 |
cker | +0.028 |
Neg logit contributions | |
oph | -0.398 |
board | -0.384 |
aw | -0.376 |
cake | -0.362 |
ue | -0.349 |
Token | sw |
Token ID | 1509 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
emo | +1.306 |
eer | +1.122 |
rito | +1.113 |
sailor | +1.097 |
ba | +1.063 |
Neg logit contributions | |
oph | -0.850 |
cake | -0.790 |
cakes | -0.759 |
board | -0.731 |
ue | -0.692 |
Token | am |
Token ID | 321 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
emo | +0.053 |
sailor | +0.048 |
rito | +0.048 |
eer | +0.047 |
ba | +0.046 |
Neg logit contributions | |
oph | -0.042 |
cakes | -0.037 |
aw | -0.037 |
board | -0.037 |
cake | -0.037 |
Token | up |
Token ID | 510 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
emo | +0.305 |
eer | +0.249 |
sailor | +0.246 |
ba | +0.245 |
cker | +0.239 |
Neg logit contributions | |
oph | -0.257 |
cake | -0.249 |
cakes | -0.243 |
board | -0.224 |
amusement | -0.222 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
emo | +0.157 |
eer | +0.132 |
sailor | +0.129 |
ba | +0.127 |
rito | +0.127 |
Neg logit contributions | |
oph | -0.123 |
cake | -0.121 |
cakes | -0.118 |
board | -0.109 |
amusement | -0.107 |
Token | his |
Token ID | 465 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
oph | +0.009 |
Tom | +0.009 |
amusement | +0.009 |
Sophia | +0.008 |
Meg | +0.008 |
Neg logit contributions | |
rito | -0.024 |
cker | -0.024 |
emo | -0.023 |
eer | -0.023 |
ery | -0.022 |
Token | shark |
Token ID | 21027 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
oph | +0.028 |
cake | +0.028 |
cakes | +0.027 |
amusement | +0.027 |
board | +0.027 |
Neg logit contributions | |
emo | -0.013 |
ba | -0.009 |
eer | -0.009 |
rito | -0.009 |
cker | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
emo | +0.336 |
eer | +0.278 |
sailor | +0.272 |
ba | +0.270 |
cker | +0.268 |
Neg logit contributions | |
oph | -0.268 |
cake | -0.261 |
cakes | -0.254 |
board | -0.235 |
amusement | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
oph | +0.011 |
cake | +0.011 |
cakes | +0.010 |
board | +0.009 |
That | +0.009 |
Neg logit contributions | |
emo | -0.015 |
cker | -0.014 |
eer | -0.014 |
ba | -0.013 |
sailor | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
emo | +0.168 |
eer | +0.160 |
cker | +0.158 |
sailor | +0.156 |
rito | +0.151 |
Neg logit contributions | |
oph | -0.107 |
cake | -0.103 |
cakes | -0.101 |
That | -0.093 |
ue | -0.089 |
Token | N |
Token ID | 45 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
emo | +0.183 |
eer | +0.151 |
sailor | +0.151 |
ba | +0.151 |
cker | +0.147 |
Neg logit contributions | |
oph | -0.113 |
cake | -0.109 |
cakes | -0.106 |
board | -0.097 |
amusement | -0.095 |
Token | emo |
Token ID | 41903 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
emo | +0.014 |
cker | +0.010 |
sailor | +0.009 |
rito | +0.009 |
Albert | +0.007 |
Neg logit contributions | |
oph | -0.443 |
cake | -0.411 |
board | -0.408 |
aw | -0.399 |
cakes | -0.395 |
Token | said |
Token ID | 531 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
emo | +1.257 |
eer | +1.049 |
sailor | +1.035 |
ba | +1.031 |
cker | +1.012 |
Neg logit contributions | |
oph | -0.921 |
cake | -0.901 |
cakes | -0.883 |
board | -0.796 |
amusement | -0.793 |
Token | , |
Token ID | 11 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
cake | +0.144 |
oph | +0.144 |
cakes | +0.140 |
board | +0.125 |
amusement | +0.121 |
Neg logit contributions | |
emo | -0.232 |
eer | -0.198 |
cker | -0.194 |
rito | -0.193 |
ba | -0.192 |
Token | " |
Token ID | 366 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
emo | +0.044 |
eer | +0.038 |
cker | +0.036 |
rito | +0.036 |
ba | +0.036 |
Neg logit contributions | |
cake | -0.024 |
oph | -0.024 |
cakes | -0.023 |
board | -0.020 |
amusement | -0.020 |
Token | Thanks |
Token ID | 9690 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
oph | +0.109 |
cake | +0.105 |
cakes | +0.101 |
board | +0.089 |
amusement | +0.087 |
Neg logit contributions | |
emo | -0.239 |
eer | -0.206 |
sailor | -0.203 |
ba | -0.202 |
cker | -0.200 |
Token | for |
Token ID | 329 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
oph | +0.199 |
cake | +0.191 |
cakes | +0.185 |
board | +0.170 |
amusement | +0.166 |
Neg logit contributions | |
emo | -0.318 |
eer | -0.271 |
cker | -0.268 |
rito | -0.264 |
sailor | -0.262 |
Token | cl |
Token ID | 537 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
oph | +0.399 |
cake | +0.377 |
cakes | +0.370 |
amusement | +0.341 |
board | +0.337 |
Neg logit contributions | |
emo | -0.449 |
eer | -0.381 |
ba | -0.379 |
sailor | -0.378 |
fish | -0.368 |
Token | apped |
Token ID | 6320 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
oph | +0.139 |
cake | +0.136 |
cakes | +0.135 |
amusement | +0.122 |
board | +0.121 |
Neg logit contributions | |
emo | -0.183 |
eer | -0.149 |
ba | -0.148 |
sailor | -0.146 |
cker | -0.144 |
Token | her |
Token ID | 607 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
oph | +0.084 |
cake | +0.082 |
cakes | +0.081 |
board | +0.075 |
amusement | +0.072 |
Neg logit contributions | |
emo | -0.073 |
sailor | -0.059 |
eer | -0.058 |
ba | -0.057 |
fish | -0.056 |
Token | hands |
Token ID | 2832 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
oph | +0.044 |
cake | +0.043 |
cakes | +0.042 |
board | +0.038 |
amusement | +0.038 |
Neg logit contributions | |
emo | -0.052 |
eer | -0.043 |
sailor | -0.042 |
ba | -0.042 |
cker | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
oph | +0.011 |
cakes | +0.010 |
cake | +0.010 |
board | +0.010 |
ue | +0.010 |
Neg logit contributions | |
emo | -0.007 |
eer | -0.006 |
sailor | -0.006 |
ba | -0.006 |
fish | -0.006 |
Token | amusement |
Token ID | 30184 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
emo | +0.263 |
sailor | +0.229 |
sail | +0.224 |
eer | +0.213 |
crew | +0.210 |
Neg logit contributions | |
cakes | -0.294 |
cake | -0.284 |
oph | -0.282 |
board | -0.263 |
liv | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
cake | +1.179 |
cakes | +1.175 |
oph | +1.173 |
uct | +1.107 |
liv | +1.087 |
Neg logit contributions | |
emo | -0.637 |
sailor | -0.571 |
eer | -0.569 |
fish | -0.509 |
sword | -0.453 |
Token | The |
Token ID | 383 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
oph | +0.017 |
cake | +0.016 |
cakes | +0.015 |
amusement | +0.015 |
board | +0.014 |
Neg logit contributions | |
emo | -0.019 |
eer | -0.015 |
Albert | -0.014 |
cker | -0.014 |
sailor | -0.014 |
Token | other |
Token ID | 584 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
emo | +0.006 |
sailor | +0.005 |
crew | +0.005 |
eer | +0.005 |
sailors | +0.005 |
Neg logit contributions | |
oph | -0.007 |
cake | -0.006 |
uct | -0.006 |
liv | -0.006 |
ue | -0.006 |
Token | boys |
Token ID | 6510 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
oph | +0.070 |
cake | +0.065 |
uct | +0.063 |
liv | +0.060 |
cakes | +0.057 |
Neg logit contributions | |
emo | -0.057 |
eer | -0.050 |
crew | -0.049 |
sailor | -0.048 |
sailors | -0.047 |
Token | had |
Token ID | 550 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
oph | +0.328 |
cake | +0.312 |
cakes | +0.306 |
board | +0.274 |
amusement | +0.274 |
Neg logit contributions | |
emo | -0.405 |
sailor | -0.349 |
eer | -0.346 |
ba | -0.345 |
fish | -0.338 |
Token | they |
Token ID | 484 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
emo | +0.051 |
eer | +0.045 |
cker | +0.043 |
sailor | +0.043 |
rito | +0.043 |
Neg logit contributions | |
oph | -0.028 |
cake | -0.027 |
cakes | -0.026 |
board | -0.023 |
amusement | -0.023 |
Token | went |
Token ID | 1816 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
emo | +0.063 |
rito | +0.055 |
eer | +0.054 |
cker | +0.053 |
fish | +0.052 |
Neg logit contributions | |
oph | -0.039 |
cake | -0.035 |
cakes | -0.034 |
amusement | -0.033 |
board | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
cakes | +0.007 |
cake | +0.007 |
oph | +0.007 |
board | +0.007 |
amusement | +0.006 |
Neg logit contributions | |
emo | -0.012 |
rito | -0.010 |
eer | -0.010 |
cker | -0.010 |
sailor | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
oph | +0.019 |
amusement | +0.019 |
cake | +0.016 |
Rebecca | +0.016 |
cakes | +0.016 |
Neg logit contributions | |
emo | -0.039 |
rito | -0.034 |
fish | -0.034 |
eer | -0.034 |
cker | -0.033 |
Token | big |
Token ID | 1263 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
emo | +0.005 |
eer | +0.004 |
rito | +0.004 |
ba | +0.004 |
cker | +0.004 |
Neg logit contributions | |
oph | -0.005 |
cake | -0.005 |
cakes | -0.005 |
amusement | -0.004 |
board | -0.004 |
Token | amusement |
Token ID | 30184 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
oph | +0.082 |
cake | +0.081 |
cakes | +0.080 |
uct | +0.072 |
board | +0.071 |
Neg logit contributions | |
emo | -0.088 |
sailor | -0.075 |
eer | -0.073 |
cker | -0.070 |
ba | -0.070 |
Token | park |
Token ID | 3952 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
uct | +0.855 |
oph | +0.852 |
ishly | +0.831 |
cake | +0.800 |
cakes | +0.797 |
Neg logit contributions | |
emo | -1.018 |
sailor | -0.915 |
fish | -0.879 |
eer | -0.822 |
sail | -0.784 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
oph | +0.531 |
cake | +0.480 |
cakes | +0.466 |
icious | +0.462 |
uct | +0.461 |
Neg logit contributions | |
emo | -0.295 |
eer | -0.230 |
cker | -0.229 |
sail | -0.222 |
fish | -0.220 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
oph | +0.008 |
cake | +0.008 |
cakes | +0.008 |
amusement | +0.007 |
board | +0.007 |
Neg logit contributions | |
emo | -0.010 |
eer | -0.008 |
sailor | -0.008 |
ba | -0.008 |
rito | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
oph | +0.079 |
cake | +0.075 |
cakes | +0.073 |
board | +0.069 |
amusement | +0.067 |
Neg logit contributions | |
emo | -0.112 |
eer | -0.093 |
rito | -0.092 |
sailor | -0.091 |
cker | -0.090 |
Token | so |
Token ID | 523 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
oph | +0.052 |
cake | +0.050 |
cakes | +0.049 |
board | +0.045 |
amusement | +0.044 |
Neg logit contributions | |
emo | -0.070 |
eer | -0.058 |
sailor | -0.057 |
ba | -0.057 |
cker | -0.056 |
Token | took |
Token ID | 1718 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
emo | +0.140 |
eer | +0.117 |
sailor | +0.115 |
ba | +0.114 |
cker | +0.114 |
Neg logit contributions | |
oph | -0.104 |
cake | -0.100 |
cakes | -0.097 |
board | -0.090 |
amusement | -0.088 |
Token | her |
Token ID | 607 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
emo | +0.012 |
eer | +0.010 |
sailor | +0.010 |
ba | +0.010 |
cker | +0.010 |
Neg logit contributions | |
oph | -0.010 |
cake | -0.010 |
cakes | -0.010 |
board | -0.009 |
amusement | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
oph | +0.025 |
cake | +0.025 |
cakes | +0.025 |
board | +0.023 |
amusement | +0.023 |
Neg logit contributions | |
emo | -0.031 |
eer | -0.025 |
ba | -0.025 |
cker | -0.025 |
rito | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
oph | +0.022 |
cake | +0.021 |
cakes | +0.021 |
board | +0.019 |
amusement | +0.019 |
Neg logit contributions | |
emo | -0.030 |
eer | -0.025 |
sailor | -0.024 |
ba | -0.024 |
cker | -0.024 |
Token | famous |
Token ID | 5863 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
emo | +0.026 |
eer | +0.021 |
ba | +0.020 |
cker | +0.020 |
sailor | +0.020 |
Neg logit contributions | |
oph | -0.024 |
cake | -0.024 |
cakes | -0.023 |
board | -0.022 |
amusement | -0.021 |
Token | amusement |
Token ID | 30184 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
emo | +0.045 |
sailor | +0.038 |
eer | +0.037 |
ba | +0.036 |
cker | +0.036 |
Neg logit contributions | |
oph | -0.041 |
cake | -0.040 |
cakes | -0.039 |
board | -0.036 |
uct | -0.035 |
Token | park |
Token ID | 3952 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
oph | +0.803 |
cakes | +0.764 |
cake | +0.763 |
uct | +0.762 |
Those | +0.711 |
Neg logit contributions | |
emo | -0.961 |
sailor | -0.907 |
fish | -0.867 |
eer | -0.849 |
sword | -0.775 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
oph | +0.424 |
cake | +0.391 |
cakes | +0.380 |
uct | +0.367 |
ue | +0.358 |
Neg logit contributions | |
emo | -0.315 |
eer | -0.266 |
sailor | -0.261 |
fish | -0.259 |
cker | -0.253 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
cakes | +0.002 |
amusement | +0.002 |
board | +0.002 |
Neg logit contributions | |
emo | -0.004 |
eer | -0.003 |
sailor | -0.003 |
ba | -0.003 |
rito | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
oph | +0.071 |
cake | +0.069 |
cakes | +0.068 |
board | +0.062 |
amusement | +0.061 |
Neg logit contributions | |
emo | -0.084 |
eer | -0.070 |
sailor | -0.069 |
ba | -0.068 |
cker | -0.067 |
Token | so |
Token ID | 523 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
oph | +0.029 |
cake | +0.028 |
cakes | +0.027 |
board | +0.025 |
amusement | +0.024 |
Neg logit contributions | |
emo | -0.042 |
eer | -0.035 |
sailor | -0.035 |
ba | -0.035 |
cker | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
emo | +0.182 |
eer | +0.156 |
sailor | +0.154 |
ba | +0.152 |
cker | +0.151 |
Neg logit contributions | |
oph | -0.123 |
cake | -0.121 |
cakes | -0.117 |
amusement | -0.107 |
board | -0.107 |
Token | They |
Token ID | 2990 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
emo | +0.180 |
ba | +0.147 |
sailor | +0.141 |
cker | +0.140 |
fish | +0.140 |
Neg logit contributions | |
oph | -0.143 |
cake | -0.135 |
cakes | -0.134 |
board | -0.123 |
amusement | -0.115 |
Token | learn |
Token ID | 2193 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
oph | +0.196 |
cake | +0.192 |
cakes | +0.190 |
board | +0.171 |
amusement | +0.166 |
Neg logit contributions | |
emo | -0.218 |
sailor | -0.183 |
ba | -0.180 |
eer | -0.180 |
fish | -0.175 |
Token | that |
Token ID | 326 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
oph | +0.350 |
cake | +0.320 |
cakes | +0.305 |
board | +0.294 |
ue | +0.288 |
Neg logit contributions | |
emo | -0.416 |
sailor | -0.339 |
eer | -0.334 |
fish | -0.331 |
ba | -0.321 |
Token | qu |
Token ID | 627 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
oph | +0.249 |
cake | +0.248 |
cakes | +0.243 |
amusement | +0.236 |
board | +0.220 |
Neg logit contributions | |
emo | -0.379 |
rito | -0.328 |
eer | -0.321 |
ba | -0.320 |
cker | -0.310 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
oph | +0.021 |
cake | +0.020 |
cakes | +0.020 |
amusement | +0.017 |
board | +0.017 |
Neg logit contributions | |
emo | -0.045 |
eer | -0.038 |
ba | -0.037 |
sailor | -0.037 |
cker | -0.037 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
cakes | +0.869 |
cake | +0.851 |
oph | +0.847 |
board | +0.815 |
aw | +0.793 |
Neg logit contributions | |
emo | -0.841 |
sailor | -0.701 |
rito | -0.678 |
Albert | -0.671 |
eer | -0.657 |
Token | is |
Token ID | 318 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
emo | +0.321 |
eer | +0.267 |
sailor | +0.264 |
ba | +0.262 |
cker | +0.258 |
Neg logit contributions | |
oph | -0.238 |
cake | -0.234 |
cakes | -0.228 |
board | -0.211 |
amusement | -0.205 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
emo | +0.018 |
eer | +0.016 |
sailor | +0.015 |
ba | +0.015 |
rito | +0.015 |
Neg logit contributions | |
cake | -0.015 |
oph | -0.015 |
cakes | -0.015 |
amusement | -0.014 |
uct | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
oph | +0.151 |
cake | +0.149 |
cakes | +0.146 |
board | +0.137 |
amusement | +0.131 |
Neg logit contributions | |
emo | -0.214 |
eer | -0.177 |
sailor | -0.176 |
ba | -0.176 |
cker | -0.175 |
Token | sharing |
Token ID | 7373 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
cake | +0.016 |
cakes | +0.016 |
oph | +0.015 |
amusement | +0.015 |
That | +0.015 |
Neg logit contributions | |
emo | -0.025 |
ba | -0.021 |
eer | -0.021 |
rito | -0.021 |
sailor | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
cake | +0.108 |
cakes | +0.106 |
oph | +0.105 |
board | +0.095 |
amusement | +0.091 |
Neg logit contributions | |
emo | -0.169 |
eer | -0.143 |
rito | -0.142 |
cker | -0.142 |
ba | -0.139 |
Token | Why |
Token ID | 5195 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
oph | +0.145 |
cakes | +0.131 |
cake | +0.131 |
amusement | +0.121 |
board | +0.117 |
Neg logit contributions | |
emo | -0.231 |
ba | -0.202 |
eer | -0.194 |
cker | -0.191 |
sailor | -0.191 |
Token | are |
Token ID | 389 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
oph | +0.328 |
cake | +0.319 |
cakes | +0.311 |
board | +0.284 |
amusement | +0.278 |
Neg logit contributions | |
emo | -0.507 |
eer | -0.428 |
sailor | -0.421 |
ba | -0.417 |
cker | -0.415 |
Token | you |
Token ID | 345 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
oph | +0.189 |
cake | +0.187 |
cakes | +0.177 |
board | +0.170 |
amusement | +0.165 |
Neg logit contributions | |
emo | -0.179 |
sailor | -0.144 |
eer | -0.142 |
ba | -0.141 |
fish | -0.138 |
Token | qu |
Token ID | 627 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
emo | +0.086 |
ba | +0.071 |
sailor | +0.071 |
eer | +0.070 |
cker | +0.069 |
Neg logit contributions | |
oph | -0.074 |
cake | -0.071 |
cakes | -0.070 |
board | -0.065 |
amusement | -0.063 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.018 |
cakes | +0.017 |
amusement | +0.017 |
Rebecca | +0.016 |
Neg logit contributions | |
emo | -0.038 |
ba | -0.032 |
ery | -0.030 |
eer | -0.030 |
cker | -0.030 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
oph | +0.984 |
cakes | +0.977 |
cake | +0.976 |
board | +0.922 |
uct | +0.875 |
Neg logit contributions | |
emo | -0.763 |
sailor | -0.590 |
eer | -0.582 |
rito | -0.581 |
cker | -0.566 |
Token | ? |
Token ID | 30 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
emo | +0.229 |
eer | +0.180 |
sailor | +0.179 |
ba | +0.171 |
fish | +0.168 |
Neg logit contributions | |
oph | -0.360 |
cake | -0.344 |
cakes | -0.344 |
uct | -0.321 |
amusement | -0.312 |
Token | You |
Token ID | 921 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
emo | +0.059 |
eer | +0.050 |
sailor | +0.050 |
ba | +0.049 |
cker | +0.049 |
Neg logit contributions | |
oph | -0.035 |
cake | -0.034 |
cakes | -0.033 |
board | -0.030 |
amusement | -0.029 |
Token | can |
Token ID | 460 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
cake | +0.110 |
oph | +0.109 |
cakes | +0.106 |
board | +0.099 |
amusement | +0.097 |
Neg logit contributions | |
emo | -0.159 |
eer | -0.128 |
sailor | -0.128 |
rito | -0.127 |
ba | -0.125 |
Token | share |
Token ID | 2648 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
emo | +0.234 |
eer | +0.190 |
sailor | +0.187 |
ba | +0.187 |
cker | +0.183 |
Neg logit contributions | |
oph | -0.220 |
cake | -0.212 |
cakes | -0.208 |
board | -0.194 |
amusement | -0.190 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
emo | +0.029 |
eer | +0.023 |
sailor | +0.022 |
exc | +0.022 |
cker | +0.022 |
Neg logit contributions | |
oph | -0.021 |
cake | -0.020 |
cakes | -0.020 |
board | -0.018 |
amusement | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
oph | +0.285 |
cake | +0.274 |
cakes | +0.268 |
amusement | +0.239 |
board | +0.239 |
Neg logit contributions | |
emo | -0.408 |
eer | -0.346 |
sailor | -0.339 |
ba | -0.336 |
cker | -0.331 |
Token | Mia |
Token ID | 32189 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
oph | +0.006 |
cake | +0.006 |
cakes | +0.005 |
amusement | +0.005 |
board | +0.005 |
Neg logit contributions | |
emo | -0.011 |
eer | -0.009 |
sailor | -0.009 |
ba | -0.009 |
cker | -0.009 |
Token | stop |
Token ID | 2245 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
oph | +0.206 |
cake | +0.203 |
cakes | +0.197 |
board | +0.183 |
amusement | +0.180 |
Neg logit contributions | |
emo | -0.282 |
eer | -0.232 |
sailor | -0.227 |
ba | -0.225 |
cker | -0.224 |
Token | qu |
Token ID | 627 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
oph | +0.240 |
cake | +0.235 |
cakes | +0.227 |
amusement | +0.212 |
board | +0.209 |
Neg logit contributions | |
emo | -0.367 |
eer | -0.308 |
sailor | -0.301 |
ba | -0.300 |
rito | -0.300 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
oph | +0.033 |
cake | +0.032 |
cakes | +0.031 |
amusement | +0.029 |
Rebecca | +0.028 |
Neg logit contributions | |
emo | -0.038 |
eer | -0.030 |
ba | -0.029 |
cker | -0.028 |
ery | -0.028 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
oph | +1.086 |
cake | +1.071 |
cakes | +1.056 |
board | +1.001 |
amusement | +0.975 |
Neg logit contributions | |
emo | -0.696 |
eer | -0.515 |
sailor | -0.512 |
rito | -0.494 |
cker | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
emo | +0.230 |
eer | +0.190 |
sailor | +0.183 |
fish | +0.178 |
ba | +0.177 |
Neg logit contributions | |
oph | -0.382 |
cake | -0.346 |
cakes | -0.346 |
liv | -0.330 |
uct | -0.320 |
Token | They |
Token ID | 1119 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
emo | +0.015 |
eer | +0.011 |
sailor | +0.011 |
cker | +0.011 |
Albert | +0.011 |
Neg logit contributions | |
oph | -0.017 |
cake | -0.016 |
cakes | -0.016 |
amusement | -0.015 |
uct | -0.015 |
Token | see |
Token ID | 766 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
oph | +0.035 |
cake | +0.034 |
cakes | +0.033 |
board | +0.030 |
amusement | +0.030 |
Neg logit contributions | |
emo | -0.036 |
eer | -0.029 |
sailor | -0.029 |
ba | -0.029 |
cker | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
emo | +0.113 |
eer | +0.093 |
sailor | +0.092 |
ba | +0.088 |
cker | +0.088 |
Neg logit contributions | |
oph | -0.113 |
cake | -0.108 |
cakes | -0.104 |
board | -0.098 |
uct | -0.095 |
Token | They |
Token ID | 2990 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
emo | +0.172 |
ba | +0.140 |
cker | +0.139 |
sailor | +0.137 |
fish | +0.135 |
Neg logit contributions | |
oph | -0.133 |
cake | -0.124 |
cakes | -0.122 |
board | -0.114 |
amusement | -0.104 |
Token | are |
Token ID | 389 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
oph | +0.223 |
cake | +0.223 |
cakes | +0.220 |
board | +0.195 |
liv | +0.189 |
Neg logit contributions | |
emo | -0.213 |
sailor | -0.184 |
eer | -0.173 |
ba | -0.171 |
sail | -0.171 |
Token | tired |
Token ID | 10032 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
oph | +0.169 |
cake | +0.168 |
cakes | +0.164 |
amusement | +0.154 |
uct | +0.151 |
Neg logit contributions | |
emo | -0.185 |
eer | -0.156 |
rito | -0.151 |
cker | -0.151 |
ba | -0.151 |
Token | from |
Token ID | 422 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
emo | +0.045 |
sailor | +0.038 |
eer | +0.038 |
ba | +0.037 |
fish | +0.036 |
Neg logit contributions | |
oph | -0.046 |
cakes | -0.042 |
cake | -0.042 |
liv | -0.041 |
uct | -0.040 |
Token | qu |
Token ID | 627 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
oph | +0.094 |
cake | +0.091 |
cakes | +0.089 |
amusement | +0.083 |
board | +0.081 |
Neg logit contributions | |
emo | -0.130 |
eer | -0.109 |
ba | -0.107 |
sailor | -0.107 |
rito | -0.107 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
oph | +0.026 |
cake | +0.025 |
cakes | +0.024 |
amusement | +0.022 |
Rebecca | +0.021 |
Neg logit contributions | |
emo | -0.042 |
eer | -0.034 |
ba | -0.034 |
cker | -0.033 |
fish | -0.033 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
cake | +0.982 |
cakes | +0.981 |
oph | +0.979 |
board | +0.927 |
aw | +0.889 |
Neg logit contributions | |
emo | -0.747 |
rito | -0.568 |
sailor | -0.563 |
eer | -0.557 |
cker | -0.541 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
emo | +0.231 |
eer | +0.190 |
sailor | +0.178 |
fish | +0.171 |
ba | +0.166 |
Neg logit contributions | |
oph | -0.372 |
cake | -0.341 |
cakes | -0.336 |
liv | -0.320 |
uct | -0.314 |
Token | They |
Token ID | 1119 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
emo | +0.010 |
eer | +0.007 |
sailor | +0.007 |
cker | +0.007 |
sail | +0.007 |
Neg logit contributions | |
cake | -0.013 |
oph | -0.013 |
cakes | -0.012 |
board | -0.012 |
uct | -0.011 |
Token | sit |
Token ID | 1650 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
oph | +0.035 |
cake | +0.034 |
cakes | +0.033 |
board | +0.030 |
amusement | +0.030 |
Neg logit contributions | |
emo | -0.038 |
eer | -0.032 |
sailor | -0.031 |
ba | -0.031 |
cker | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
emo | +0.133 |
eer | +0.110 |
sailor | +0.107 |
rito | +0.106 |
ba | +0.106 |
Neg logit contributions | |
oph | -0.112 |
cake | -0.110 |
cakes | -0.108 |
board | -0.100 |
amusement | -0.099 |
Token | says |
Token ID | 1139 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
oph | +0.223 |
cake | +0.214 |
cakes | +0.204 |
board | +0.188 |
amusement | +0.184 |
Neg logit contributions | |
emo | -0.244 |
eer | -0.207 |
ba | -0.201 |
sailor | -0.200 |
cker | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
oph | +0.116 |
cake | +0.113 |
cakes | +0.110 |
board | +0.101 |
amusement | +0.099 |
Neg logit contributions | |
emo | -0.152 |
eer | -0.126 |
sailor | -0.124 |
ba | -0.123 |
cker | -0.122 |
Token | " |
Token ID | 366 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
emo | +0.043 |
eer | +0.036 |
sailor | +0.035 |
ba | +0.035 |
cker | +0.034 |
Neg logit contributions | |
oph | -0.029 |
cake | -0.028 |
cakes | -0.027 |
board | -0.025 |
amusement | -0.025 |
Token | Stop |
Token ID | 19485 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
cake | +0.162 |
cakes | +0.162 |
oph | +0.156 |
board | +0.153 |
oga | +0.136 |
Neg logit contributions | |
emo | -0.187 |
ba | -0.166 |
sailor | -0.147 |
Ar | -0.147 |
Albert | -0.144 |
Token | qu |
Token ID | 627 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
oph | +0.306 |
cake | +0.297 |
cakes | +0.290 |
board | +0.266 |
amusement | +0.261 |
Neg logit contributions | |
emo | -0.399 |
eer | -0.332 |
sailor | -0.327 |
ba | -0.324 |
cker | -0.320 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
cake | +0.028 |
oph | +0.027 |
cakes | +0.027 |
amusement | +0.025 |
Rebecca | +0.023 |
Neg logit contributions | |
emo | -0.046 |
ba | -0.038 |
eer | -0.036 |
cker | -0.036 |
ery | -0.035 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
oph | +1.047 |
cake | +1.033 |
cakes | +1.022 |
board | +0.973 |
amusement | +0.937 |
Neg logit contributions | |
emo | -0.720 |
sailor | -0.539 |
eer | -0.537 |
rito | -0.528 |
cker | -0.519 |
Token | , |
Token ID | 11 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
emo | +0.242 |
eer | +0.206 |
ba | +0.201 |
sailor | +0.194 |
fish | +0.184 |
Neg logit contributions | |
oph | -0.348 |
cake | -0.325 |
cakes | -0.324 |
uct | -0.305 |
amusement | -0.296 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
emo | +0.029 |
sailor | +0.027 |
eer | +0.024 |
ba | +0.024 |
exc | +0.024 |
Neg logit contributions | |
oph | -0.035 |
cake | -0.034 |
cakes | -0.033 |
oga | -0.031 |
board | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
oph | +0.318 |
cakes | +0.309 |
cake | +0.308 |
amusement | +0.282 |
board | +0.272 |
Neg logit contributions | |
emo | -0.363 |
eer | -0.307 |
ba | -0.297 |
sailor | -0.293 |
cker | -0.293 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
oph | +0.016 |
cake | +0.015 |
cakes | +0.014 |
board | +0.013 |
amusement | +0.013 |
Neg logit contributions | |
emo | -0.018 |
eer | -0.015 |
sailor | -0.015 |
ba | -0.014 |
cker | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.018 |
cakes | +0.017 |
board | +0.016 |
amusement | +0.016 |
Neg logit contributions | |
emo | -0.020 |
eer | -0.016 |
sailor | -0.016 |
ba | -0.016 |
cker | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
oph | +0.076 |
cake | +0.073 |
cakes | +0.072 |
board | +0.066 |
amusement | +0.064 |
Neg logit contributions | |
emo | -0.115 |
eer | -0.098 |
ba | -0.096 |
rito | -0.095 |
sailor | -0.095 |
Token | they |
Token ID | 484 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
emo | +0.019 |
eer | +0.016 |
rito | +0.016 |
cker | +0.016 |
ba | +0.016 |
Neg logit contributions | |
oph | -0.012 |
cake | -0.011 |
cakes | -0.011 |
amusement | -0.010 |
board | -0.010 |
Token | never |
Token ID | 1239 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
emo | +0.029 |
eer | +0.024 |
sailor | +0.023 |
ba | +0.023 |
cker | +0.023 |
Neg logit contributions | |
oph | -0.024 |
cake | -0.024 |
cakes | -0.023 |
board | -0.021 |
amusement | -0.021 |
Token | qu |
Token ID | 627 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
oph | +0.033 |
cake | +0.033 |
cakes | +0.032 |
board | +0.029 |
amusement | +0.029 |
Neg logit contributions | |
emo | -0.038 |
eer | -0.031 |
sailor | -0.030 |
ba | -0.030 |
cker | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.018 |
cakes | +0.016 |
amusement | +0.016 |
Rebecca | +0.015 |
Neg logit contributions | |
emo | -0.050 |
ba | -0.042 |
eer | -0.041 |
rito | -0.041 |
cker | -0.041 |
Token | led |
Token ID | 992 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
oph | +0.891 |
cake | +0.873 |
cakes | +0.873 |
board | +0.805 |
uct | +0.784 |
Neg logit contributions | |
emo | -0.865 |
sailor | -0.701 |
eer | -0.692 |
rito | -0.688 |
cker | -0.675 |
Token | again |
Token ID | 757 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
emo | +0.462 |
eer | +0.395 |
sailor | +0.385 |
ba | +0.384 |
cker | +0.383 |
Neg logit contributions | |
oph | -0.265 |
cake | -0.256 |
cakes | -0.247 |
board | -0.222 |
amusement | -0.221 |
Token | over |
Token ID | 625 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
oph | +0.289 |
cake | +0.279 |
cakes | +0.268 |
amusement | +0.248 |
board | +0.248 |
Neg logit contributions | |
emo | -0.424 |
eer | -0.357 |
sailor | -0.347 |
rito | -0.346 |
ba | -0.345 |
Token | clothes |
Token ID | 8242 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
oph | +0.242 |
cake | +0.233 |
cakes | +0.227 |
amusement | +0.213 |
board | +0.209 |
Neg logit contributions | |
emo | -0.358 |
eer | -0.308 |
rito | -0.304 |
cker | -0.299 |
ba | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
oph | +0.055 |
cakes | +0.052 |
cake | +0.052 |
ue | +0.048 |
amusement | +0.048 |
Neg logit contributions | |
emo | -0.066 |
sailor | -0.058 |
fish | -0.056 |
ba | -0.056 |
eer | -0.055 |
Token | sharing |
Token ID | 7373 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
oph | +0.313 |
cake | +0.302 |
cakes | +0.294 |
board | +0.279 |
amusement | +0.258 |
Neg logit contributions | |
emo | -0.350 |
sailor | -0.281 |
eer | -0.280 |
cker | -0.272 |
ba | -0.269 |
Token | is |
Token ID | 318 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
oph | +0.260 |
cake | +0.252 |
cakes | +0.246 |
board | +0.227 |
amusement | +0.224 |
Neg logit contributions | |
emo | -0.319 |
eer | -0.264 |
sailor | -0.259 |
ba | -0.257 |
cker | -0.254 |
Token | important |
Token ID | 1593 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
emo | +0.004 |
eer | +0.003 |
sailor | +0.003 |
ba | +0.003 |
rito | +0.003 |
Neg logit contributions | |
oph | -0.004 |
cake | -0.004 |
cakes | -0.004 |
amusement | -0.004 |
board | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
emo | +0.131 |
eer | +0.108 |
sailor | +0.105 |
fish | +0.102 |
ba | +0.102 |
Neg logit contributions | |
oph | -0.119 |
cake | -0.113 |
cakes | -0.110 |
amusement | -0.101 |
board | -0.100 |
Token | qu |
Token ID | 627 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
oph | +0.033 |
cake | +0.033 |
cakes | +0.032 |
amusement | +0.029 |
board | +0.029 |
Neg logit contributions | |
emo | -0.043 |
eer | -0.036 |
ba | -0.035 |
rito | -0.035 |
sailor | -0.035 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
oph | +0.013 |
cake | +0.012 |
cakes | +0.011 |
amusement | +0.010 |
board | +0.010 |
Neg logit contributions | |
emo | -0.037 |
eer | -0.031 |
ba | -0.031 |
cker | -0.031 |
rito | -0.030 |
Token | lling |
Token ID | 2680 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
cakes | +0.889 |
cake | +0.873 |
oph | +0.866 |
board | +0.818 |
uct | +0.782 |
Neg logit contributions | |
emo | -0.829 |
sailor | -0.685 |
rito | -0.661 |
eer | -0.650 |
Albert | -0.643 |
Token | is |
Token ID | 318 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
oph | +0.149 |
cake | +0.145 |
cakes | +0.142 |
board | +0.131 |
amusement | +0.129 |
Neg logit contributions | |
emo | -0.176 |
eer | -0.145 |
sailor | -0.143 |
ba | -0.141 |
cker | -0.140 |
Token | not |
Token ID | 407 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
emo | +0.007 |
eer | +0.006 |
sailor | +0.006 |
ba | +0.006 |
rito | +0.006 |
Neg logit contributions | |
cake | -0.006 |
oph | -0.006 |
cakes | -0.006 |
amusement | -0.005 |
uct | -0.005 |
Token | good |
Token ID | 922 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
emo | +0.062 |
eer | +0.052 |
ba | +0.052 |
sailor | +0.052 |
fish | +0.052 |
Neg logit contributions | |
oph | -0.043 |
cake | -0.042 |
cakes | -0.040 |
amusement | -0.038 |
uct | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
emo | +0.179 |
eer | +0.147 |
sailor | +0.144 |
ba | +0.142 |
cker | +0.141 |
Neg logit contributions | |
oph | -0.155 |
cake | -0.150 |
cakes | -0.147 |
board | -0.135 |
amusement | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
oph | +0.064 |
cake | +0.062 |
cakes | +0.060 |
board | +0.055 |
amusement | +0.054 |
Neg logit contributions | |
emo | -0.077 |
eer | -0.064 |
sailor | -0.063 |
ba | -0.062 |
fish | -0.061 |
Token | mess |
Token ID | 2085 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
oph | +0.016 |
cake | +0.015 |
cakes | +0.015 |
board | +0.014 |
amusement | +0.013 |
Neg logit contributions | |
emo | -0.022 |
eer | -0.019 |
sailor | -0.019 |
ba | -0.018 |
cker | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
oph | +0.551 |
amusement | +0.468 |
cake | +0.450 |
uct | +0.442 |
liv | +0.440 |
Neg logit contributions | |
emo | -0.346 |
fish | -0.301 |
ba | -0.301 |
eer | -0.281 |
sailor | -0.274 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
oph | +0.001 |
cake | +0.001 |
cakes | +0.001 |
board | +0.001 |
liv | +0.001 |
Neg logit contributions | |
emo | -0.001 |
eer | -0.001 |
sailor | -0.001 |
ba | -0.001 |
exc | -0.001 |
Token | qu |
Token ID | 627 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
oph | +0.014 |
cake | +0.014 |
cakes | +0.013 |
board | +0.012 |
amusement | +0.012 |
Neg logit contributions | |
emo | -0.018 |
eer | -0.015 |
sailor | -0.015 |
ba | -0.014 |
cker | -0.014 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.022 |
amusement | +0.020 |
cake | +0.020 |
cakes | +0.018 |
uct | +0.018 |
Neg logit contributions | |
emo | -0.027 |
eer | -0.022 |
ba | -0.022 |
rito | -0.021 |
ery | -0.021 |
Token | ling |
Token ID | 1359 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
oph | +1.117 |
cake | +1.092 |
cakes | +1.073 |
board | +1.013 |
amusement | +1.006 |
Neg logit contributions | |
emo | -0.675 |
eer | -0.505 |
sailor | -0.490 |
ba | -0.484 |
cker | -0.474 |
Token | twins |
Token ID | 20345 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
emo | +0.286 |
eer | +0.231 |
sailor | +0.228 |
fish | +0.225 |
ba | +0.215 |
Neg logit contributions | |
oph | -0.334 |
cake | -0.301 |
uct | -0.296 |
cakes | -0.293 |
amusement | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
emo | +0.050 |
eer | +0.042 |
sailor | +0.041 |
ba | +0.040 |
fish | +0.040 |
Neg logit contributions | |
oph | -0.078 |
cake | -0.070 |
cakes | -0.070 |
liv | -0.064 |
amusement | -0.064 |
Token | She |
Token ID | 1375 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
emo | +0.028 |
eer | +0.024 |
sailor | +0.023 |
ba | +0.023 |
Albert | +0.023 |
Neg logit contributions | |
oph | -0.016 |
cake | -0.015 |
cakes | -0.015 |
amusement | -0.014 |
uct | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
oph | +0.263 |
cake | +0.248 |
cakes | +0.237 |
board | +0.220 |
amusement | +0.219 |
Neg logit contributions | |
emo | -0.208 |
ba | -0.170 |
sailor | -0.168 |
eer | -0.166 |
exc | -0.162 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
emo | +0.019 |
sailor | +0.015 |
eer | +0.015 |
ba | +0.014 |
fish | +0.014 |
Neg logit contributions | |
oph | -0.013 |
cake | -0.013 |
cakes | -0.013 |
board | -0.012 |
amusement | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
oph | +0.080 |
cake | +0.079 |
cakes | +0.078 |
amusement | +0.070 |
board | +0.069 |
Neg logit contributions | |
emo | -0.108 |
eer | -0.090 |
sailor | -0.089 |
ba | -0.088 |
cker | -0.086 |
Token | Jack |
Token ID | 3619 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
cake | +0.041 |
cakes | +0.040 |
oph | +0.037 |
board | +0.036 |
aw | +0.035 |
Neg logit contributions | |
emo | -0.059 |
sailor | -0.049 |
eer | -0.048 |
Albert | -0.046 |
cker | -0.045 |
Token | never |
Token ID | 1239 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
oph | +0.355 |
cake | +0.349 |
cakes | +0.343 |
board | +0.314 |
amusement | +0.311 |
Neg logit contributions | |
emo | -0.373 |
eer | -0.311 |
ba | -0.304 |
sailor | -0.303 |
cker | -0.298 |
Token | qu |
Token ID | 627 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
oph | +0.030 |
cakes | +0.029 |
cake | +0.029 |
board | +0.027 |
liv | +0.026 |
Neg logit contributions | |
emo | -0.030 |
eer | -0.024 |
ba | -0.024 |
sailor | -0.024 |
cker | -0.023 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.015 |
cake | +0.015 |
amusement | +0.014 |
cakes | +0.014 |
Rebecca | +0.012 |
Neg logit contributions | |
emo | -0.038 |
ba | -0.031 |
eer | -0.031 |
cker | -0.030 |
ery | -0.030 |
Token | led |
Token ID | 992 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
oph | +0.969 |
cake | +0.951 |
cakes | +0.939 |
board | +0.877 |
amusement | +0.853 |
Neg logit contributions | |
emo | -0.804 |
eer | -0.631 |
sailor | -0.629 |
rito | -0.611 |
cker | -0.609 |
Token | again |
Token ID | 757 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
emo | +0.452 |
eer | +0.381 |
sailor | +0.378 |
ba | +0.374 |
cker | +0.367 |
Neg logit contributions | |
oph | -0.286 |
cake | -0.278 |
cakes | -0.271 |
board | -0.247 |
amusement | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
oph | +0.315 |
cake | +0.306 |
cakes | +0.299 |
board | +0.274 |
amusement | +0.269 |
Neg logit contributions | |
emo | -0.400 |
eer | -0.331 |
sailor | -0.326 |
ba | -0.323 |
cker | -0.320 |
Token | They |
Token ID | 1119 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
oph | +0.021 |
cake | +0.020 |
cakes | +0.020 |
board | +0.019 |
amusement | +0.019 |
Neg logit contributions | |
emo | -0.027 |
eer | -0.021 |
sailor | -0.020 |
ba | -0.020 |
rito | -0.020 |
Token | learned |
Token ID | 4499 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
oph | +0.047 |
cake | +0.046 |
cakes | +0.045 |
board | +0.041 |
amusement | +0.040 |
Neg logit contributions | |
emo | -0.057 |
eer | -0.048 |
ba | -0.047 |
sailor | -0.047 |
cker | -0.046 |
Token | walking |
Token ID | 6155 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
oph | +0.050 |
cake | +0.048 |
cakes | +0.047 |
board | +0.044 |
amusement | +0.042 |
Neg logit contributions | |
emo | -0.048 |
eer | -0.039 |
ba | -0.039 |
sailor | -0.039 |
cker | -0.038 |
Token | by |
Token ID | 416 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
emo | +0.151 |
eer | +0.133 |
ba | +0.129 |
sailor | +0.124 |
cker | +0.121 |
Neg logit contributions | |
oph | -0.208 |
cake | -0.192 |
cakes | -0.186 |
uct | -0.174 |
amusement | -0.174 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
oph | +0.010 |
cake | +0.010 |
cakes | +0.009 |
board | +0.008 |
uct | +0.008 |
Neg logit contributions | |
emo | -0.009 |
ba | -0.007 |
eer | -0.007 |
cker | -0.007 |
fish | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
oph | +0.074 |
cake | +0.073 |
cakes | +0.068 |
uct | +0.066 |
board | +0.066 |
Neg logit contributions | |
emo | -0.039 |
eer | -0.029 |
ba | -0.027 |
fish | -0.027 |
sailor | -0.027 |
Token | qu |
Token ID | 627 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
emo | +0.185 |
ba | +0.159 |
eer | +0.158 |
sailor | +0.154 |
cker | +0.153 |
Neg logit contributions | |
oph | -0.237 |
cake | -0.214 |
cakes | -0.212 |
board | -0.191 |
liv | -0.190 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.021 |
cake | +0.021 |
cakes | +0.019 |
amusement | +0.019 |
Rebecca | +0.017 |
Neg logit contributions | |
emo | -0.047 |
eer | -0.039 |
ba | -0.039 |
cker | -0.038 |
ery | -0.037 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
oph | +1.064 |
cake | +1.051 |
cakes | +1.038 |
board | +0.983 |
amusement | +0.957 |
Neg logit contributions | |
emo | -0.706 |
eer | -0.522 |
sailor | -0.520 |
rito | -0.503 |
cker | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
emo | +0.213 |
eer | +0.189 |
ba | +0.176 |
sailor | +0.173 |
fish | +0.168 |
Neg logit contributions | |
oph | -0.350 |
cake | -0.316 |
cakes | -0.314 |
liv | -0.302 |
uct | -0.298 |
Token | She |
Token ID | 1375 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
emo | +0.006 |
Albert | +0.005 |
eer | +0.005 |
exc | +0.005 |
cker | +0.005 |
Neg logit contributions | |
oph | -0.004 |
cakes | -0.004 |
cake | -0.004 |
amusement | -0.004 |
icious | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
oph | +0.231 |
cake | +0.224 |
cakes | +0.221 |
board | +0.202 |
amusement | +0.201 |
Neg logit contributions | |
emo | -0.242 |
ba | -0.203 |
eer | -0.200 |
sailor | -0.199 |
cker | -0.195 |
Token | very |
Token ID | 845 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
oph | +0.049 |
cake | +0.047 |
cakes | +0.046 |
board | +0.044 |
ue | +0.042 |
Neg logit contributions | |
emo | -0.044 |
ba | -0.035 |
eer | -0.035 |
sailor | -0.035 |
rito | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
oph | +0.258 |
cake | +0.250 |
cakes | +0.244 |
board | +0.224 |
amusement | +0.220 |
Neg logit contributions | |
emo | -0.348 |
eer | -0.290 |
sailor | -0.285 |
ba | -0.283 |
cker | -0.280 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
oph | +0.010 |
uct | +0.009 |
cake | +0.009 |
cakes | +0.009 |
ue | +0.008 |
Neg logit contributions | |
emo | -0.008 |
eer | -0.007 |
sailor | -0.007 |
fish | -0.006 |
cker | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
oph | +0.201 |
cake | +0.187 |
cakes | +0.185 |
board | +0.167 |
amusement | +0.166 |
Neg logit contributions | |
emo | -0.210 |
eer | -0.181 |
ba | -0.176 |
sailor | -0.174 |
fish | -0.173 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
oph | +0.017 |
cake | +0.017 |
cakes | +0.016 |
board | +0.015 |
amusement | +0.015 |
Neg logit contributions | |
emo | -0.022 |
eer | -0.018 |
sailor | -0.018 |
ba | -0.018 |
cker | -0.018 |
Token | black |
Token ID | 2042 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
oph | +0.012 |
cake | +0.011 |
cakes | +0.011 |
uct | +0.010 |
ue | +0.010 |
Neg logit contributions | |
emo | -0.012 |
eer | -0.010 |
sailor | -0.010 |
cker | -0.010 |
ba | -0.009 |
Token | board |
Token ID | 3526 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.147 |
uct | +0.144 |
cakes | +0.137 |
cake | +0.135 |
liv | +0.124 |
Neg logit contributions | |
emo | -0.129 |
eer | -0.116 |
sailor | -0.107 |
cker | -0.104 |
fish | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
oph | +1.088 |
cake | +0.938 |
cakes | +0.934 |
amusement | +0.921 |
uct | +0.901 |
Neg logit contributions | |
emo | -0.704 |
fish | -0.612 |
eer | -0.589 |
cker | -0.574 |
sailor | -0.554 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.018 |
cakes | +0.017 |
board | +0.016 |
amusement | +0.016 |
Neg logit contributions | |
emo | -0.021 |
eer | -0.017 |
sailor | -0.017 |
cker | -0.017 |
ba | -0.017 |
Token | chalk |
Token ID | 30860 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
oph | +0.012 |
cake | +0.011 |
cakes | +0.011 |
uct | +0.010 |
ue | +0.010 |
Neg logit contributions | |
emo | -0.012 |
eer | -0.010 |
sailor | -0.010 |
cker | -0.010 |
ba | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
oph | +0.510 |
cake | +0.451 |
cakes | +0.449 |
amusement | +0.439 |
uct | +0.437 |
Neg logit contributions | |
emo | -0.377 |
fish | -0.328 |
eer | -0.325 |
sailor | -0.305 |
ba | -0.303 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
oph | +0.020 |
cake | +0.019 |
cakes | +0.018 |
board | +0.017 |
ue | +0.017 |
Neg logit contributions | |
emo | -0.018 |
eer | -0.015 |
sailor | -0.015 |
cker | -0.015 |
fish | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
emo | +0.135 |
eer | +0.109 |
sailor | +0.107 |
ba | +0.106 |
fish | +0.105 |
Neg logit contributions | |
oph | -0.138 |
cake | -0.134 |
cakes | -0.130 |
board | -0.121 |
amusement | -0.119 |
Token | They |
Token ID | 1119 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
cake | +0.027 |
oph | +0.026 |
cakes | +0.026 |
amusement | +0.024 |
board | +0.023 |
Neg logit contributions | |
emo | -0.033 |
sailor | -0.026 |
eer | -0.025 |
ba | -0.024 |
fish | -0.024 |
Token | opened |
Token ID | 4721 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
cake | +0.052 |
oph | +0.052 |
cakes | +0.050 |
amusement | +0.047 |
liv | +0.046 |
Neg logit contributions | |
emo | -0.039 |
ba | -0.032 |
sailor | -0.032 |
eer | -0.031 |
cker | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
emo | +0.268 |
eer | +0.216 |
sailor | +0.215 |
ba | +0.212 |
cker | +0.208 |
Neg logit contributions | |
oph | -0.267 |
cake | -0.264 |
cakes | -0.255 |
board | -0.239 |
amusement | -0.230 |
Token | cup |
Token ID | 6508 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
oph | +0.029 |
uct | +0.025 |
cake | +0.025 |
amusement | +0.024 |
cakes | +0.024 |
Neg logit contributions | |
emo | -0.031 |
rito | -0.028 |
ba | -0.027 |
eer | -0.027 |
fish | -0.026 |
Token | board |
Token ID | 3526 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
amusement | +0.348 |
uct | +0.345 |
icious | +0.341 |
oph | +0.338 |
Tam | +0.305 |
Neg logit contributions | |
fish | -0.534 |
emo | -0.502 |
ware | -0.482 |
eer | -0.474 |
sword | -0.466 |
Token | and |
Token ID | 290 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
oph | +1.164 |
icious | +1.071 |
amusement | +1.065 |
uct | +1.050 |
Tam | +1.032 |
Neg logit contributions | |
fish | -0.456 |
emo | -0.448 |
sword | -0.389 |
sail | -0.376 |
eer | -0.355 |
Token | took |
Token ID | 1718 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
oph | +0.051 |
cake | +0.050 |
cakes | +0.048 |
amusement | +0.045 |
ue | +0.045 |
Neg logit contributions | |
emo | -0.046 |
sailor | -0.038 |
ba | -0.037 |
eer | -0.036 |
fish | -0.035 |
Token | out |
Token ID | 503 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
emo | +0.024 |
eer | +0.020 |
sailor | +0.020 |
cker | +0.020 |
ba | +0.020 |
Neg logit contributions | |
oph | -0.019 |
cake | -0.018 |
cakes | -0.018 |
board | -0.016 |
amusement | -0.016 |
Token | some |
Token ID | 617 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
emo | +0.180 |
eer | +0.147 |
sailor | +0.146 |
ba | +0.143 |
rito | +0.140 |
Neg logit contributions | |
oph | -0.176 |
cake | -0.172 |
cakes | -0.163 |
board | -0.154 |
uct | -0.150 |
Token | pots |
Token ID | 32195 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
oph | +0.374 |
cake | +0.357 |
cakes | +0.345 |
amusement | +0.317 |
board | +0.317 |
Neg logit contributions | |
emo | -0.423 |
eer | -0.352 |
sailor | -0.344 |
ba | -0.338 |
rito | -0.338 |
Token | They |
Token ID | 1119 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
cake | +0.027 |
cakes | +0.026 |
oph | +0.026 |
amusement | +0.024 |
uct | +0.024 |
Neg logit contributions | |
emo | -0.028 |
sailor | -0.022 |
eer | -0.021 |
rito | -0.021 |
sail | -0.020 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
oph | +0.043 |
cake | +0.042 |
cakes | +0.041 |
board | +0.038 |
amusement | +0.037 |
Neg logit contributions | |
emo | -0.052 |
eer | -0.043 |
sailor | -0.042 |
ba | -0.042 |
cker | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
oph | +0.077 |
cake | +0.073 |
uct | +0.070 |
ue | +0.070 |
cakes | +0.067 |
Neg logit contributions | |
emo | -0.059 |
sailor | -0.048 |
eer | -0.047 |
fish | -0.044 |
ba | -0.043 |
Token | big |
Token ID | 1263 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
oph | +0.008 |
cake | +0.008 |
cakes | +0.008 |
uct | +0.007 |
amusement | +0.007 |
Neg logit contributions | |
emo | -0.006 |
sailor | -0.005 |
eer | -0.005 |
fish | -0.005 |
ba | -0.005 |
Token | cup |
Token ID | 6508 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
oph | +0.096 |
uct | +0.090 |
cake | +0.088 |
cakes | +0.088 |
liv | +0.083 |
Neg logit contributions | |
emo | -0.077 |
sailor | -0.073 |
fish | -0.069 |
sail | -0.066 |
eer | -0.066 |
Token | board |
Token ID | 3526 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.536 |
uct | +0.499 |
amusement | +0.479 |
Tam | +0.470 |
liv | +0.449 |
Neg logit contributions | |
fish | -0.424 |
emo | -0.371 |
sailor | -0.344 |
ery | -0.333 |
eer | -0.327 |
Token | with |
Token ID | 351 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
oph | +1.176 |
uct | +0.987 |
amusement | +0.973 |
Tam | +0.951 |
icious | +0.945 |
Neg logit contributions | |
emo | -0.582 |
fish | -0.551 |
sail | -0.475 |
exc | -0.473 |
eer | -0.470 |
Token | many |
Token ID | 867 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
oph | +0.087 |
cake | +0.084 |
cakes | +0.079 |
uct | +0.078 |
ue | +0.077 |
Neg logit contributions | |
emo | -0.074 |
eer | -0.061 |
sailor | -0.059 |
ba | -0.057 |
rito | -0.057 |
Token | things |
Token ID | 1243 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
oph | +0.182 |
cake | +0.175 |
cakes | +0.165 |
uct | +0.157 |
amusement | +0.157 |
Neg logit contributions | |
emo | -0.161 |
eer | -0.133 |
sailor | -0.128 |
fish | -0.127 |
ba | -0.127 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
emo | +0.196 |
eer | +0.159 |
sailor | +0.155 |
ba | +0.154 |
fish | +0.152 |
Neg logit contributions | |
oph | -0.210 |
cake | -0.200 |
cakes | -0.195 |
board | -0.182 |
amusement | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
emo | +0.135 |
eer | +0.109 |
sailor | +0.107 |
ba | +0.106 |
fish | +0.105 |
Neg logit contributions | |
oph | -0.138 |
cake | -0.134 |
cakes | -0.130 |
board | -0.121 |
amusement | -0.119 |
Token | teacher |
Token ID | 4701 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
oph | +0.006 |
cake | +0.005 |
cakes | +0.005 |
uct | +0.005 |
ue | +0.005 |
Neg logit contributions | |
emo | -0.006 |
sailor | -0.006 |
eer | -0.005 |
fish | -0.005 |
exc | -0.005 |
Token | writes |
Token ID | 6797 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
oph | +0.421 |
cake | +0.405 |
cakes | +0.394 |
board | +0.363 |
amusement | +0.362 |
Neg logit contributions | |
emo | -0.469 |
eer | -0.399 |
sailor | -0.392 |
ba | -0.381 |
cker | -0.380 |
Token | on |
Token ID | 319 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
emo | +0.322 |
eer | +0.274 |
sailor | +0.269 |
ba | +0.266 |
fish | +0.263 |
Neg logit contributions | |
oph | -0.246 |
cake | -0.230 |
cakes | -0.221 |
amusement | -0.207 |
board | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
oph | +0.101 |
cake | +0.100 |
cakes | +0.096 |
uct | +0.089 |
board | +0.088 |
Neg logit contributions | |
emo | -0.088 |
eer | -0.076 |
sailor | -0.072 |
ba | -0.069 |
rito | -0.068 |
Token | black |
Token ID | 2042 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
oph | +0.025 |
cake | +0.023 |
cakes | +0.023 |
ue | +0.021 |
uct | +0.021 |
Neg logit contributions | |
emo | -0.028 |
eer | -0.024 |
sailor | -0.024 |
cker | -0.023 |
fish | -0.023 |
Token | board |
Token ID | 3526 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.054 |
uct | +0.046 |
cakes | +0.038 |
cake | +0.037 |
liv | +0.033 |
Neg logit contributions | |
emo | -0.229 |
eer | -0.214 |
sailor | -0.208 |
fish | -0.204 |
rito | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
oph | +0.907 |
cake | +0.787 |
amusement | +0.782 |
cakes | +0.779 |
uct | +0.750 |
Neg logit contributions | |
emo | -0.845 |
eer | -0.717 |
fish | -0.707 |
sailor | -0.705 |
ba | -0.682 |
Token | She |
Token ID | 1375 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
oph | +0.025 |
cake | +0.024 |
cakes | +0.023 |
board | +0.021 |
amusement | +0.021 |
Neg logit contributions | |
emo | -0.034 |
eer | -0.029 |
sailor | -0.029 |
rito | -0.027 |
Albert | -0.027 |
Token | writes |
Token ID | 6797 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
oph | +0.209 |
cake | +0.204 |
cakes | +0.199 |
board | +0.183 |
amusement | +0.180 |
Neg logit contributions | |
emo | -0.288 |
eer | -0.239 |
sailor | -0.234 |
ba | -0.233 |
rito | -0.233 |
Token | words |
Token ID | 2456 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
emo | +0.321 |
eer | +0.272 |
sailor | +0.267 |
ba | +0.265 |
fish | +0.260 |
Neg logit contributions | |
oph | -0.249 |
cake | -0.234 |
cakes | -0.225 |
amusement | -0.211 |
board | -0.209 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
oph | +0.143 |
cake | +0.138 |
cakes | +0.134 |
board | +0.123 |
amusement | +0.121 |
Neg logit contributions | |
emo | -0.207 |
eer | -0.174 |
sailor | -0.172 |
ba | -0.170 |
cker | -0.168 |
Token | on |
Token ID | 319 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
oph | +0.013 |
cake | +0.013 |
cakes | +0.012 |
amusement | +0.012 |
board | +0.012 |
Neg logit contributions | |
emo | -0.010 |
ba | -0.008 |
sailor | -0.007 |
eer | -0.007 |
fish | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
oph | +0.069 |
cake | +0.066 |
cakes | +0.065 |
board | +0.060 |
amusement | +0.058 |
Neg logit contributions | |
emo | -0.107 |
eer | -0.092 |
ba | -0.090 |
rito | -0.090 |
cker | -0.089 |
Token | they |
Token ID | 484 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
emo | +0.020 |
sailor | +0.016 |
eer | +0.016 |
ba | +0.016 |
cker | +0.016 |
Neg logit contributions | |
oph | -0.013 |
cake | -0.013 |
cakes | -0.013 |
board | -0.012 |
amusement | -0.011 |
Token | never |
Token ID | 1239 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
emo | +0.035 |
ba | +0.029 |
sailor | +0.029 |
eer | +0.029 |
cker | +0.028 |
Neg logit contributions | |
cake | -0.028 |
oph | -0.028 |
cakes | -0.028 |
board | -0.025 |
amusement | -0.025 |
Token | qu |
Token ID | 627 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
oph | +0.027 |
cake | +0.027 |
cakes | +0.027 |
board | +0.024 |
liv | +0.024 |
Neg logit contributions | |
emo | -0.029 |
eer | -0.023 |
ba | -0.023 |
sailor | -0.023 |
cker | -0.022 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
oph | +0.018 |
cake | +0.018 |
cakes | +0.016 |
amusement | +0.016 |
Rebecca | +0.014 |
Neg logit contributions | |
emo | -0.048 |
eer | -0.040 |
ba | -0.040 |
rito | -0.039 |
cker | -0.039 |
Token | led |
Token ID | 992 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
oph | +0.932 |
cake | +0.917 |
cakes | +0.913 |
board | +0.848 |
uct | +0.823 |
Neg logit contributions | |
emo | -0.821 |
sailor | -0.658 |
eer | -0.648 |
rito | -0.639 |
cker | -0.632 |
Token | again |
Token ID | 757 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
emo | +0.470 |
eer | +0.401 |
sailor | +0.392 |
ba | +0.391 |
cker | +0.390 |
Neg logit contributions | |
oph | -0.265 |
cake | -0.255 |
cakes | -0.247 |
board | -0.222 |
amusement | -0.221 |
Token | and |
Token ID | 290 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
oph | +0.275 |
cake | +0.265 |
cakes | +0.255 |
amusement | +0.235 |
board | +0.235 |
Neg logit contributions | |
emo | -0.430 |
eer | -0.363 |
sailor | -0.355 |
rito | -0.355 |
ba | -0.352 |
Token | played |
Token ID | 2826 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
oph | +0.039 |
cake | +0.038 |
cakes | +0.037 |
board | +0.035 |
amusement | +0.033 |
Neg logit contributions | |
emo | -0.044 |
eer | -0.036 |
sailor | -0.035 |
ba | -0.035 |
cker | -0.034 |
Token | together |
Token ID | 1978 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
oph | +0.036 |
cake | +0.035 |
cakes | +0.034 |
board | +0.031 |
amusement | +0.031 |
Neg logit contributions | |
emo | -0.039 |
sailor | -0.032 |
eer | -0.032 |
ba | -0.031 |
fish | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
emo | +0.104 |
eer | +0.086 |
ba | +0.083 |
cker | +0.082 |
sailor | +0.082 |
Neg logit contributions | |
oph | -0.118 |
cakes | -0.115 |
cake | -0.113 |
amusement | -0.108 |
uct | -0.105 |
Token | Ben |
Token ID | 3932 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
oph | +0.003 |
cake | +0.003 |
cakes | +0.002 |
board | +0.002 |
amusement | +0.002 |
Neg logit contributions | |
emo | -0.004 |
sailor | -0.003 |
eer | -0.003 |
ba | -0.003 |
fish | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
cakes | +0.062 |
oph | +0.062 |
cake | +0.060 |
amusement | +0.056 |
uct | +0.054 |
Neg logit contributions | |
emo | -0.046 |
eer | -0.037 |
ba | -0.036 |
sailor | -0.036 |
cker | -0.035 |
Token | stop |
Token ID | 2245 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
emo | +0.048 |
eer | +0.039 |
sailor | +0.039 |
ba | +0.038 |
fish | +0.037 |
Neg logit contributions | |
oph | -0.045 |
cake | -0.044 |
cakes | -0.043 |
board | -0.039 |
amusement | -0.039 |
Token | qu |
Token ID | 627 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
oph | +0.264 |
cake | +0.254 |
cakes | +0.249 |
board | +0.227 |
amusement | +0.219 |
Neg logit contributions | |
emo | -0.330 |
sailor | -0.273 |
eer | -0.271 |
ba | -0.269 |
fish | -0.263 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
cake | +0.015 |
oph | +0.015 |
cakes | +0.014 |
amusement | +0.013 |
Rebecca | +0.012 |
Neg logit contributions | |
emo | -0.024 |
ba | -0.020 |
ery | -0.019 |
eer | -0.019 |
cker | -0.019 |
Token | ling |
Token ID | 1359 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
oph | +1.148 |
cake | +1.123 |
cakes | +1.103 |
board | +1.041 |
amusement | +1.038 |
Neg logit contributions | |
emo | -0.646 |
eer | -0.479 |
sailor | -0.462 |
ba | -0.461 |
cker | -0.446 |
Token | right |
Token ID | 826 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
emo | +0.250 |
eer | +0.217 |
sailor | +0.208 |
ba | +0.207 |
fish | +0.197 |
Neg logit contributions | |
oph | -0.349 |
cakes | -0.328 |
cake | -0.326 |
uct | -0.303 |
liv | -0.300 |
Token | now |
Token ID | 783 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
oph | +0.480 |
cake | +0.460 |
cakes | +0.457 |
amusement | +0.410 |
board | +0.404 |
Neg logit contributions | |
emo | -0.479 |
eer | -0.407 |
ba | -0.398 |
sailor | -0.394 |
fish | -0.386 |
Token | ! |
Token ID | 0 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
oph | +0.377 |
cakes | +0.359 |
cake | +0.359 |
board | +0.331 |
amusement | +0.330 |
Neg logit contributions | |
emo | -0.273 |
eer | -0.219 |
sailor | -0.215 |
ba | -0.207 |
cker | -0.206 |
Token | Look |
Token ID | 6803 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
oph | +0.254 |
cake | +0.252 |
cakes | +0.240 |
board | +0.220 |
amusement | +0.208 |
Neg logit contributions | |
emo | -0.509 |
eer | -0.444 |
sailor | -0.440 |
cker | -0.440 |
ba | -0.438 |
Token | they |
Token ID | 484 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
emo | +0.028 |
eer | +0.023 |
sailor | +0.022 |
ba | +0.022 |
rito | +0.022 |
Neg logit contributions | |
oph | -0.024 |
cake | -0.023 |
cakes | -0.023 |
board | -0.021 |
amusement | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
emo | +0.043 |
sailor | +0.035 |
ba | +0.035 |
eer | +0.031 |
sail | +0.031 |
Neg logit contributions | |
cake | -0.056 |
cakes | -0.055 |
oph | -0.053 |
liv | -0.051 |
uct | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
oph | +0.080 |
cake | +0.079 |
cakes | +0.075 |
uct | +0.073 |
ue | +0.073 |
Neg logit contributions | |
emo | -0.052 |
sailor | -0.041 |
eer | -0.038 |
sail | -0.037 |
crew | -0.037 |
Token | big |
Token ID | 1263 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
emo | +0.001 |
sailor | +0.001 |
fish | +0.001 |
ba | +0.001 |
eer | +0.001 |
Neg logit contributions | |
oph | -0.002 |
cake | -0.002 |
cakes | -0.002 |
uct | -0.001 |
board | -0.001 |
Token | black |
Token ID | 2042 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
oph | +0.086 |
cakes | +0.085 |
cake | +0.084 |
uct | +0.083 |
liv | +0.076 |
Neg logit contributions | |
sailor | -0.069 |
emo | -0.068 |
sword | -0.063 |
fish | -0.062 |
sail | -0.061 |
Token | board |
Token ID | 3526 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
uct | +0.083 |
oph | +0.079 |
cakes | +0.072 |
liv | +0.070 |
cake | +0.066 |
Neg logit contributions | |
emo | -0.167 |
sailor | -0.165 |
fish | -0.158 |
eer | -0.155 |
sword | -0.155 |
Token | near |
Token ID | 1474 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
oph | +1.231 |
cakes | +0.996 |
Rebecca | +0.991 |
uct | +0.990 |
amusement | +0.989 |
Neg logit contributions | |
emo | -0.527 |
fish | -0.527 |
cker | -0.464 |
sail | -0.460 |
exc | -0.455 |
Token | the |
Token ID | 262 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
emo | +0.122 |
eer | +0.094 |
sailor | +0.093 |
sail | +0.093 |
cker | +0.092 |
Neg logit contributions | |
cake | -0.171 |
oph | -0.169 |
cakes | -0.166 |
board | -0.153 |
liv | -0.144 |
Token | fence |
Token ID | 13990 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
oph | +0.008 |
uct | +0.007 |
cakes | +0.007 |
cake | +0.007 |
liv | +0.007 |
Neg logit contributions | |
sailor | -0.005 |
emo | -0.005 |
mineral | -0.005 |
sword | -0.005 |
sail | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
oph | +0.523 |
liv | +0.446 |
cakes | +0.438 |
cake | +0.431 |
icious | +0.431 |
Neg logit contributions | |
emo | -0.162 |
fish | -0.147 |
cker | -0.141 |
sail | -0.134 |
eer | -0.132 |
Token | It |
Token ID | 632 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
oph | +0.024 |
cake | +0.023 |
cakes | +0.021 |
amusement | +0.021 |
uct | +0.020 |
Neg logit contributions | |
emo | -0.026 |
eer | -0.020 |
cker | -0.019 |
sailor | -0.019 |
sail | -0.019 |
Token | ll |
Token ID | 297 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
emo | +0.502 |
eer | +0.456 |
sailor | +0.453 |
rito | +0.451 |
Albert | +0.416 |
Neg logit contributions | |
oph | -0.500 |
ue | -0.474 |
cake | -0.460 |
cakes | -0.450 |
aw | -0.446 |
Token | ie |
Token ID | 494 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
emo | +0.402 |
rito | +0.360 |
sailor | +0.353 |
Albert | +0.345 |
Albert | +0.341 |
Neg logit contributions | |
oph | -0.374 |
ue | -0.337 |
board | -0.332 |
cake | -0.321 |
cakes | -0.320 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
emo | +0.771 |
rito | +0.647 |
sailor | +0.640 |
eer | +0.627 |
Albert | +0.622 |
Neg logit contributions | |
oph | -0.380 |
cake | -0.373 |
board | -0.345 |
aw | -0.342 |
cakes | -0.338 |
Token | O |
Token ID | 440 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
cake | +0.016 |
cakes | +0.016 |
oph | +0.016 |
board | +0.015 |
ue | +0.014 |
Neg logit contributions | |
emo | -0.014 |
cker | -0.012 |
sailor | -0.012 |
eer | -0.012 |
fish | -0.012 |
Token | ll |
Token ID | 297 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
emo | +0.488 |
sailor | +0.459 |
eer | +0.455 |
rito | +0.436 |
crew | +0.429 |
Neg logit contributions | |
oph | -0.524 |
cake | -0.484 |
cakes | -0.479 |
ue | -0.479 |
board | -0.462 |
Token | ie |
Token ID | 494 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
emo | +0.396 |
sailor | +0.363 |
rito | +0.361 |
Albert | +0.348 |
Albert | +0.345 |
Neg logit contributions | |
oph | -0.352 |
board | -0.321 |
ue | -0.318 |
cake | -0.304 |
cakes | -0.300 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
emo | +0.726 |
rito | +0.684 |
ancer | +0.644 |
ba | +0.634 |
sailor | +0.633 |
Neg logit contributions | |
board | -0.376 |
aw | -0.350 |
cake | -0.343 |
That | -0.337 |
cakes | -0.327 |
Token | to |
Token ID | 284 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
emo | +0.330 |
rito | +0.300 |
ba | +0.297 |
cker | +0.292 |
eer | +0.287 |
Neg logit contributions | |
cakes | -0.149 |
cake | -0.139 |
oph | -0.132 |
amusement | -0.129 |
board | -0.127 |
Token | read |
Token ID | 1100 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
amusement | +0.022 |
cakes | +0.022 |
board | +0.021 |
cake | +0.021 |
course | +0.020 |
Neg logit contributions | |
emo | -0.023 |
eer | -0.019 |
rito | -0.019 |
ba | -0.019 |
ancer | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
oph | +0.146 |
cake | +0.144 |
cakes | +0.143 |
board | +0.130 |
amusement | +0.129 |
Neg logit contributions | |
emo | -0.207 |
eer | -0.172 |
ba | -0.171 |
cker | -0.170 |
sailor | -0.169 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
cake | +0.011 |
oph | +0.010 |
cakes | +0.010 |
board | +0.010 |
ue | +0.009 |
Neg logit contributions | |
emo | -0.022 |
cker | -0.021 |
fish | -0.020 |
sailor | -0.020 |
ba | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
emo | +0.261 |
sailor | +0.208 |
rito | +0.205 |
ba | +0.203 |
eer | +0.202 |
Neg logit contributions | |
cakes | -0.287 |
oph | -0.285 |
cake | -0.281 |
board | -0.263 |
aw | -0.249 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
oph | +0.017 |
cake | +0.017 |
cakes | +0.017 |
amusement | +0.015 |
board | +0.015 |
Neg logit contributions | |
emo | -0.019 |
sailor | -0.016 |
eer | -0.016 |
cker | -0.015 |
rito | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
oph | +0.120 |
cake | +0.110 |
cakes | +0.110 |
amusement | +0.105 |
uct | +0.103 |
Neg logit contributions | |
emo | -0.094 |
sailor | -0.077 |
eer | -0.077 |
fish | -0.075 |
cker | -0.074 |
Token | L |
Token ID | 406 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
oph | +0.009 |
cake | +0.009 |
cakes | +0.009 |
board | +0.008 |
amusement | +0.008 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.011 |
sailor | -0.011 |
ba | -0.011 |
rito | -0.010 |
Token | izz |
Token ID | 6457 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
oph | +0.036 |
cake | +0.035 |
cakes | +0.034 |
amusement | +0.033 |
board | +0.032 |
Neg logit contributions | |
emo | -0.032 |
ba | -0.025 |
eer | -0.024 |
rito | -0.024 |
sailor | -0.024 |
Token | ie |
Token ID | 494 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
emo | +0.269 |
eer | +0.201 |
ba | +0.195 |
sailor | +0.193 |
cker | +0.188 |
Neg logit contributions | |
oph | -0.449 |
cake | -0.441 |
cakes | -0.433 |
amusement | -0.408 |
board | -0.407 |
Token | hugged |
Token ID | 41130 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
emo | +0.647 |
eer | +0.527 |
sailor | +0.525 |
ba | +0.523 |
cker | +0.510 |
Neg logit contributions | |
oph | -0.567 |
cake | -0.548 |
cakes | -0.534 |
amusement | -0.496 |
board | -0.488 |
Token | them |
Token ID | 606 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
oph | +0.037 |
cake | +0.036 |
cakes | +0.035 |
board | +0.032 |
amusement | +0.031 |
Neg logit contributions | |
emo | -0.059 |
eer | -0.050 |
sailor | -0.049 |
ba | -0.049 |
cker | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
emo | +0.195 |
sailor | +0.169 |
ba | +0.160 |
fish | +0.156 |
sail | +0.156 |
Neg logit contributions | |
oph | -0.219 |
cake | -0.215 |
cakes | -0.215 |
amusement | -0.201 |
board | -0.199 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
cake | +0.025 |
oph | +0.025 |
cakes | +0.024 |
board | +0.023 |
amusement | +0.022 |
Neg logit contributions | |
emo | -0.027 |
sailor | -0.023 |
ba | -0.022 |
fish | -0.021 |
eer | -0.021 |
Token | them |
Token ID | 606 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
oph | +0.016 |
cake | +0.015 |
cakes | +0.014 |
board | +0.013 |
amusement | +0.013 |
Neg logit contributions | |
emo | -0.029 |
eer | -0.025 |
cker | -0.024 |
sailor | -0.024 |
rito | -0.024 |
Token | Quick |
Token ID | 12029 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
emo | +0.036 |
eer | +0.029 |
rito | +0.028 |
ba | +0.028 |
sailor | +0.028 |
Neg logit contributions | |
oph | -0.038 |
cake | -0.038 |
cakes | -0.037 |
board | -0.035 |
amusement | -0.035 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
oph | +0.253 |
cake | +0.247 |
cakes | +0.242 |
board | +0.219 |
amusement | +0.219 |
Neg logit contributions | |
emo | -0.308 |
eer | -0.257 |
sailor | -0.251 |
ba | -0.250 |
cker | -0.247 |
Token | some |
Token ID | 617 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
oph | +0.276 |
cake | +0.257 |
cakes | +0.248 |
uct | +0.232 |
liv | +0.231 |
Neg logit contributions | |
emo | -0.164 |
eer | -0.131 |
sailor | -0.129 |
ba | -0.123 |
sword | -0.120 |
Token | other |
Token ID | 584 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
oph | +0.426 |
cake | +0.391 |
cakes | +0.368 |
uct | +0.353 |
liv | +0.347 |
Neg logit contributions | |
emo | -0.342 |
sailor | -0.290 |
eer | -0.289 |
ba | -0.277 |
cker | -0.272 |
Token | animals |
Token ID | 4695 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
oph | +0.068 |
cake | +0.066 |
cakes | +0.063 |
uct | +0.060 |
liv | +0.057 |
Neg logit contributions | |
emo | -0.062 |
eer | -0.055 |
sailor | -0.051 |
ba | -0.050 |
cker | -0.047 |
Token | whist |
Token ID | 32262 |
Feature activation | +8.51e+00 |
Pos logit contributions | |
emo | +0.312 |
eer | +0.260 |
ba | +0.257 |
sailor | +0.257 |
fish | +0.251 |
Neg logit contributions | |
oph | -0.303 |
cake | -0.287 |
cakes | -0.280 |
board | -0.255 |
amusement | -0.251 |
Token | ling |
Token ID | 1359 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
emo | +0.479 |
eer | +0.353 |
sailor | +0.349 |
rito | +0.336 |
cker | +0.333 |
Neg logit contributions | |
oph | -0.797 |
cake | -0.777 |
cakes | -0.767 |
board | -0.730 |
amusement | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
emo | +0.297 |
eer | +0.252 |
ba | +0.241 |
sailor | +0.240 |
cker | +0.235 |
Neg logit contributions | |
oph | -0.327 |
cake | -0.309 |
cakes | -0.301 |
board | -0.276 |
ue | -0.272 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
oph | +0.003 |
cake | +0.003 |
cakes | +0.003 |
amusement | +0.003 |
board | +0.003 |
Neg logit contributions | |
emo | -0.004 |
eer | -0.003 |
sailor | -0.003 |
cker | -0.003 |
ba | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
emo | +0.174 |
eer | +0.152 |
sailor | +0.149 |
cker | +0.145 |
rito | +0.144 |
Neg logit contributions | |
oph | -0.116 |
cake | -0.115 |
cakes | -0.112 |
ue | -0.104 |
board | -0.104 |
Token | " |
Token ID | 1 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
emo | +0.161 |
cker | +0.134 |
ba | +0.132 |
eer | +0.130 |
sailor | +0.129 |
Neg logit contributions | |
oph | -0.144 |
cake | -0.135 |
cakes | -0.132 |
amusement | -0.120 |
board | -0.119 |
Token | confident |
Token ID | 6563 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
oph | +0.184 |
cake | +0.177 |
amusement | +0.165 |
aw | +0.163 |
cakes | +0.162 |
Neg logit contributions | |
emo | -0.206 |
eer | -0.172 |
ba | -0.169 |
cker | -0.167 |
rito | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
emo | +0.027 |
eer | +0.023 |
sailor | +0.022 |
ba | +0.022 |
cker | +0.022 |
Neg logit contributions | |
oph | -0.022 |
cake | -0.021 |
cakes | -0.021 |
board | -0.019 |
amusement | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
emo | +0.004 |
ba | +0.003 |
sailor | +0.003 |
eer | +0.003 |
cker | +0.003 |
Neg logit contributions | |
oph | -0.002 |
cake | -0.002 |
cakes | -0.002 |
board | -0.002 |
That | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
emo | +0.018 |
eer | +0.015 |
sailor | +0.015 |
ba | +0.015 |
cker | +0.014 |
Neg logit contributions | |
oph | -0.015 |
cake | -0.015 |
cakes | -0.014 |
board | -0.013 |
amusement | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
oph | +0.023 |
cake | +0.022 |
cakes | +0.021 |
board | +0.020 |
amusement | +0.020 |
Neg logit contributions | |
emo | -0.024 |
eer | -0.019 |
sailor | -0.019 |
ba | -0.019 |
cker | -0.019 |
Token | pig |
Token ID | 12967 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
oph | +0.005 |
cake | +0.005 |
cakes | +0.004 |
board | +0.004 |
amusement | +0.004 |
Neg logit contributions | |
emo | -0.005 |
eer | -0.004 |
ba | -0.004 |
fish | -0.004 |
rito | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
emo | +0.716 |
eer | +0.600 |
sailor | +0.590 |
ba | +0.586 |
cker | +0.579 |
Neg logit contributions | |
oph | -0.498 |
cake | -0.483 |
cakes | -0.470 |
board | -0.430 |
amusement | -0.422 |
Token | a |
Token ID | 257 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
oph | +0.048 |
cake | +0.047 |
cakes | +0.047 |
board | +0.043 |
amusement | +0.041 |
Neg logit contributions | |
emo | -0.052 |
eer | -0.042 |
sailor | -0.042 |
ba | -0.041 |
cker | -0.041 |
Token | big |
Token ID | 1263 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
emo | +0.030 |
eer | +0.025 |
ba | +0.024 |
cker | +0.023 |
sailor | +0.023 |
Neg logit contributions | |
oph | -0.032 |
cake | -0.031 |
cakes | -0.030 |
board | -0.028 |
amusement | -0.028 |
Token | smile |
Token ID | 8212 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
oph | +0.066 |
cakes | +0.064 |
cake | +0.064 |
board | +0.059 |
uct | +0.057 |
Neg logit contributions | |
emo | -0.058 |
sailor | -0.048 |
eer | -0.047 |
cker | -0.045 |
rito | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
emo | +0.049 |
eer | +0.041 |
sailor | +0.040 |
ba | +0.040 |
cker | +0.039 |
Neg logit contributions | |
oph | -0.047 |
cakes | -0.045 |
cake | -0.044 |
amusement | -0.041 |
board | -0.040 |
Token | be |
Token ID | 307 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
cakes | +0.002 |
amusement | +0.002 |
ue | +0.002 |
Neg logit contributions | |
emo | -0.002 |
eer | -0.002 |
sailor | -0.002 |
ba | -0.002 |
rito | -0.002 |
Token | alone |
Token ID | 3436 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
emo | +0.002 |
sailor | +0.002 |
ba | +0.002 |
eer | +0.002 |
ancer | +0.002 |
Neg logit contributions | |
cake | -0.002 |
cakes | -0.002 |
oph | -0.002 |
aw | -0.002 |
Meg | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
cake | +0.006 |
oph | +0.006 |
cakes | +0.005 |
board | +0.005 |
amusement | +0.005 |
Neg logit contributions | |
emo | -0.009 |
eer | -0.008 |
cker | -0.008 |
rito | -0.008 |
ba | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
emo | +0.064 |
fish | +0.058 |
rito | +0.056 |
ba | +0.056 |
cker | +0.056 |
Neg logit contributions | |
cake | -0.032 |
oph | -0.031 |
That | -0.030 |
cakes | -0.029 |
ue | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
emo | +0.235 |
eer | +0.204 |
sailor | +0.202 |
ba | +0.198 |
rito | +0.198 |
Neg logit contributions | |
cake | -0.148 |
oph | -0.148 |
cakes | -0.143 |
board | -0.131 |
amusement | -0.130 |
Token | Bee |
Token ID | 49512 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
emo | +0.256 |
eer | +0.220 |
sailor | +0.215 |
ba | +0.212 |
rito | +0.212 |
Neg logit contributions | |
oph | -0.143 |
cake | -0.139 |
cakes | -0.134 |
board | -0.121 |
amusement | -0.119 |
Token | decided |
Token ID | 3066 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
emo | +0.779 |
eer | +0.650 |
sailor | +0.635 |
ba | +0.634 |
cker | +0.628 |
Neg logit contributions | |
oph | -0.623 |
cake | -0.607 |
cakes | -0.594 |
board | -0.541 |
amusement | -0.540 |
Token | to |
Token ID | 284 |
Feature activation | +7.92e-03 |
Pos logit contributions | |
oph | +0.232 |
cake | +0.227 |
cakes | +0.221 |
board | +0.204 |
amusement | +0.202 |
Neg logit contributions | |
emo | -0.269 |
eer | -0.221 |
sailor | -0.216 |
ba | -0.215 |
cker | -0.212 |
Token | leave |
Token ID | 2666 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
emo | +0.001 |
eer | +0.000 |
sailor | +0.000 |
ba | +0.000 |
cker | +0.000 |
Neg logit contributions | |
oph | -0.001 |
cake | -0.001 |
cakes | -0.001 |
board | -0.001 |
amusement | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
cake | +0.046 |
oph | +0.045 |
cakes | +0.044 |
Meg | +0.042 |
board | +0.041 |
Neg logit contributions | |
emo | -0.083 |
ba | -0.068 |
sailor | -0.067 |
eer | -0.067 |
rito | -0.067 |
Token | He |
Token ID | 679 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
emo | +0.082 |
fish | +0.072 |
ba | +0.071 |
sailor | +0.071 |
cker | +0.070 |
Neg logit contributions | |
cake | -0.019 |
oph | -0.017 |
cakes | -0.016 |
board | -0.016 |
Meg | -0.013 |
Token | do |
Token ID | 466 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
oph | +0.050 |
cake | +0.049 |
cakes | +0.047 |
amusement | +0.044 |
board | +0.044 |
Neg logit contributions | |
emo | -0.052 |
eer | -0.043 |
sailor | -0.042 |
ba | -0.041 |
cker | -0.041 |
Token | what |
Token ID | 644 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
oph | +0.304 |
cake | +0.296 |
cakes | +0.290 |
board | +0.270 |
amusement | +0.266 |
Neg logit contributions | |
emo | -0.304 |
eer | -0.246 |
sailor | -0.241 |
ba | -0.239 |
cker | -0.236 |
Token | they |
Token ID | 484 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
emo | +0.069 |
rito | +0.064 |
eer | +0.063 |
ba | +0.062 |
cker | +0.061 |
Neg logit contributions | |
cakes | -0.030 |
oph | -0.030 |
cake | -0.030 |
Meg | -0.027 |
ue | -0.027 |
Token | do |
Token ID | 466 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
emo | +0.055 |
eer | +0.046 |
sailor | +0.045 |
rito | +0.045 |
ba | +0.044 |
Neg logit contributions | |
oph | -0.041 |
cake | -0.040 |
cakes | -0.039 |
board | -0.036 |
amusement | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
oph | +0.272 |
cake | +0.264 |
cakes | +0.258 |
board | +0.237 |
amusement | +0.234 |
Neg logit contributions | |
emo | -0.332 |
eer | -0.274 |
sailor | -0.269 |
ba | -0.267 |
cker | -0.264 |
Token | He |
Token ID | 679 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
oph | +0.007 |
cake | +0.007 |
cakes | +0.006 |
board | +0.006 |
amusement | +0.006 |
Neg logit contributions | |
emo | -0.008 |
eer | -0.007 |
sailor | -0.006 |
ba | -0.006 |
cker | -0.006 |
Token | feels |
Token ID | 5300 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
emo | +0.115 |
eer | +0.097 |
rito | +0.095 |
sailor | +0.095 |
ba | +0.094 |
Neg logit contributions | |
oph | -0.080 |
cake | -0.078 |
cakes | -0.076 |
board | -0.071 |
amusement | -0.069 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
emo | +0.047 |
cker | +0.042 |
eer | +0.042 |
ba | +0.042 |
rito | +0.040 |
Neg logit contributions | |
cake | -0.030 |
oph | -0.029 |
amusement | -0.029 |
aw | -0.029 |
That | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
emo | +0.118 |
eer | +0.098 |
sailor | +0.097 |
ba | +0.095 |
fish | +0.095 |
Neg logit contributions | |
oph | -0.092 |
cake | -0.087 |
cakes | -0.086 |
amusement | -0.077 |
board | -0.077 |
Token | He |
Token ID | 679 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
cakes | +0.002 |
board | +0.002 |
ue | +0.002 |
Neg logit contributions | |
emo | -0.003 |
eer | -0.003 |
sailor | -0.003 |
cker | -0.003 |
ba | -0.003 |
Token | says |
Token ID | 1139 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
emo | +0.112 |
eer | +0.094 |
rito | +0.092 |
ba | +0.092 |
cker | +0.091 |
Neg logit contributions | |
oph | -0.088 |
cake | -0.085 |
cakes | -0.082 |
board | -0.078 |
amusement | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
emo | +0.043 |
eer | +0.036 |
ba | +0.035 |
sailor | +0.035 |
cker | +0.034 |
Neg logit contributions | |
oph | -0.033 |
cake | -0.032 |
cakes | -0.032 |
board | -0.029 |
amusement | -0.029 |
Token | giant |
Token ID | 6175 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
emo | +0.024 |
eer | +0.020 |
ba | +0.019 |
rito | +0.019 |
cker | +0.019 |
Neg logit contributions | |
oph | -0.023 |
cake | -0.023 |
cakes | -0.022 |
amusement | -0.020 |
board | -0.020 |
Token | feast |
Token ID | 26951 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
oph | +0.213 |
cake | +0.203 |
cakes | +0.200 |
uct | +0.183 |
board | +0.182 |
Neg logit contributions | |
emo | -0.213 |
sailor | -0.179 |
eer | -0.177 |
fish | -0.172 |
cker | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
oph | +0.108 |
cake | +0.100 |
cakes | +0.098 |
uct | +0.096 |
amusement | +0.096 |
Neg logit contributions | |
emo | -0.104 |
fish | -0.091 |
sailor | -0.088 |
eer | -0.087 |
cker | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
emo | +0.007 |
eer | +0.006 |
sailor | +0.006 |
ba | +0.006 |
rito | +0.006 |
Neg logit contributions | |
oph | -0.005 |
cake | -0.005 |
cakes | -0.005 |
amusement | -0.005 |
board | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
emo | +0.176 |
eer | +0.145 |
sailor | +0.142 |
ba | +0.141 |
cker | +0.139 |
Neg logit contributions | |
oph | -0.156 |
cake | -0.152 |
cakes | -0.148 |
board | -0.137 |
amusement | -0.135 |
Token | They |
Token ID | 2990 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
emo | +0.182 |
ba | +0.153 |
sailor | +0.145 |
Ar | +0.145 |
Albert | +0.142 |
Neg logit contributions | |
oph | -0.150 |
cake | -0.141 |
cakes | -0.138 |
board | -0.133 |
uct | -0.124 |
Token | jumped |
Token ID | 11687 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
oph | +0.174 |
cake | +0.170 |
cakes | +0.166 |
board | +0.152 |
amusement | +0.149 |
Neg logit contributions | |
emo | -0.234 |
eer | -0.196 |
sailor | -0.194 |
ba | -0.192 |
cker | -0.189 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
oph | +0.029 |
cake | +0.027 |
cakes | +0.026 |
amusement | +0.025 |
board | +0.025 |
Neg logit contributions | |
emo | -0.026 |
sailor | -0.021 |
eer | -0.020 |
ba | -0.020 |
fish | -0.020 |
Token | cl |
Token ID | 537 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
oph | +0.010 |
cake | +0.010 |
cakes | +0.009 |
board | +0.009 |
amusement | +0.008 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.011 |
sailor | -0.011 |
ba | -0.011 |
cker | -0.011 |
Token | apped |
Token ID | 6320 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
oph | +0.113 |
cake | +0.109 |
cakes | +0.106 |
board | +0.097 |
amusement | +0.096 |
Neg logit contributions | |
emo | -0.164 |
eer | -0.136 |
sailor | -0.134 |
ba | -0.132 |
rito | -0.131 |
Token | Todd |
Token ID | 14377 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
emo | +0.115 |
eer | +0.095 |
sailor | +0.092 |
ba | +0.092 |
cker | +0.092 |
Neg logit contributions | |
oph | -0.095 |
cake | -0.092 |
cakes | -0.090 |
board | -0.083 |
amusement | -0.082 |
Token | put |
Token ID | 1234 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
emo | +0.482 |
eer | +0.398 |
rito | +0.392 |
sailor | +0.384 |
cker | +0.382 |
Neg logit contributions | |
oph | -0.322 |
cake | -0.302 |
cakes | -0.288 |
board | -0.276 |
aw | -0.261 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
emo | +0.293 |
cker | +0.245 |
eer | +0.241 |
ba | +0.236 |
sailor | +0.232 |
Neg logit contributions | |
oph | -0.191 |
cake | -0.191 |
cakes | -0.190 |
board | -0.174 |
aw | -0.170 |
Token | coin |
Token ID | 10752 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
cake | +0.011 |
oph | +0.011 |
cakes | +0.011 |
board | +0.010 |
amusement | +0.010 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.010 |
ba | -0.010 |
cker | -0.010 |
rito | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
emo | +0.669 |
eer | +0.545 |
sailor | +0.524 |
ba | +0.517 |
rito | +0.515 |
Neg logit contributions | |
cake | -0.523 |
cakes | -0.508 |
oph | -0.499 |
board | -0.477 |
aw | -0.439 |
Token | his |
Token ID | 465 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
emo | +0.239 |
eer | +0.187 |
sailor | +0.183 |
ba | +0.180 |
cker | +0.177 |
Neg logit contributions | |
oph | -0.311 |
cake | -0.304 |
cakes | -0.299 |
board | -0.280 |
amusement | -0.275 |
Token | pocket |
Token ID | 10000 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
emo | +0.267 |
ba | +0.228 |
eer | +0.215 |
rito | +0.211 |
fish | +0.209 |
Neg logit contributions | |
oph | -0.176 |
cake | -0.173 |
board | -0.168 |
cakes | -0.168 |
amusement | -0.165 |
Token | and |
Token ID | 290 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
emo | +0.120 |
eer | +0.100 |
sailor | +0.098 |
ba | +0.097 |
cker | +0.096 |
Neg logit contributions | |
oph | -0.090 |
cake | -0.087 |
cakes | -0.085 |
board | -0.077 |
amusement | -0.077 |
Token | they |
Token ID | 484 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
oph | +0.022 |
cake | +0.021 |
cakes | +0.021 |
board | +0.019 |
amusement | +0.019 |
Neg logit contributions | |
emo | -0.029 |
eer | -0.024 |
rito | -0.023 |
cker | -0.023 |
ba | -0.023 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
emo | +0.054 |
eer | +0.046 |
sailor | +0.045 |
ba | +0.044 |
cker | +0.044 |
Neg logit contributions | |
oph | -0.039 |
cake | -0.038 |
cakes | -0.037 |
board | -0.034 |
amusement | -0.033 |
Token | away |
Token ID | 1497 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
emo | +0.082 |
sailor | +0.067 |
eer | +0.065 |
ba | +0.064 |
sail | +0.062 |
Neg logit contributions | |
oph | -0.093 |
cake | -0.091 |
cakes | -0.089 |
board | -0.082 |
uct | -0.080 |
Token | because |
Token ID | 780 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
emo | +0.171 |
sailor | +0.140 |
eer | +0.138 |
fish | +0.136 |
ba | +0.136 |
Neg logit contributions | |
oph | -0.183 |
cake | -0.171 |
cakes | -0.170 |
amusement | -0.157 |
board | -0.156 |
Token | he |
Token ID | 339 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
oph | +0.080 |
cake | +0.077 |
cakes | +0.075 |
board | +0.071 |
amusement | +0.070 |
Neg logit contributions | |
emo | -0.051 |
eer | -0.039 |
sailor | -0.039 |
ba | -0.036 |
fish | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
emo | +0.203 |
sailor | +0.172 |
rito | +0.168 |
eer | +0.168 |
cker | +0.165 |
Neg logit contributions | |
oph | -0.138 |
cake | -0.134 |
cakes | -0.129 |
board | -0.124 |
ue | -0.113 |
Token | too |
Token ID | 1165 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
cake | +0.048 |
oph | +0.047 |
cakes | +0.045 |
amusement | +0.043 |
uct | +0.043 |
Neg logit contributions | |
emo | -0.077 |
fish | -0.066 |
eer | -0.065 |
cker | -0.065 |
ba | -0.065 |
Token | boss |
Token ID | 6478 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
oph | +0.154 |
cake | +0.153 |
cakes | +0.143 |
aw | +0.134 |
amusement | +0.132 |
Neg logit contributions | |
emo | -0.181 |
eer | -0.156 |
rito | -0.154 |
ba | -0.152 |
fish | -0.150 |
Token | y |
Token ID | 88 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
oph | +0.014 |
cake | +0.014 |
cakes | +0.014 |
amusement | +0.013 |
board | +0.012 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.010 |
ba | -0.010 |
sailor | -0.010 |
cker | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
emo | +0.149 |
eer | +0.124 |
sailor | +0.118 |
ba | +0.118 |
cker | +0.115 |
Neg logit contributions | |
oph | -0.153 |
cake | -0.147 |
cakes | -0.145 |
amusement | -0.133 |
board | -0.131 |
Token | At |
Token ID | 1629 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
oph | +0.022 |
cake | +0.021 |
cakes | +0.020 |
amusement | +0.019 |
liv | +0.018 |
Neg logit contributions | |
emo | -0.018 |
eer | -0.014 |
sailor | -0.013 |
Albert | -0.013 |
crew | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
emo | +0.087 |
sailor | +0.073 |
ba | +0.070 |
eer | +0.069 |
cker | +0.068 |
Neg logit contributions | |
cake | -0.086 |
oph | -0.086 |
cakes | -0.085 |
board | -0.079 |
aw | -0.074 |
Token | end |
Token ID | 886 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
cakes | +0.023 |
cake | +0.022 |
oph | +0.022 |
uct | +0.021 |
aw | +0.020 |
Neg logit contributions | |
sailor | -0.014 |
sail | -0.014 |
emo | -0.014 |
own | -0.014 |
sword | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
oph | +0.338 |
cake | +0.308 |
cakes | +0.292 |
uct | +0.287 |
amusement | +0.276 |
Neg logit contributions | |
emo | -0.446 |
sailor | -0.363 |
eer | -0.359 |
fish | -0.351 |
ba | -0.350 |
Token | both |
Token ID | 1111 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
emo | +0.243 |
eer | +0.204 |
rito | +0.196 |
cker | +0.193 |
sailor | +0.192 |
Neg logit contributions | |
oph | -0.207 |
cake | -0.204 |
cakes | -0.198 |
board | -0.184 |
amusement | -0.184 |
Token | have |
Token ID | 423 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
oph | +0.202 |
cake | +0.197 |
cakes | +0.192 |
board | +0.180 |
amusement | +0.178 |
Neg logit contributions | |
emo | -0.206 |
eer | -0.167 |
sailor | -0.163 |
ba | -0.162 |
rito | -0.160 |
Token | a |
Token ID | 257 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
emo | +0.017 |
eer | +0.015 |
ba | +0.014 |
cker | +0.014 |
sailor | +0.014 |
Neg logit contributions | |
oph | -0.011 |
cake | -0.011 |
cakes | -0.011 |
amusement | -0.010 |
board | -0.010 |
Token | new |
Token ID | 649 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
emo | +0.002 |
eer | +0.001 |
cker | +0.001 |
ba | +0.001 |
rito | +0.001 |
Neg logit contributions | |
oph | -0.001 |
cake | -0.001 |
amusement | -0.001 |
cakes | -0.001 |
board | -0.001 |
Token | shirt |
Token ID | 10147 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
emo | +0.307 |
eer | +0.261 |
ba | +0.254 |
cker | +0.252 |
rito | +0.252 |
Neg logit contributions | |
oph | -0.197 |
cake | -0.188 |
cakes | -0.181 |
board | -0.170 |
amusement | -0.169 |
Token | ." |
Token ID | 526 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
oph | +0.362 |
cake | +0.338 |
cakes | +0.333 |
amusement | +0.321 |
uct | +0.317 |
Neg logit contributions | |
emo | -0.288 |
eer | -0.231 |
sailor | -0.226 |
ba | -0.224 |
fish | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
emo | +0.316 |
eer | +0.258 |
sailor | +0.255 |
ba | +0.251 |
cker | +0.247 |
Neg logit contributions | |
oph | -0.276 |
cake | -0.269 |
cakes | -0.263 |
board | -0.243 |
amusement | -0.240 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
emo | +0.180 |
eer | +0.162 |
cker | +0.158 |
rito | +0.157 |
sailor | +0.155 |
Neg logit contributions | |
oph | -0.116 |
cake | -0.109 |
cakes | -0.104 |
ue | -0.101 |
That | -0.098 |
Token | Ben |
Token ID | 11696 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
emo | +0.182 |
sailor | +0.152 |
ba | +0.152 |
fish | +0.149 |
eer | +0.146 |
Neg logit contributions | |
oph | -0.127 |
cake | -0.126 |
cakes | -0.125 |
board | -0.111 |
amusement | -0.107 |
Token | shakes |
Token ID | 29959 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
oph | +0.149 |
cake | +0.147 |
cakes | +0.146 |
liv | +0.131 |
amusement | +0.131 |
Neg logit contributions | |
emo | -0.141 |
sailor | -0.119 |
eer | -0.118 |
fish | -0.113 |
ba | -0.108 |
Token | his |
Token ID | 465 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
emo | +0.009 |
eer | +0.006 |
sailor | +0.006 |
ba | +0.006 |
cker | +0.005 |
Neg logit contributions | |
oph | -0.022 |
cake | -0.021 |
cakes | -0.021 |
board | -0.020 |
amusement | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
oph | +0.044 |
cake | +0.041 |
cakes | +0.040 |
uct | +0.037 |
amusement | +0.037 |
Neg logit contributions | |
emo | -0.038 |
eer | -0.032 |
sailor | -0.031 |
ba | -0.030 |
fish | -0.030 |
Token | But |
Token ID | 887 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
emo | +0.018 |
eer | +0.013 |
sailor | +0.012 |
crew | +0.012 |
Albert | +0.012 |
Neg logit contributions | |
oph | -0.021 |
cake | -0.020 |
cakes | -0.019 |
board | -0.018 |
amusement | -0.018 |
Token | when |
Token ID | 618 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
emo | +0.235 |
sailor | +0.195 |
eer | +0.187 |
ba | +0.187 |
cker | +0.185 |
Neg logit contributions | |
oph | -0.211 |
cake | -0.203 |
cakes | -0.195 |
board | -0.184 |
uct | -0.170 |
Token | they |
Token ID | 484 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
emo | +0.097 |
sailor | +0.078 |
eer | +0.075 |
ba | +0.075 |
fish | +0.073 |
Neg logit contributions | |
oph | -0.108 |
cake | -0.106 |
cakes | -0.102 |
board | -0.097 |
amusement | -0.093 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
emo | +0.081 |
ba | +0.070 |
fish | +0.068 |
sailor | +0.068 |
eer | +0.064 |
Neg logit contributions | |
cakes | -0.083 |
cake | -0.083 |
oph | -0.082 |
amusement | -0.074 |
oga | -0.073 |
Token | at |
Token ID | 379 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
emo | +0.145 |
eer | +0.120 |
sailor | +0.120 |
ba | +0.117 |
fish | +0.116 |
Neg logit contributions | |
oph | -0.110 |
cake | -0.107 |
cakes | -0.104 |
board | -0.095 |
amusement | -0.093 |
Token | their |
Token ID | 511 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
oph | +0.220 |
cake | +0.213 |
cakes | +0.208 |
board | +0.190 |
amusement | +0.188 |
Neg logit contributions | |
emo | -0.314 |
eer | -0.263 |
sailor | -0.259 |
ba | -0.258 |
cker | -0.255 |
Token | patch |
Token ID | 8529 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
emo | +0.054 |
eer | +0.043 |
sailor | +0.043 |
cker | +0.042 |
fish | +0.042 |
Neg logit contributions | |
oph | -0.057 |
cake | -0.056 |
cakes | -0.054 |
board | -0.050 |
uct | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
oph | +0.172 |
cake | +0.162 |
cakes | +0.157 |
amusement | +0.150 |
uct | +0.146 |
Neg logit contributions | |
emo | -0.190 |
eer | -0.155 |
sailor | -0.153 |
fish | -0.153 |
ba | -0.151 |
Token | they |
Token ID | 484 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
emo | +0.062 |
eer | +0.050 |
sailor | +0.050 |
ba | +0.049 |
cker | +0.048 |
Neg logit contributions | |
oph | -0.061 |
cake | -0.059 |
cakes | -0.057 |
board | -0.053 |
amusement | -0.052 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
emo | +0.092 |
sailor | +0.076 |
ba | +0.075 |
eer | +0.075 |
fish | +0.074 |
Neg logit contributions | |
oph | -0.083 |
cake | -0.081 |
cakes | -0.079 |
board | -0.072 |
amusement | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
oph | +0.328 |
cake | +0.320 |
cakes | +0.313 |
board | +0.290 |
amusement | +0.287 |
Neg logit contributions | |
emo | -0.337 |
eer | -0.273 |
sailor | -0.268 |
ba | -0.265 |
cker | -0.262 |
Token | I |
Token ID | 314 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
emo | +0.036 |
eer | +0.030 |
ba | +0.029 |
sailor | +0.029 |
cker | +0.029 |
Neg logit contributions | |
oph | -0.028 |
cake | -0.027 |
cakes | -0.027 |
board | -0.025 |
amusement | -0.024 |
Token | will |
Token ID | 481 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
emo | +0.089 |
eer | +0.072 |
sailor | +0.071 |
ba | +0.069 |
cker | +0.069 |
Neg logit contributions | |
oph | -0.094 |
cake | -0.094 |
cakes | -0.090 |
board | -0.085 |
amusement | -0.084 |
Token | use |
Token ID | 779 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
emo | +0.143 |
eer | +0.113 |
sailor | +0.113 |
ba | +0.111 |
cker | +0.110 |
Neg logit contributions | |
oph | -0.155 |
cake | -0.151 |
cakes | -0.149 |
board | -0.138 |
amusement | -0.135 |
Token | my |
Token ID | 616 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
emo | +0.336 |
eer | +0.270 |
sailor | +0.267 |
ba | +0.261 |
cker | +0.257 |
Neg logit contributions | |
oph | -0.347 |
cake | -0.339 |
cakes | -0.331 |
board | -0.308 |
amusement | -0.301 |
Token | papers |
Token ID | 9473 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
emo | +0.207 |
ba | +0.174 |
eer | +0.173 |
rito | +0.168 |
sailor | +0.168 |
Neg logit contributions | |
oph | -0.133 |
cake | -0.131 |
cakes | -0.128 |
board | -0.122 |
amusement | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
oph | +0.148 |
cake | +0.139 |
cakes | +0.138 |
amusement | +0.129 |
board | +0.126 |
Neg logit contributions | |
emo | -0.148 |
eer | -0.121 |
sailor | -0.119 |
ba | -0.118 |
rito | -0.116 |
Token | I |
Token ID | 314 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
emo | +0.039 |
eer | +0.032 |
sailor | +0.032 |
ba | +0.032 |
cker | +0.031 |
Neg logit contributions | |
oph | -0.031 |
cake | -0.030 |
cakes | -0.029 |
board | -0.027 |
amusement | -0.026 |
Token | will |
Token ID | 481 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
emo | +0.095 |
eer | +0.077 |
sailor | +0.076 |
cker | +0.073 |
ba | +0.073 |
Neg logit contributions | |
cake | -0.095 |
oph | -0.094 |
cakes | -0.091 |
board | -0.087 |
amusement | -0.084 |
Token | ask |
Token ID | 1265 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
emo | +0.146 |
sailor | +0.115 |
eer | +0.115 |
ba | +0.113 |
cker | +0.112 |
Neg logit contributions | |
oph | -0.159 |
cake | -0.154 |
cakes | -0.153 |
board | -0.142 |
amusement | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
emo | +0.507 |
eer | +0.425 |
cker | +0.414 |
sailor | +0.413 |
rito | +0.412 |
Neg logit contributions | |
oph | -0.373 |
cake | -0.364 |
cakes | -0.355 |
board | -0.325 |
amusement | -0.320 |
Token | plays |
Token ID | 5341 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
oph | +0.033 |
cake | +0.032 |
cakes | +0.031 |
board | +0.029 |
amusement | +0.028 |
Neg logit contributions | |
emo | -0.044 |
eer | -0.037 |
rito | -0.036 |
sailor | -0.035 |
cker | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
emo | +0.071 |
sailor | +0.058 |
eer | +0.058 |
ba | +0.057 |
fish | +0.057 |
Neg logit contributions | |
oph | -0.074 |
cake | -0.069 |
cakes | -0.068 |
amusement | -0.063 |
board | -0.063 |
Token | She |
Token ID | 1375 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
emo | +0.022 |
eer | +0.020 |
sailor | +0.019 |
cker | +0.019 |
ba | +0.019 |
Neg logit contributions | |
oph | -0.008 |
cake | -0.008 |
cakes | -0.007 |
board | -0.006 |
amusement | -0.006 |
Token | sings |
Token ID | 33041 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
oph | +0.188 |
cake | +0.183 |
cakes | +0.177 |
board | +0.165 |
amusement | +0.163 |
Neg logit contributions | |
emo | -0.250 |
eer | -0.205 |
rito | -0.202 |
ba | -0.200 |
sailor | -0.199 |
Token | loud |
Token ID | 7812 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
emo | +0.417 |
sailor | +0.344 |
eer | +0.343 |
ba | +0.341 |
fish | +0.326 |
Neg logit contributions | |
oph | -0.392 |
cake | -0.372 |
cakes | -0.365 |
amusement | -0.346 |
board | -0.344 |
Token | and |
Token ID | 290 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
oph | +0.265 |
cake | +0.256 |
cakes | +0.250 |
board | +0.228 |
amusement | +0.226 |
Neg logit contributions | |
emo | -0.339 |
eer | -0.288 |
sailor | -0.280 |
ba | -0.277 |
rito | -0.271 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
oph | +0.006 |
cake | +0.006 |
cakes | +0.005 |
board | +0.005 |
amusement | +0.005 |
Neg logit contributions | |
emo | -0.006 |
eer | -0.004 |
sailor | -0.004 |
ba | -0.004 |
cker | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
emo | +0.103 |
eer | +0.086 |
sailor | +0.084 |
ba | +0.083 |
fish | +0.081 |
Neg logit contributions | |
oph | -0.098 |
cake | -0.094 |
cakes | -0.092 |
amusement | -0.085 |
board | -0.085 |
Token | She |
Token ID | 1375 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
emo | +0.016 |
cker | +0.014 |
eer | +0.014 |
fish | +0.014 |
rito | +0.014 |
Neg logit contributions | |
oph | -0.007 |
cake | -0.006 |
cakes | -0.006 |
board | -0.005 |
Rebecca | -0.005 |
Token | makes |
Token ID | 1838 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
oph | +0.210 |
cake | +0.204 |
cakes | +0.199 |
board | +0.185 |
amusement | +0.183 |
Neg logit contributions | |
emo | -0.238 |
eer | -0.194 |
sailor | -0.190 |
ba | -0.188 |
cker | -0.187 |
Token | up |
Token ID | 510 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
emo | +0.035 |
eer | +0.029 |
sailor | +0.029 |
ba | +0.028 |
cker | +0.028 |
Neg logit contributions | |
oph | -0.025 |
cake | -0.025 |
cakes | -0.024 |
board | -0.022 |
amusement | -0.022 |
Token | world |
Token ID | 995 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
oph | +0.012 |
cake | +0.011 |
amusement | +0.011 |
cakes | +0.011 |
board | +0.011 |
Neg logit contributions | |
emo | -0.013 |
rito | -0.011 |
eer | -0.010 |
cker | -0.010 |
ba | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
oph | +0.012 |
cake | +0.011 |
cakes | +0.011 |
amusement | +0.010 |
uct | +0.010 |
Neg logit contributions | |
emo | -0.012 |
eer | -0.010 |
sailor | -0.010 |
fish | -0.010 |
ba | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
emo | +0.063 |
eer | +0.052 |
sailor | +0.052 |
ba | +0.051 |
cker | +0.050 |
Neg logit contributions | |
oph | -0.053 |
cake | -0.051 |
cakes | -0.050 |
board | -0.046 |
amusement | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
cakes | +0.002 |
board | +0.002 |
amusement | +0.002 |
Neg logit contributions | |
emo | -0.003 |
sailor | -0.002 |
eer | -0.002 |
ba | -0.002 |
fish | -0.002 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
oph | +0.025 |
cake | +0.024 |
cakes | +0.024 |
board | +0.023 |
amusement | +0.022 |
Neg logit contributions | |
emo | -0.041 |
rito | -0.036 |
eer | -0.035 |
cker | -0.034 |
sailor | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
oph | +0.008 |
cake | +0.008 |
cakes | +0.008 |
board | +0.007 |
amusement | +0.007 |
Neg logit contributions | |
emo | -0.010 |
eer | -0.008 |
sailor | -0.008 |
ba | -0.008 |
cker | -0.008 |
Token | mer |
Token ID | 4017 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
oph | +0.008 |
amusement | +0.008 |
cake | +0.008 |
board | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
emo | -0.008 |
cker | -0.007 |
rito | -0.007 |
eer | -0.007 |
ba | -0.006 |
Token | maid |
Token ID | 23151 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
emo | +0.138 |
eer | +0.108 |
cker | +0.107 |
exc | +0.106 |
rito | +0.104 |
Neg logit contributions | |
oph | -0.284 |
cake | -0.269 |
cakes | -0.263 |
board | -0.253 |
ue | -0.235 |
Token | to |
Token ID | 284 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
emo | +0.863 |
eer | +0.709 |
sailor | +0.696 |
cker | +0.696 |
rito | +0.691 |
Neg logit contributions | |
cake | -0.577 |
oph | -0.571 |
cakes | -0.562 |
board | -0.497 |
amusement | -0.481 |
Token | come |
Token ID | 1282 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
amusement | +0.002 |
cakes | +0.002 |
board | +0.002 |
Neg logit contributions | |
emo | -0.002 |
eer | -0.002 |
cker | -0.002 |
rito | -0.002 |
ba | -0.002 |
Token | too |
Token ID | 1165 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
emo | +0.012 |
eer | +0.011 |
rito | +0.010 |
cker | +0.010 |
eers | +0.010 |
Neg logit contributions | |
oph | -0.005 |
cake | -0.005 |
amusement | -0.005 |
cakes | -0.005 |
Meg | -0.004 |
Token | quickly |
Token ID | 2952 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
emo | +0.131 |
rito | +0.113 |
eer | +0.112 |
ancer | +0.107 |
sailor | +0.105 |
Neg logit contributions | |
oph | -0.072 |
cake | -0.064 |
aw | -0.061 |
cakes | -0.061 |
board | -0.060 |
Token | flew |
Token ID | 13112 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
oph | +0.133 |
cake | +0.125 |
cakes | +0.121 |
board | +0.116 |
aw | +0.112 |
Neg logit contributions | |
emo | -0.180 |
eer | -0.149 |
sailor | -0.145 |
ba | -0.145 |
rito | -0.144 |
Token | down |
Token ID | 866 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
emo | +0.264 |
ba | +0.215 |
eer | +0.210 |
sailor | +0.210 |
rito | +0.206 |
Neg logit contributions | |
oph | -0.277 |
cake | -0.266 |
cakes | -0.263 |
board | -0.245 |
amusement | -0.244 |
Token | to |
Token ID | 284 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
oph | +0.005 |
cake | +0.004 |
cakes | +0.004 |
amusement | +0.004 |
board | +0.004 |
Neg logit contributions | |
emo | -0.005 |
sailor | -0.004 |
eer | -0.004 |
ba | -0.004 |
fish | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
oph | +0.024 |
cake | +0.023 |
amusement | +0.022 |
cakes | +0.022 |
board | +0.020 |
Neg logit contributions | |
emo | -0.037 |
eer | -0.031 |
cker | -0.030 |
fish | -0.030 |
ba | -0.030 |
Token | what |
Token ID | 644 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
emo | +0.151 |
cker | +0.127 |
eer | +0.124 |
rito | +0.123 |
ba | +0.121 |
Neg logit contributions | |
cake | -0.083 |
cakes | -0.081 |
oph | -0.081 |
amusement | -0.076 |
aw | -0.074 |
Token | it |
Token ID | 340 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
emo | +0.078 |
ba | +0.065 |
cker | +0.065 |
eer | +0.065 |
rito | +0.065 |
Neg logit contributions | |
cake | -0.056 |
oph | -0.056 |
cakes | -0.055 |
board | -0.049 |
amusement | -0.047 |
Token | could |
Token ID | 714 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
emo | +0.189 |
sailor | +0.160 |
eer | +0.159 |
rito | +0.154 |
cker | +0.154 |
Neg logit contributions | |
oph | -0.110 |
cake | -0.109 |
cakes | -0.108 |
board | -0.097 |
ue | -0.089 |
Token | be |
Token ID | 307 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
emo | +0.303 |
eer | +0.250 |
sailor | +0.246 |
ba | +0.242 |
rito | +0.238 |
Neg logit contributions | |
oph | -0.260 |
cake | -0.258 |
cakes | -0.250 |
board | -0.233 |
amusement | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
cake | +0.022 |
cakes | +0.021 |
oph | +0.021 |
aw | +0.019 |
board | +0.019 |
Neg logit contributions | |
emo | -0.035 |
sailor | -0.030 |
Albert | -0.029 |
eer | -0.029 |
ba | -0.029 |
Token | As |
Token ID | 1081 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
cake | +0.005 |
cakes | +0.005 |
oph | +0.004 |
board | +0.004 |
That | +0.004 |
Neg logit contributions | |
emo | -0.008 |
ba | -0.007 |
fish | -0.007 |
cker | -0.007 |
sailor | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
emo | +0.123 |
eer | +0.105 |
sailor | +0.103 |
rito | +0.102 |
cker | +0.102 |
Neg logit contributions | |
oph | -0.086 |
cake | -0.083 |
cakes | -0.080 |
board | -0.075 |
amusement | -0.073 |
Token | two |
Token ID | 734 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
oph | +0.183 |
cake | +0.182 |
cakes | +0.177 |
board | +0.166 |
amusement | +0.158 |
Neg logit contributions | |
emo | -0.238 |
sailor | -0.194 |
eer | -0.193 |
ba | -0.190 |
cker | -0.183 |
Token | best |
Token ID | 1266 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
oph | +0.348 |
cake | +0.344 |
cakes | +0.334 |
board | +0.316 |
amusement | +0.310 |
Neg logit contributions | |
emo | -0.231 |
eer | -0.179 |
sailor | -0.175 |
ba | -0.170 |
cker | -0.168 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
emo | +0.142 |
ba | +0.110 |
eer | +0.110 |
rito | +0.109 |
cker | +0.107 |
Neg logit contributions | |
oph | -0.174 |
cakes | -0.172 |
cake | -0.170 |
board | -0.161 |
amusement | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
emo | +0.124 |
eer | +0.102 |
sailor | +0.098 |
cker | +0.097 |
ba | +0.096 |
Neg logit contributions | |
oph | -0.165 |
cake | -0.163 |
cakes | -0.160 |
board | -0.145 |
uct | -0.143 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
emo | +0.056 |
eer | +0.047 |
sailor | +0.047 |
ba | +0.046 |
cker | +0.046 |
Neg logit contributions | |
oph | -0.034 |
cake | -0.033 |
cakes | -0.032 |
board | -0.029 |
amusement | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
oph | +0.441 |
cake | +0.432 |
cakes | +0.430 |
amusement | +0.388 |
board | +0.384 |
Neg logit contributions | |
emo | -0.542 |
eer | -0.464 |
cker | -0.448 |
sailor | -0.447 |
ba | -0.438 |
Token | Th |
Token ID | 536 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
oph | +0.015 |
cake | +0.014 |
cakes | +0.014 |
board | +0.012 |
amusement | +0.012 |
Neg logit contributions | |
emo | -0.029 |
eer | -0.025 |
sailor | -0.024 |
rito | -0.024 |
ba | -0.024 |
Token | alia |
Token ID | 9752 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
emo | +0.202 |
eer | +0.161 |
ba | +0.160 |
cker | +0.155 |
sailor | +0.153 |
Neg logit contributions | |
cake | -0.199 |
oph | -0.198 |
cakes | -0.196 |
amusement | -0.181 |
board | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-03 |
Pos logit contributions | |
emo | +0.050 |
eer | +0.041 |
sailor | +0.040 |
ba | +0.039 |
cker | +0.039 |
Neg logit contributions | |
oph | -0.046 |
cake | -0.045 |
cakes | -0.044 |
board | -0.040 |
amusement | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
emo | +0.001 |
eer | +0.000 |
cker | +0.000 |
gy | +0.000 |
common | +0.000 |
Neg logit contributions | |
cake | -0.001 |
cakes | -0.001 |
aw | -0.001 |
oph | -0.001 |
board | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
oph | +0.038 |
cake | +0.038 |
cakes | +0.036 |
board | +0.034 |
ue | +0.034 |
Neg logit contributions | |
emo | -0.042 |
sailor | -0.036 |
ba | -0.034 |
eer | -0.034 |
crew | -0.034 |
Token | three |
Token ID | 1115 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
oph | +0.440 |
cake | +0.427 |
cakes | +0.415 |
board | +0.385 |
amusement | +0.377 |
Neg logit contributions | |
emo | -0.479 |
eer | -0.412 |
sailor | -0.398 |
cker | -0.387 |
ba | -0.384 |
Token | went |
Token ID | 1816 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
oph | +0.010 |
cake | +0.010 |
cakes | +0.010 |
board | +0.009 |
amusement | +0.009 |
Neg logit contributions | |
emo | -0.013 |
eer | -0.011 |
sailor | -0.011 |
ba | -0.011 |
cker | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
oph | +0.002 |
cake | +0.002 |
cakes | +0.002 |
board | +0.002 |
amusement | +0.002 |
Neg logit contributions | |
emo | -0.002 |
sailor | -0.001 |
eer | -0.001 |
ba | -0.001 |
rito | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
oph | +0.028 |
cake | +0.028 |
cakes | +0.027 |
board | +0.025 |
aw | +0.024 |
Neg logit contributions | |
emo | -0.030 |
sailor | -0.025 |
eer | -0.024 |
ba | -0.024 |
cker | -0.023 |
Token | party |
Token ID | 2151 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
oph | +0.061 |
cake | +0.059 |
liv | +0.056 |
cakes | +0.056 |
uct | +0.055 |
Neg logit contributions | |
emo | -0.071 |
sailor | -0.067 |
crew | -0.065 |
sail | -0.064 |
fish | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
oph | +0.635 |
uct | +0.601 |
cake | +0.597 |
liv | +0.587 |
That | +0.585 |
Neg logit contributions | |
emo | -0.356 |
sailor | -0.315 |
crew | -0.298 |
ba | -0.287 |
fish | -0.285 |
Token | They |
Token ID | 1119 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
oph | +0.007 |
cake | +0.007 |
cakes | +0.007 |
amusement | +0.006 |
aw | +0.006 |
Neg logit contributions | |
emo | -0.008 |
sailor | -0.006 |
Albert | -0.006 |
eer | -0.006 |
ba | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
oph | +0.039 |
cake | +0.039 |
cakes | +0.037 |
board | +0.035 |
amusement | +0.034 |
Neg logit contributions | |
emo | -0.044 |
sailor | -0.037 |
ba | -0.037 |
eer | -0.036 |
fish | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
oph | +0.116 |
cake | +0.116 |
cakes | +0.111 |
board | +0.108 |
ue | +0.104 |
Neg logit contributions | |
emo | -0.117 |
sailor | -0.096 |
eer | -0.095 |
ba | -0.092 |
crew | -0.091 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
emo | +0.009 |
sailor | +0.007 |
eer | +0.007 |
ba | +0.007 |
fish | +0.007 |
Neg logit contributions | |
oph | -0.010 |
cake | -0.010 |
cakes | -0.010 |
board | -0.009 |
uct | -0.009 |
Token | could |
Token ID | 714 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
emo | +0.377 |
eer | +0.305 |
sailor | +0.299 |
ba | +0.295 |
cker | +0.291 |
Neg logit contributions | |
oph | -0.393 |
cake | -0.383 |
cakes | -0.374 |
board | -0.348 |
amusement | -0.345 |
Token | get |
Token ID | 651 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
emo | +0.327 |
eer | +0.268 |
sailor | +0.260 |
ba | +0.258 |
rito | +0.257 |
Neg logit contributions | |
oph | -0.287 |
cake | -0.283 |
cakes | -0.276 |
amusement | -0.254 |
board | -0.254 |
Token | to |
Token ID | 284 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
emo | +0.071 |
eer | +0.059 |
sailor | +0.057 |
rito | +0.057 |
cker | +0.057 |
Neg logit contributions | |
oph | -0.058 |
cake | -0.058 |
cakes | -0.057 |
amusement | -0.051 |
board | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
emo | +0.001 |
eer | +0.000 |
sailor | +0.000 |
ba | +0.000 |
cker | +0.000 |
Neg logit contributions | |
oph | -0.001 |
cake | -0.001 |
cakes | -0.001 |
board | -0.000 |
amusement | -0.000 |
Token | finish |
Token ID | 5461 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
oph | +0.004 |
cake | +0.004 |
cakes | +0.004 |
board | +0.003 |
uct | +0.003 |
Neg logit contributions | |
emo | -0.004 |
sailor | -0.003 |
eer | -0.003 |
cker | -0.003 |
ba | -0.003 |
Token | line |
Token ID | 1627 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
oph | +0.266 |
cake | +0.253 |
cakes | +0.241 |
uct | +0.219 |
amusement | +0.216 |
Neg logit contributions | |
emo | -0.321 |
sailor | -0.274 |
eer | -0.273 |
fish | -0.267 |
ba | -0.264 |
Token | first |
Token ID | 717 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
oph | +0.564 |
cake | +0.526 |
cakes | +0.512 |
amusement | +0.487 |
board | +0.473 |
Neg logit contributions | |
emo | -0.513 |
eer | -0.417 |
ba | -0.411 |
sailor | -0.411 |
fish | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
oph | +0.163 |
cake | +0.158 |
cakes | +0.155 |
board | +0.142 |
amusement | +0.141 |
Neg logit contributions | |
emo | -0.159 |
eer | -0.130 |
sailor | -0.126 |
ba | -0.125 |
cker | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
emo | +0.013 |
eer | +0.010 |
sailor | +0.010 |
ba | +0.009 |
fish | +0.009 |
Neg logit contributions | |
cake | -0.013 |
oph | -0.013 |
cakes | -0.012 |
amusement | -0.012 |
board | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
emo | +0.183 |
eer | +0.155 |
sailor | +0.151 |
cker | +0.151 |
ba | +0.149 |
Neg logit contributions | |
oph | -0.157 |
cake | -0.151 |
cakes | -0.147 |
board | -0.136 |
amusement | -0.133 |
Token | But |
Token ID | 1537 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
emo | +0.162 |
fish | +0.126 |
sailor | +0.122 |
ba | +0.120 |
Albert | +0.117 |
Neg logit contributions | |
cake | -0.181 |
cakes | -0.179 |
oph | -0.170 |
board | -0.163 |
amusement | -0.162 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
oph | +0.231 |
cake | +0.229 |
cakes | +0.225 |
board | +0.205 |
amusement | +0.204 |
Neg logit contributions | |
emo | -0.252 |
sailor | -0.205 |
ba | -0.205 |
eer | -0.204 |
cker | -0.200 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
cake | +0.114 |
cakes | +0.113 |
oph | +0.112 |
board | +0.106 |
ue | +0.101 |
Neg logit contributions | |
emo | -0.098 |
ba | -0.078 |
sailor | -0.077 |
rito | -0.076 |
eer | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
emo | +0.100 |
eer | +0.083 |
sailor | +0.082 |
ba | +0.081 |
cker | +0.079 |
Neg logit contributions | |
oph | -0.082 |
cake | -0.080 |
cakes | -0.078 |
board | -0.072 |
amusement | -0.070 |
Token | famous |
Token ID | 5863 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
emo | +0.014 |
eer | +0.011 |
ba | +0.011 |
cker | +0.011 |
rito | +0.011 |
Neg logit contributions | |
oph | -0.014 |
cake | -0.014 |
cakes | -0.013 |
amusement | -0.012 |
board | -0.012 |
Token | carpet |
Token ID | 20710 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
emo | +0.030 |
eer | +0.024 |
ba | +0.023 |
sailor | +0.023 |
cker | +0.023 |
Neg logit contributions | |
oph | -0.029 |
cake | -0.029 |
cakes | -0.028 |
board | -0.026 |
amusement | -0.026 |
Token | today |
Token ID | 1909 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
emo | +0.097 |
fish | +0.094 |
sailor | +0.092 |
ba | +0.087 |
eer | +0.085 |
Neg logit contributions | |
oph | -0.144 |
cakes | -0.125 |
liv | -0.124 |
cake | -0.124 |
uct | -0.123 |
Token | ! |
Token ID | 0 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
oph | +0.474 |
cakes | +0.454 |
cake | +0.453 |
amusement | +0.431 |
uct | +0.430 |
Neg logit contributions | |
emo | -0.407 |
fish | -0.347 |
sailor | -0.340 |
eer | -0.325 |
ba | -0.325 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
oph | +0.391 |
cake | +0.387 |
cakes | +0.385 |
amusement | +0.358 |
board | +0.352 |
Neg logit contributions | |
emo | -0.430 |
eer | -0.335 |
sailor | -0.330 |
ba | -0.326 |
Albert | -0.325 |
Token | Paul |
Token ID | 12041 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
oph | +0.174 |
cake | +0.172 |
cakes | +0.167 |
board | +0.158 |
amusement | +0.150 |
Neg logit contributions | |
emo | -0.199 |
eer | -0.165 |
cker | -0.165 |
sailor | -0.163 |
rito | -0.160 |
Token | was |
Token ID | 373 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
emo | +0.115 |
rito | +0.097 |
sailor | +0.095 |
eer | +0.094 |
crew | +0.093 |
Neg logit contributions | |
oph | -0.065 |
board | -0.058 |
cake | -0.057 |
aw | -0.054 |
cakes | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
oph | +0.057 |
cake | +0.056 |
cakes | +0.054 |
amusement | +0.050 |
board | +0.050 |
Neg logit contributions | |
emo | -0.069 |
eer | -0.058 |
rito | -0.056 |
fish | -0.056 |
sailor | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
oph | +0.376 |
cake | +0.343 |
cakes | +0.337 |
ue | +0.313 |
uct | +0.311 |
Neg logit contributions | |
emo | -0.363 |
eer | -0.305 |
sailor | -0.291 |
ba | -0.287 |
fish | -0.281 |
Token | started |
Token ID | 2067 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
oph | +0.029 |
cake | +0.028 |
cakes | +0.027 |
amusement | +0.025 |
board | +0.025 |
Neg logit contributions | |
emo | -0.031 |
eer | -0.026 |
sailor | -0.025 |
ba | -0.025 |
cker | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
oph | +0.087 |
cake | +0.084 |
cakes | +0.082 |
board | +0.076 |
amusement | +0.074 |
Neg logit contributions | |
emo | -0.086 |
eer | -0.069 |
sailor | -0.068 |
ba | -0.067 |
cker | -0.066 |
Token | fight |
Token ID | 1907 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
oph | +0.025 |
cake | +0.024 |
cakes | +0.023 |
board | +0.021 |
aw | +0.020 |
Neg logit contributions | |
emo | -0.025 |
eer | -0.020 |
sailor | -0.020 |
ba | -0.020 |
cker | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
oph | +0.347 |
cake | +0.313 |
cakes | +0.305 |
board | +0.283 |
amusement | +0.281 |
Neg logit contributions | |
emo | -0.285 |
eer | -0.216 |
ba | -0.214 |
exc | -0.206 |
sailor | -0.201 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
oph | +0.047 |
cake | +0.047 |
cakes | +0.044 |
board | +0.041 |
amusement | +0.038 |
Neg logit contributions | |
emo | -0.070 |
eer | -0.058 |
sailor | -0.058 |
ba | -0.056 |
cker | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
oph | +0.599 |
cake | +0.566 |
cakes | +0.561 |
amusement | +0.514 |
board | +0.509 |
Neg logit contributions | |
emo | -0.406 |
eer | -0.340 |
ba | -0.329 |
cker | -0.320 |
fish | -0.309 |
Token | They |
Token ID | 1119 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
oph | +0.019 |
cake | +0.018 |
amusement | +0.017 |
aw | +0.017 |
cakes | +0.017 |
Neg logit contributions | |
emo | -0.024 |
ba | -0.018 |
Albert | -0.018 |
exc | -0.018 |
cker | -0.017 |
Token | both |
Token ID | 1111 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
oph | +0.056 |
cake | +0.054 |
cakes | +0.050 |
board | +0.046 |
oga | +0.045 |
Neg logit contributions | |
emo | -0.035 |
ba | -0.032 |
cker | -0.031 |
eer | -0.031 |
exc | -0.031 |
Token | got |
Token ID | 1392 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
oph | +0.257 |
cake | +0.247 |
cakes | +0.245 |
board | +0.218 |
amusement | +0.214 |
Neg logit contributions | |
emo | -0.161 |
eer | -0.143 |
cker | -0.138 |
ba | -0.132 |
exc | -0.129 |
Token | hurt |
Token ID | 5938 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
oph | +0.050 |
cake | +0.047 |
cakes | +0.044 |
board | +0.043 |
ue | +0.042 |
Neg logit contributions | |
emo | -0.043 |
eer | -0.035 |
ba | -0.034 |
sailor | -0.034 |
cker | -0.033 |