Token | his |
Token ID | 465 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
bur | +0.117 |
ppa | +0.116 |
rying | +0.115 |
gie | +0.114 |
ior | +0.114 |
Neg logit contributions | |
vows | -0.071 |
prize | -0.067 |
great | -0.064 |
trophy | -0.062 |
are | -0.061 |
Token | head |
Token ID | 1182 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
rying | +0.044 |
bur | +0.043 |
ppa | +0.043 |
ind | +0.041 |
i | +0.041 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.031 |
trophy | -0.031 |
contest | -0.030 |
apy | -0.028 |
Token | out |
Token ID | 503 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bur | +0.025 |
rying | +0.025 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.022 |
contest | -0.021 |
trophy | -0.021 |
cakes | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
ind | +0.009 |
i | +0.009 |
Neg logit contributions | |
vows | -0.008 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ppa | +0.058 |
rying | +0.058 |
bur | +0.057 |
ety | +0.055 |
i | +0.055 |
Neg logit contributions | |
vows | -0.036 |
prize | -0.033 |
contest | -0.032 |
trophy | -0.032 |
apy | -0.030 |
Token | bur |
Token ID | 4356 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
rying | +0.066 |
bur | +0.066 |
ppa | +0.065 |
ety | +0.061 |
i | +0.060 |
Neg logit contributions | |
vows | -0.059 |
prize | -0.053 |
trophy | -0.052 |
contest | -0.051 |
apy | -0.049 |
Token | row |
Token ID | 808 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ior | +0.147 |
ety | +0.128 |
ppa | +0.128 |
Owl | +0.123 |
ind | +0.123 |
Neg logit contributions | |
ades | -0.244 |
uits | -0.239 |
vows | -0.222 |
ade | -0.217 |
are | -0.213 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
bur | +0.115 |
ppa | +0.113 |
ind | +0.113 |
rying | +0.112 |
ior | +0.111 |
Neg logit contributions | |
vows | -0.079 |
cakes | -0.069 |
contest | -0.069 |
prize | -0.069 |
case | -0.068 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
bur | +0.055 |
rying | +0.054 |
ppa | +0.053 |
ind | +0.053 |
ety | +0.051 |
Neg logit contributions | |
vows | -0.048 |
prize | -0.042 |
apy | -0.041 |
trophy | -0.041 |
contest | -0.040 |
Token | something |
Token ID | 1223 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
bur | +0.048 |
rying | +0.048 |
ppa | +0.047 |
ind | +0.045 |
ety | +0.045 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.025 |
apy | -0.025 |
Token | new |
Token ID | 649 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
vows | +0.048 |
Prize | +0.040 |
contest | +0.040 |
prize | +0.039 |
cakes | +0.039 |
Neg logit contributions | |
rying | -0.055 |
i | -0.054 |
bur | -0.054 |
ind | -0.053 |
ppa | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
bur | +0.064 |
ppa | +0.062 |
ind | +0.062 |
rying | +0.062 |
ior | +0.060 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.036 |
contest | -0.036 |
trophy | -0.035 |
joke | -0.033 |
Token | venture |
Token ID | 13189 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
vows | +0.021 |
cakes | +0.018 |
prize | +0.018 |
contest | +0.018 |
trophy | +0.018 |
Neg logit contributions | |
bur | -0.031 |
rying | -0.030 |
ppa | -0.029 |
i | -0.029 |
ind | -0.029 |
Token | out |
Token ID | 503 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ppa | +0.102 |
bur | +0.100 |
ior | +0.097 |
gie | +0.096 |
ind | +0.096 |
Neg logit contributions | |
contest | -0.061 |
prize | -0.059 |
tea | -0.058 |
vows | -0.057 |
are | -0.053 |
Token | from |
Token ID | 422 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ppa | +0.120 |
bur | +0.118 |
ior | +0.113 |
ind | +0.111 |
ety | +0.110 |
Neg logit contributions | |
contest | -0.055 |
prize | -0.052 |
are | -0.051 |
tea | -0.051 |
vows | -0.049 |
Token | his |
Token ID | 465 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ppa | +0.152 |
bur | +0.136 |
rying | +0.134 |
i | +0.134 |
ety | +0.134 |
Neg logit contributions | |
contest | -0.064 |
prize | -0.064 |
tea | -0.059 |
festival | -0.056 |
stage | -0.055 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
rying | +0.072 |
ppa | +0.071 |
bur | +0.067 |
ior | +0.066 |
cker | +0.066 |
Neg logit contributions | |
prize | -0.080 |
vows | -0.080 |
tea | -0.075 |
contest | -0.075 |
third | -0.074 |
Token | row |
Token ID | 808 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ior | +0.166 |
ppa | +0.144 |
bruised | +0.140 |
pless | +0.137 |
afar | +0.135 |
Neg logit contributions | |
ades | -0.215 |
uits | -0.209 |
ade | -0.208 |
parties | -0.189 |
br | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ior | +0.168 |
ind | +0.163 |
bur | +0.160 |
ppa | +0.159 |
gie | +0.154 |
Neg logit contributions | |
contest | -0.072 |
case | -0.070 |
uits | -0.065 |
vows | -0.063 |
cakes | -0.063 |
Token | explore |
Token ID | 7301 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ind | +0.099 |
ppa | +0.098 |
bur | +0.098 |
rying | +0.095 |
ior | +0.094 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.045 |
celebrate | -0.043 |
contest | -0.043 |
are | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ppa | +0.058 |
bur | +0.058 |
rying | +0.055 |
ety | +0.055 |
ior | +0.054 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.026 |
contest | -0.026 |
trophy | -0.024 |
are | -0.024 |
Token | forest |
Token ID | 8222 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
ppa | +0.180 |
ior | +0.167 |
owing | +0.165 |
cker | +0.164 |
rying | +0.163 |
Neg logit contributions | |
great | -0.116 |
lot | -0.115 |
funny | -0.103 |
big | -0.101 |
tea | -0.098 |
Token | who |
Token ID | 508 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
bur | +0.090 |
rying | +0.086 |
ppa | +0.084 |
ior | +0.083 |
ind | +0.080 |
Neg logit contributions | |
vows | -0.079 |
contest | -0.079 |
prize | -0.076 |
trophy | -0.075 |
case | -0.073 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
bur | +0.058 |
ppa | +0.057 |
ior | +0.057 |
gie | +0.055 |
rying | +0.055 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.044 |
prize | -0.042 |
trophy | -0.042 |
apy | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
ind | +0.010 |
i | +0.010 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
apy | -0.005 |
Token | cozy |
Token ID | 37438 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
rying | +0.082 |
ppa | +0.079 |
bur | +0.077 |
gie | +0.072 |
ener | +0.072 |
Neg logit contributions | |
vows | -0.068 |
prize | -0.063 |
contest | -0.062 |
tea | -0.061 |
trophy | -0.060 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
rying | +0.139 |
bur | +0.130 |
ppa | +0.129 |
eking | +0.122 |
ior | +0.119 |
Neg logit contributions | |
vows | -0.147 |
tea | -0.137 |
prize | -0.134 |
team | -0.133 |
lot | -0.131 |
Token | row |
Token ID | 808 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ior | +0.158 |
fred | +0.130 |
Tooth | +0.129 |
ppa | +0.127 |
shadow | +0.127 |
Neg logit contributions | |
ades | -0.234 |
vows | -0.216 |
uits | -0.215 |
ade | -0.206 |
apy | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
bur | +0.171 |
ior | +0.170 |
ppa | +0.163 |
rying | +0.159 |
gie | +0.159 |
Neg logit contributions | |
vows | -0.090 |
case | -0.085 |
contest | -0.081 |
trophy | -0.081 |
prize | -0.079 |
Token | He |
Token ID | 679 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
rying | +0.039 |
bur | +0.038 |
ppa | +0.038 |
ind | +0.036 |
i | +0.036 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
rying | +0.068 |
bur | +0.068 |
ppa | +0.065 |
ind | +0.063 |
ior | +0.062 |
Neg logit contributions | |
vows | -0.038 |
prize | -0.030 |
contest | -0.029 |
apy | -0.029 |
trophy | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
ppa | +0.063 |
rying | +0.062 |
bur | +0.061 |
cker | +0.058 |
ior | +0.058 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.040 |
trophy | -0.039 |
contest | -0.039 |
tea | -0.039 |
Token | N |
Token ID | 45 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
vows | +0.000 |
prize | +0.000 |
contest | +0.000 |
trophy | +0.000 |
cakes | +0.000 |
Neg logit contributions | |
bur | -0.000 |
rying | -0.000 |
ppa | -0.000 |
ind | -0.000 |
i | -0.000 |
Token | ina |
Token ID | 1437 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
bur | +0.035 |
rying | +0.033 |
ppa | +0.033 |
ind | +0.032 |
gie | +0.031 |
Neg logit contributions | |
vows | -0.038 |
prize | -0.033 |
trophy | -0.033 |
contest | -0.032 |
cakes | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
bur | +0.028 |
rying | +0.027 |
ppa | +0.027 |
ind | +0.026 |
i | +0.026 |
Neg logit contributions | |
vows | -0.020 |
prize | -0.017 |
contest | -0.017 |
trophy | -0.017 |
apy | -0.016 |
Token | panic |
Token ID | 13619 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
ind | +0.006 |
i | +0.006 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.005 |
cakes | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
rying | -0.001 |
bur | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | str |
Token ID | 2536 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
ior | +0.101 |
bur | +0.100 |
ppa | +0.095 |
ind | +0.094 |
gie | +0.093 |
Neg logit contributions | |
apy | -0.084 |
cakes | -0.083 |
contest | -0.079 |
vows | -0.076 |
case | -0.076 |
Token | icken |
Token ID | 5973 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ior | +0.155 |
axe | +0.147 |
oscope | +0.140 |
seen | +0.136 |
since | +0.135 |
Neg logit contributions | |
ades | -0.214 |
vows | -0.200 |
� | -0.197 |
apy | -0.188 |
ics | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
bur | +0.051 |
rying | +0.050 |
ppa | +0.050 |
ind | +0.048 |
ety | +0.047 |
Neg logit contributions | |
vows | -0.042 |
prize | -0.037 |
contest | -0.037 |
trophy | -0.036 |
cakes | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
bur | +0.044 |
rying | +0.043 |
ppa | +0.043 |
ind | +0.041 |
i | +0.040 |
Neg logit contributions | |
vows | -0.024 |
contest | -0.020 |
prize | -0.020 |
apy | -0.019 |
trophy | -0.019 |
Token | screamed |
Token ID | 25421 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
bur | +0.068 |
rying | +0.067 |
ppa | +0.065 |
ind | +0.063 |
ior | +0.061 |
Neg logit contributions | |
vows | -0.048 |
apy | -0.041 |
prize | -0.040 |
contest | -0.039 |
joke | -0.039 |
Token | for |
Token ID | 329 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
vows | +0.025 |
prize | +0.023 |
contest | +0.023 |
trophy | +0.022 |
cakes | +0.022 |
Neg logit contributions | |
rying | -0.020 |
bur | -0.019 |
ppa | -0.019 |
i | -0.019 |
ind | -0.019 |
Token | Benny |
Token ID | 44275 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bur | +0.034 |
rying | +0.034 |
ppa | +0.034 |
ind | +0.032 |
i | +0.032 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.025 |
contest | -0.024 |
trophy | -0.024 |
apy | -0.024 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
rying | +0.086 |
bur | +0.085 |
ppa | +0.082 |
ener | +0.079 |
ind | +0.079 |
Neg logit contributions | |
vows | -0.039 |
are | -0.032 |
joke | -0.031 |
contest | -0.031 |
trophy | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
bur | +0.065 |
ppa | +0.065 |
ior | +0.064 |
gie | +0.062 |
i | +0.062 |
Neg logit contributions | |
contest | -0.045 |
vows | -0.044 |
prize | -0.042 |
trophy | -0.041 |
apy | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
rying | +0.032 |
ppa | +0.032 |
bur | +0.032 |
i | +0.031 |
ind | +0.030 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.015 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | cozy |
Token ID | 37438 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
rying | +0.034 |
bur | +0.034 |
ppa | +0.033 |
i | +0.032 |
gie | +0.032 |
Neg logit contributions | |
vows | -0.019 |
contest | -0.017 |
prize | -0.017 |
trophy | -0.017 |
apy | -0.016 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
rying | +0.127 |
bur | +0.120 |
ppa | +0.117 |
eking | +0.116 |
cker | +0.110 |
Neg logit contributions | |
vows | -0.109 |
team | -0.106 |
prize | -0.106 |
tea | -0.105 |
lot | -0.104 |
Token | row |
Token ID | 808 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ior | +0.156 |
shadow | +0.140 |
ppa | +0.129 |
gie | +0.127 |
Tooth | +0.126 |
Neg logit contributions | |
ade | -0.205 |
uits | -0.204 |
ades | -0.204 |
tea | -0.195 |
parties | -0.191 |
Token | with |
Token ID | 351 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ior | +0.184 |
bur | +0.181 |
ppa | +0.175 |
gie | +0.171 |
umper | +0.167 |
Neg logit contributions | |
contest | -0.099 |
case | -0.097 |
trophy | -0.090 |
vows | -0.088 |
prize | -0.087 |
Token | his |
Token ID | 465 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
rying | +0.023 |
bur | +0.023 |
ppa | +0.023 |
ind | +0.022 |
i | +0.022 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.012 |
Token | family |
Token ID | 1641 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
rying | +0.083 |
ppa | +0.079 |
bur | +0.078 |
ior | +0.077 |
umper | +0.075 |
Neg logit contributions | |
vows | -0.051 |
prize | -0.048 |
trophy | -0.044 |
lot | -0.043 |
contest | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
rying | +0.072 |
bur | +0.072 |
ppa | +0.072 |
ior | +0.068 |
ind | +0.068 |
Neg logit contributions | |
vows | -0.045 |
trophy | -0.042 |
prize | -0.042 |
contest | -0.041 |
tea | -0.039 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.018 |
ppa | +0.017 |
i | +0.017 |
ind | +0.017 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
apy | -0.010 |
Token | called |
Token ID | 1444 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
rying | +0.097 |
ind | +0.096 |
bur | +0.094 |
ior | +0.092 |
cker | +0.091 |
Neg logit contributions | |
vows | -0.061 |
were | -0.058 |
contest | -0.057 |
cakes | -0.056 |
are | -0.056 |
Token | out |
Token ID | 503 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
vows | +0.038 |
trophy | +0.034 |
contest | +0.034 |
prize | +0.034 |
cakes | +0.033 |
Neg logit contributions | |
rying | -0.029 |
ind | -0.027 |
i | -0.027 |
bur | -0.027 |
ppa | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
bur | +0.084 |
rying | +0.082 |
ppa | +0.082 |
ind | +0.081 |
cker | +0.079 |
Neg logit contributions | |
vows | -0.019 |
apy | -0.014 |
contest | -0.013 |
prize | -0.012 |
cakes | -0.012 |
Token | Mill |
Token ID | 22603 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
ppa | +0.131 |
asured | +0.130 |
rying | +0.130 |
cker | +0.130 |
ishing | +0.127 |
Neg logit contributions | |
Everyone | -0.098 |
Happy | -0.098 |
vows | -0.094 |
were | -0.093 |
celebrate | -0.092 |
Token | ie |
Token ID | 494 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
oscope | +0.208 |
territory | +0.192 |
ior | +0.186 |
crank | +0.181 |
ringe | +0.180 |
Neg logit contributions | |
tea | -0.137 |
are | -0.134 |
were | -0.126 |
parties | -0.125 |
they | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.020 |
ind | +0.019 |
i | +0.019 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.010 |
apy | -0.010 |
Token | come |
Token ID | 1282 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
bur | +0.034 |
ppa | +0.033 |
rying | +0.033 |
ind | +0.032 |
i | +0.032 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.020 |
are | -0.020 |
Token | home |
Token ID | 1363 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ppa | +0.083 |
bur | +0.080 |
cker | +0.077 |
i | +0.076 |
ior | +0.076 |
Neg logit contributions | |
vows | -0.061 |
celebrate | -0.059 |
prize | -0.059 |
blast | -0.057 |
contest | -0.056 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
bur | +0.064 |
ppa | +0.062 |
rying | +0.060 |
cker | +0.059 |
gie | +0.059 |
Neg logit contributions | |
vows | -0.052 |
prize | -0.047 |
contest | -0.046 |
cakes | -0.045 |
trophy | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
vows | +0.028 |
prize | +0.023 |
trophy | +0.022 |
contest | +0.022 |
Prize | +0.021 |
Neg logit contributions | |
rying | -0.056 |
bur | -0.056 |
i | -0.055 |
ppa | -0.054 |
ety | -0.053 |
Token | struggling |
Token ID | 9648 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
cakes | +0.004 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.004 |
ind | -0.004 |
i | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
bur | +0.077 |
ppa | +0.076 |
ior | +0.073 |
rying | +0.071 |
ind | +0.070 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.045 |
prize | -0.045 |
trophy | -0.044 |
apy | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rying | +0.094 |
ppa | +0.093 |
bur | +0.093 |
ind | +0.091 |
i | +0.089 |
Neg logit contributions | |
vows | -0.032 |
Everyone | -0.030 |
apy | -0.030 |
cakes | -0.029 |
contest | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
rying | +0.076 |
bur | +0.074 |
ppa | +0.073 |
i | +0.072 |
ind | +0.071 |
Neg logit contributions | |
vows | -0.026 |
apy | -0.023 |
contest | -0.023 |
prize | -0.022 |
ades | -0.022 |
Token | Mill |
Token ID | 22603 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
bur | +0.058 |
rying | +0.057 |
ppa | +0.054 |
i | +0.053 |
ior | +0.053 |
Neg logit contributions | |
vows | -0.061 |
apy | -0.061 |
contest | -0.058 |
ades | -0.058 |
Everyone | -0.058 |
Token | ie |
Token ID | 494 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
property | +0.216 |
territory | +0.212 |
spine | +0.208 |
rying | +0.205 |
shadow | +0.202 |
Neg logit contributions | |
were | -0.135 |
vows | -0.126 |
are | -0.116 |
ade | -0.110 |
tea | -0.110 |
Token | tried |
Token ID | 3088 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
bur | +0.140 |
rying | +0.135 |
ind | +0.125 |
ior | +0.124 |
ppa | +0.124 |
Neg logit contributions | |
vows | -0.082 |
case | -0.072 |
contest | -0.071 |
apy | -0.071 |
were | -0.068 |
Token | to |
Token ID | 284 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
bur | +0.026 |
rying | +0.026 |
ppa | +0.026 |
ind | +0.025 |
i | +0.024 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
apy | -0.019 |
Token | reach |
Token ID | 3151 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.020 |
ind | +0.019 |
i | +0.019 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.012 |
apy | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ppa | +0.040 |
rying | +0.040 |
bur | +0.040 |
ind | +0.038 |
ior | +0.037 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.023 |
trophy | -0.022 |
apy | -0.021 |
Token | should |
Token ID | 815 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.016 |
ppa | +0.016 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | never |
Token ID | 1239 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.015 |
ppa | +0.015 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.007 |
Token | come |
Token ID | 1282 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
bur | +0.062 |
ppa | +0.061 |
rying | +0.061 |
ind | +0.060 |
ior | +0.058 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.026 |
contest | -0.025 |
joke | -0.025 |
trophy | -0.024 |
Token | close |
Token ID | 1969 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ior | +0.102 |
ppa | +0.102 |
bur | +0.097 |
i | +0.095 |
ind | +0.094 |
Neg logit contributions | |
prize | -0.063 |
vows | -0.062 |
contest | -0.060 |
join | -0.058 |
celebrate | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ppa | +0.165 |
ior | +0.162 |
cker | +0.156 |
bur | +0.155 |
gie | +0.153 |
Neg logit contributions | |
vows | -0.073 |
prize | -0.072 |
contest | -0.072 |
trophy | -0.066 |
are | -0.063 |
Token | an |
Token ID | 281 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
rying | +0.156 |
ppa | +0.154 |
bur | +0.153 |
ior | +0.151 |
ishing | +0.150 |
Neg logit contributions | |
are | -0.056 |
prize | -0.055 |
celebrate | -0.054 |
tea | -0.053 |
contest | -0.050 |
Token | owl |
Token ID | 39610 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
bur | +0.196 |
rying | +0.191 |
ishing | +0.180 |
ppa | +0.179 |
eking | +0.167 |
Neg logit contributions | |
prize | -0.203 |
idea | -0.195 |
great | -0.184 |
contest | -0.184 |
surprise | -0.181 |
Token | again |
Token ID | 757 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
bur | +0.097 |
ppa | +0.093 |
ind | +0.093 |
rying | +0.092 |
ior | +0.090 |
Neg logit contributions | |
vows | -0.071 |
contest | -0.071 |
prize | -0.071 |
trophy | -0.067 |
celebrate | -0.063 |
Token | !". |
Token ID | 48220 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
bur | +0.137 |
ppa | +0.132 |
gie | +0.131 |
ior | +0.129 |
rying | +0.128 |
Neg logit contributions | |
vows | -0.076 |
prize | -0.073 |
contest | -0.073 |
win | -0.069 |
celebrate | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
bur | +0.048 |
rying | +0.048 |
ppa | +0.047 |
ind | +0.047 |
i | +0.046 |
Neg logit contributions | |
vows | -0.022 |
contest | -0.019 |
prize | -0.019 |
cakes | -0.019 |
apy | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
i | +0.018 |
ind | +0.018 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
ppa | +0.072 |
bur | +0.072 |
rying | +0.070 |
ior | +0.069 |
ety | +0.068 |
Neg logit contributions | |
vows | -0.066 |
contest | -0.065 |
prize | -0.064 |
trophy | -0.062 |
festival | -0.058 |
Token | ?", |
Token ID | 35379 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
rying | +0.039 |
ppa | +0.039 |
bur | +0.039 |
ind | +0.038 |
i | +0.037 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.042 |
contest | -0.042 |
trophy | -0.041 |
cakes | -0.039 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
rying | +0.077 |
bur | +0.077 |
ind | +0.074 |
ppa | +0.074 |
ety | +0.071 |
Neg logit contributions | |
vows | -0.052 |
apy | -0.050 |
prize | -0.049 |
contest | -0.049 |
trophy | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
rying | +0.069 |
bur | +0.068 |
ind | +0.067 |
ppa | +0.067 |
ety | +0.064 |
Neg logit contributions | |
vows | -0.034 |
prize | -0.032 |
contest | -0.031 |
trophy | -0.030 |
apy | -0.030 |
Token | wood |
Token ID | 4898 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
rying | +0.101 |
ppa | +0.097 |
bur | +0.097 |
ind | +0.093 |
ety | +0.093 |
Neg logit contributions | |
prize | -0.063 |
contest | -0.062 |
trophy | -0.062 |
vows | -0.060 |
third | -0.056 |
Token | pe |
Token ID | 431 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
bur | +0.104 |
ind | +0.102 |
ior | +0.101 |
ety | +0.099 |
umper | +0.097 |
Neg logit contributions | |
vows | -0.124 |
trophy | -0.123 |
contest | -0.120 |
prize | -0.120 |
case | -0.117 |
Token | cker |
Token ID | 15280 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ior | +0.131 |
bur | +0.130 |
athy | +0.119 |
umper | +0.118 |
ind | +0.118 |
Neg logit contributions | |
laugh | -0.234 |
vows | -0.232 |
ves | -0.223 |
trophy | -0.220 |
ades | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
bur | +0.182 |
ind | +0.177 |
ior | +0.171 |
ppa | +0.169 |
umper | +0.168 |
Neg logit contributions | |
laugh | -0.075 |
vows | -0.074 |
trophy | -0.067 |
prize | -0.067 |
apy | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
bur | +0.025 |
rying | +0.025 |
ppa | +0.024 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
apy | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
rying | +0.037 |
bur | +0.037 |
ppa | +0.036 |
i | +0.035 |
ind | +0.035 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
apy | -0.015 |
trophy | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
bur | +0.023 |
rying | +0.022 |
ppa | +0.022 |
i | +0.021 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.013 |
apy | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ppa | +0.034 |
bur | +0.034 |
rying | +0.034 |
ind | +0.032 |
i | +0.032 |
Neg logit contributions | |
vows | -0.020 |
prize | -0.017 |
contest | -0.017 |
trophy | -0.016 |
apy | -0.016 |
Token | sunshine |
Token ID | 34488 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
ppa | +0.077 |
rying | +0.075 |
bur | +0.074 |
ety | +0.070 |
i | +0.070 |
Neg logit contributions | |
vows | -0.049 |
prize | -0.043 |
trophy | -0.042 |
contest | -0.042 |
are | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
bur | +0.030 |
rying | +0.030 |
ppa | +0.030 |
ind | +0.029 |
i | +0.028 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.021 |
cakes | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ppa | +0.117 |
rying | +0.116 |
bur | +0.114 |
ind | +0.112 |
i | +0.109 |
Neg logit contributions | |
Everyone | -0.033 |
vows | -0.033 |
apy | -0.031 |
cakes | -0.027 |
Everybody | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
rying | +0.033 |
bur | +0.033 |
ppa | +0.032 |
i | +0.032 |
ind | +0.031 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
apy | -0.013 |
trophy | -0.013 |
Token | Mill |
Token ID | 22603 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
bur | +0.062 |
rying | +0.061 |
ppa | +0.059 |
i | +0.058 |
ior | +0.058 |
Neg logit contributions | |
vows | -0.060 |
apy | -0.057 |
contest | -0.056 |
case | -0.054 |
Everyone | -0.054 |
Token | ie |
Token ID | 494 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
property | +0.216 |
territory | +0.206 |
spine | +0.205 |
rying | +0.202 |
shadow | +0.202 |
Neg logit contributions | |
were | -0.133 |
vows | -0.123 |
are | -0.113 |
ade | -0.106 |
tea | -0.106 |
Token | was |
Token ID | 373 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
bur | +0.118 |
rying | +0.112 |
ppa | +0.112 |
ior | +0.107 |
umper | +0.106 |
Neg logit contributions | |
vows | -0.075 |
contest | -0.064 |
were | -0.062 |
they | -0.061 |
apy | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
bur | +0.045 |
ppa | +0.044 |
rying | +0.044 |
ind | +0.043 |
ior | +0.042 |
Neg logit contributions | |
vows | -0.029 |
contest | -0.026 |
prize | -0.026 |
apy | -0.025 |
trophy | -0.025 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.012 |
cakes | +0.011 |
trophy | +0.011 |
contest | +0.011 |
Neg logit contributions | |
rying | -0.017 |
bur | -0.017 |
ppa | -0.017 |
i | -0.017 |
ind | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
bur | +0.076 |
ppa | +0.076 |
rying | +0.073 |
umper | +0.071 |
ind | +0.071 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.042 |
contest | -0.042 |
cakes | -0.041 |
trophy | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
bur | +0.048 |
rying | +0.048 |
i | +0.047 |
ppa | +0.047 |
ind | +0.045 |
Neg logit contributions | |
vows | -0.030 |
apy | -0.028 |
cakes | -0.027 |
case | -0.027 |
prize | -0.027 |
Token | Who |
Token ID | 8241 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
rying | +0.022 |
bur | +0.021 |
ppa | +0.021 |
i | +0.021 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.020 |
contest | -0.020 |
trophy | -0.020 |
cakes | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.020 |
cakes | +0.019 |
trophy | +0.019 |
apy | +0.019 |
Neg logit contributions | |
bur | -0.042 |
ppa | -0.041 |
rying | -0.040 |
i | -0.040 |
ind | -0.039 |
Token | there |
Token ID | 612 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
ind | +0.010 |
i | +0.010 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
apy | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
rying | +0.044 |
ppa | +0.044 |
bur | +0.043 |
ind | +0.042 |
i | +0.041 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.042 |
contest | -0.042 |
trophy | -0.041 |
are | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
rying | +0.073 |
bur | +0.071 |
ind | +0.070 |
ppa | +0.070 |
i | +0.065 |
Neg logit contributions | |
apy | -0.040 |
vows | -0.038 |
prize | -0.036 |
contest | -0.036 |
trophy | -0.036 |
Token | my |
Token ID | 1820 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ind | +0.143 |
predators | +0.141 |
rying | +0.140 |
cker | +0.136 |
property | +0.127 |
Neg logit contributions | |
laugh | -0.212 |
g | -0.208 |
joke | -0.203 |
were | -0.196 |
third | -0.196 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
bur | +0.182 |
rying | +0.179 |
ior | +0.172 |
ind | +0.171 |
property | +0.168 |
Neg logit contributions | |
g | -0.112 |
dance | -0.109 |
laugh | -0.107 |
joke | -0.107 |
cl | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
bur | +0.038 |
rying | +0.037 |
ppa | +0.037 |
ind | +0.037 |
i | +0.035 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
cakes | +0.004 |
Neg logit contributions | |
bur | -0.006 |
rying | -0.006 |
ppa | -0.006 |
i | -0.006 |
gie | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
rying | +0.049 |
bur | +0.048 |
ppa | +0.047 |
i | +0.047 |
ind | +0.046 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.018 |
contest | -0.018 |
apy | -0.017 |
cakes | -0.017 |
Token | cry |
Token ID | 3960 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
vows | +0.046 |
cakes | +0.038 |
contest | +0.037 |
prize | +0.037 |
uits | +0.037 |
Neg logit contributions | |
owl | -0.056 |
ind | -0.056 |
rying | -0.056 |
Owl | -0.055 |
gie | -0.054 |
Token | coming |
Token ID | 2406 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bur | +0.026 |
ppa | +0.026 |
rying | +0.026 |
ind | +0.025 |
i | +0.024 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
apy | -0.019 |
Token | from |
Token ID | 422 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ppa | +0.078 |
bur | +0.076 |
ishing | +0.070 |
i | +0.069 |
ind | +0.069 |
Neg logit contributions | |
vows | -0.047 |
prize | -0.044 |
contest | -0.042 |
are | -0.041 |
laugh | -0.041 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ppa | +0.113 |
ety | +0.103 |
rying | +0.103 |
bur | +0.103 |
i | +0.100 |
Neg logit contributions | |
prize | -0.055 |
contest | -0.055 |
festival | -0.051 |
trophy | -0.051 |
vows | -0.050 |
Token | his |
Token ID | 465 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
trophy | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
rying | -0.007 |
bur | -0.007 |
ppa | -0.007 |
i | -0.007 |
ind | -0.007 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
rying | +0.087 |
ppa | +0.084 |
bur | +0.082 |
cker | +0.080 |
gie | +0.077 |
Neg logit contributions | |
prize | -0.059 |
vows | -0.059 |
trophy | -0.055 |
tea | -0.053 |
case | -0.052 |
Token | row |
Token ID | 808 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ior | +0.129 |
shadow | +0.126 |
ppa | +0.126 |
afar | +0.125 |
years | +0.120 |
Neg logit contributions | |
ades | -0.188 |
ade | -0.181 |
uits | -0.180 |
br | -0.177 |
cakes | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ior | +0.137 |
bur | +0.137 |
ind | +0.136 |
ppa | +0.136 |
rying | +0.132 |
Neg logit contributions | |
case | -0.063 |
vows | -0.061 |
contest | -0.059 |
cakes | -0.057 |
prize | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
rying | +0.042 |
bur | +0.042 |
ppa | +0.041 |
ind | +0.041 |
i | +0.040 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.022 |
apy | -0.022 |
contest | -0.022 |
trophy | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
bur | +0.021 |
rying | +0.021 |
ppa | +0.021 |
i | +0.020 |
ind | +0.020 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.009 |
apy | -0.009 |
Token | He |
Token ID | 1544 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
ind | +0.006 |
i | +0.006 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.004 |
Token | fluffy |
Token ID | 39145 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rying | +0.075 |
ppa | +0.072 |
bur | +0.071 |
ind | +0.069 |
ener | +0.068 |
Neg logit contributions | |
vows | -0.037 |
apy | -0.035 |
trophy | -0.033 |
prize | -0.032 |
contest | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
rying | +0.078 |
bur | +0.077 |
ppa | +0.076 |
cker | +0.072 |
shadow | +0.070 |
Neg logit contributions | |
vows | -0.040 |
tea | -0.035 |
are | -0.034 |
tag | -0.034 |
prize | -0.034 |
Token | lived |
Token ID | 5615 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
rying | +0.035 |
bur | +0.035 |
ppa | +0.034 |
ind | +0.033 |
i | +0.033 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.019 |
apy | -0.019 |
trophy | -0.019 |
contest | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
bur | +0.035 |
ppa | +0.034 |
rying | +0.033 |
ior | +0.033 |
i | +0.033 |
Neg logit contributions | |
vows | -0.031 |
contest | -0.029 |
prize | -0.028 |
trophy | -0.028 |
apy | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
rying | +0.035 |
ppa | +0.035 |
bur | +0.035 |
i | +0.033 |
ind | +0.033 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
bur | +0.027 |
rying | +0.026 |
ppa | +0.026 |
i | +0.025 |
ind | +0.025 |
Neg logit contributions | |
vows | -0.014 |
contest | -0.012 |
prize | -0.012 |
trophy | -0.012 |
apy | -0.011 |
Token | row |
Token ID | 808 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ior | +0.152 |
shadow | +0.134 |
Tooth | +0.128 |
ppa | +0.123 |
bur | +0.120 |
Neg logit contributions | |
ade | -0.196 |
ades | -0.194 |
uits | -0.189 |
lot | -0.183 |
br | -0.183 |
Token | in |
Token ID | 287 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ior | +0.175 |
bur | +0.174 |
ppa | +0.167 |
gie | +0.160 |
ety | +0.160 |
Neg logit contributions | |
contest | -0.079 |
case | -0.077 |
vows | -0.071 |
trophy | -0.069 |
prize | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ppa | +0.070 |
rying | +0.069 |
bur | +0.066 |
i | +0.065 |
ener | +0.064 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.024 |
are | -0.023 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
rying | +0.172 |
ppa | +0.161 |
ener | +0.157 |
ishing | +0.155 |
owing | +0.155 |
Neg logit contributions | |
lot | -0.107 |
tea | -0.104 |
great | -0.104 |
third | -0.098 |
contest | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
bur | +0.095 |
ppa | +0.094 |
ior | +0.091 |
umper | +0.089 |
rying | +0.088 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.044 |
are | -0.042 |
case | -0.040 |
prize | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
rying | +0.039 |
bur | +0.039 |
ppa | +0.038 |
i | +0.038 |
ind | +0.037 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.015 |
apy | -0.015 |
trophy | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
bur | +0.046 |
rying | +0.046 |
ppa | +0.044 |
i | +0.044 |
ind | +0.043 |
Neg logit contributions | |
vows | -0.027 |
apy | -0.026 |
cakes | -0.025 |
contest | -0.025 |
prize | -0.024 |
Token | What |
Token ID | 2061 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
rying | +0.022 |
bur | +0.021 |
ppa | +0.021 |
i | +0.020 |
ind | +0.020 |
Neg logit contributions | |
vows | -0.022 |
contest | -0.020 |
prize | -0.020 |
apy | -0.020 |
trophy | -0.020 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
vows | +0.076 |
cakes | +0.064 |
prize | +0.064 |
uits | +0.063 |
contest | +0.061 |
Neg logit contributions | |
my | -0.076 |
bur | -0.070 |
ety | -0.069 |
i | -0.068 |
rying | -0.066 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
bur | +0.058 |
ppa | +0.057 |
rying | +0.056 |
ind | +0.055 |
i | +0.053 |
Neg logit contributions | |
vows | -0.040 |
contest | -0.040 |
prize | -0.040 |
trophy | -0.039 |
joke | -0.036 |
Token | Tim |
Token ID | 5045 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
rying | +0.053 |
bur | +0.053 |
ppa | +0.051 |
ind | +0.051 |
i | +0.048 |
Neg logit contributions | |
vows | -0.037 |
apy | -0.037 |
contest | -0.035 |
prize | -0.035 |
trophy | -0.034 |
Token | my |
Token ID | 1820 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
ind | +0.148 |
rying | +0.144 |
predators | +0.144 |
orns | +0.138 |
cker | +0.138 |
Neg logit contributions | |
laugh | -0.211 |
g | -0.205 |
joke | -0.201 |
third | -0.191 |
smile | -0.191 |
Token | asked |
Token ID | 1965 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
bur | +0.209 |
rying | +0.208 |
property | +0.197 |
orns | +0.193 |
ind | +0.193 |
Neg logit contributions | |
g | -0.108 |
cl | -0.108 |
laugh | -0.105 |
dance | -0.105 |
joke | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
bur | +0.046 |
rying | +0.045 |
ind | +0.044 |
ppa | +0.044 |
i | +0.042 |
Neg logit contributions | |
vows | -0.027 |
contest | -0.025 |
prize | -0.024 |
trophy | -0.024 |
apy | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
rying | +0.054 |
bur | +0.053 |
ppa | +0.052 |
i | +0.052 |
ind | +0.051 |
Neg logit contributions | |
vows | -0.022 |
contest | -0.019 |
prize | -0.019 |
apy | -0.019 |
cakes | -0.018 |
Token | mist |
Token ID | 4020 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
rying | +0.054 |
ppa | +0.053 |
bur | +0.053 |
i | +0.050 |
ety | +0.049 |
Neg logit contributions | |
vows | -0.051 |
contest | -0.047 |
prize | -0.047 |
trophy | -0.046 |
festival | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.011 |
ind | +0.010 |
i | +0.010 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.007 |
Token | into |
Token ID | 656 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
bur | +0.055 |
ppa | +0.055 |
rying | +0.054 |
ind | +0.053 |
i | +0.051 |
Neg logit contributions | |
vows | -0.044 |
contest | -0.039 |
prize | -0.039 |
apy | -0.038 |
trophy | -0.037 |
Token | their |
Token ID | 511 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.004 |
ind | +0.004 |
i | +0.004 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | cozy |
Token ID | 37438 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
bur | +0.034 |
rying | +0.034 |
ppa | +0.034 |
i | +0.031 |
gie | +0.031 |
Neg logit contributions | |
vows | -0.036 |
prize | -0.032 |
contest | -0.032 |
trophy | -0.031 |
apy | -0.030 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
ppa | +0.132 |
bur | +0.132 |
rying | +0.128 |
umper | +0.126 |
ior | +0.122 |
Neg logit contributions | |
vows | -0.114 |
tea | -0.103 |
prize | -0.100 |
dance | -0.096 |
lot | -0.096 |
Token | rows |
Token ID | 8516 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
ior | +0.151 |
ppa | +0.124 |
umper | +0.121 |
athy | +0.121 |
Tooth | +0.119 |
Neg logit contributions | |
uits | -0.218 |
ades | -0.215 |
vows | -0.205 |
apy | -0.197 |
ves | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
bur | +0.045 |
ppa | +0.044 |
rying | +0.044 |
ind | +0.043 |
ior | +0.042 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.032 |
contest | -0.032 |
trophy | -0.031 |
cakes | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.015 |
ppa | +0.015 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.007 |
Token | end |
Token ID | 886 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
bur | +0.061 |
rying | +0.061 |
ppa | +0.060 |
ior | +0.057 |
ety | +0.056 |
Neg logit contributions | |
vows | -0.053 |
prize | -0.048 |
contest | -0.047 |
trophy | -0.045 |
festival | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
trophy | +0.001 |
contest | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | able |
Token ID | 1498 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
bur | +0.030 |
rying | +0.029 |
ppa | +0.029 |
ind | +0.028 |
i | +0.028 |
Neg logit contributions | |
vows | -0.031 |
contest | -0.028 |
prize | -0.027 |
trophy | -0.027 |
apy | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
bur | +0.040 |
ppa | +0.040 |
rying | +0.039 |
ind | +0.038 |
i | +0.037 |
Neg logit contributions | |
vows | -0.034 |
prize | -0.031 |
contest | -0.030 |
trophy | -0.030 |
apy | -0.029 |
Token | escape |
Token ID | 6654 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
cakes | +0.007 |
trophy | +0.006 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.011 |
i | -0.011 |
ind | -0.011 |
Token | from |
Token ID | 422 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
bur | +0.028 |
ppa | +0.028 |
rying | +0.027 |
ind | +0.026 |
i | +0.026 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ppa | +0.094 |
bur | +0.092 |
rying | +0.091 |
ety | +0.090 |
ior | +0.089 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.049 |
contest | -0.048 |
trophy | -0.046 |
apy | -0.042 |
Token | bur |
Token ID | 4356 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
ind | +0.005 |
i | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | row |
Token ID | 808 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ior | +0.129 |
ppa | +0.119 |
ety | +0.109 |
bur | +0.108 |
Tooth | +0.105 |
Neg logit contributions | |
ades | -0.223 |
uits | -0.217 |
vows | -0.207 |
prize | -0.203 |
br | -0.203 |
Token | and |
Token ID | 290 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
bur | +0.085 |
ppa | +0.083 |
rying | +0.082 |
ind | +0.082 |
ior | +0.081 |
Neg logit contributions | |
vows | -0.066 |
prize | -0.060 |
contest | -0.060 |
trophy | -0.059 |
cakes | -0.058 |
Token | play |
Token ID | 711 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
bur | +0.041 |
rying | +0.041 |
ppa | +0.041 |
ind | +0.040 |
i | +0.039 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.025 |
contest | -0.024 |
trophy | -0.024 |
apy | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
vows | +0.067 |
cakes | +0.057 |
apy | +0.055 |
Prize | +0.055 |
trophy | +0.055 |
Neg logit contributions | |
rying | -0.049 |
bur | -0.044 |
ind | -0.043 |
ppa | -0.042 |
i | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
vows | +0.016 |
cakes | +0.014 |
prize | +0.013 |
contest | +0.013 |
trophy | +0.013 |
Neg logit contributions | |
bur | -0.018 |
rying | -0.017 |
ppa | -0.016 |
ind | -0.016 |
i | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
apy | -0.004 |
Token | One |
Token ID | 1881 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
rying | +0.085 |
ppa | +0.083 |
ind | +0.080 |
bur | +0.078 |
i | +0.077 |
Neg logit contributions | |
vows | -0.042 |
prize | -0.037 |
contest | -0.036 |
are | -0.036 |
Everyone | -0.036 |
Token | day |
Token ID | 1110 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
rying | +0.086 |
ppa | +0.084 |
bur | +0.080 |
ind | +0.079 |
ener | +0.078 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.040 |
contest | -0.039 |
joke | -0.038 |
trophy | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bur | +0.004 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.003 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | Stri |
Token ID | 26137 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
rying | +0.056 |
ppa | +0.053 |
ind | +0.053 |
bur | +0.052 |
cker | +0.050 |
Neg logit contributions | |
vows | -0.044 |
apy | -0.042 |
prize | -0.041 |
contest | -0.041 |
are | -0.039 |
Token | pe |
Token ID | 431 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
rying | +0.063 |
ind | +0.058 |
ety | +0.058 |
ppa | +0.058 |
bur | +0.057 |
Neg logit contributions | |
vows | -0.061 |
prize | -0.056 |
ves | -0.055 |
ades | -0.055 |
contest | -0.054 |
Token | y |
Token ID | 88 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ior | +0.169 |
rying | +0.167 |
Owl | +0.167 |
ppa | +0.164 |
Tooth | +0.163 |
Neg logit contributions | |
were | -0.187 |
are | -0.182 |
vows | -0.182 |
ades | -0.169 |
joke | -0.166 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
rying | +0.141 |
bur | +0.134 |
ind | +0.129 |
ppa | +0.127 |
ishing | +0.124 |
Neg logit contributions | |
vows | -0.071 |
case | -0.067 |
contest | -0.064 |
ves | -0.062 |
prize | -0.061 |
Token | his |
Token ID | 465 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
rying | +0.144 |
ppa | +0.133 |
ener | +0.132 |
ior | +0.131 |
ind | +0.131 |
Neg logit contributions | |
apy | -0.024 |
vows | -0.021 |
prize | -0.021 |
tea | -0.021 |
contest | -0.020 |
Token | friend |
Token ID | 1545 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
rying | +0.046 |
ppa | +0.045 |
bur | +0.044 |
ior | +0.042 |
ind | +0.041 |
Neg logit contributions | |
vows | -0.038 |
prize | -0.036 |
trophy | -0.033 |
contest | -0.033 |
joke | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
rying | +0.043 |
bur | +0.042 |
ppa | +0.042 |
ind | +0.042 |
i | +0.039 |
Neg logit contributions | |
vows | -0.028 |
contest | -0.025 |
prize | -0.025 |
trophy | -0.024 |
cakes | -0.023 |
Token | iver |
Token ID | 1428 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
bur | +0.074 |
ior | +0.073 |
ener | +0.073 |
ppa | +0.072 |
gie | +0.069 |
Neg logit contributions | |
ades | -0.082 |
apy | -0.079 |
case | -0.078 |
vows | -0.077 |
contest | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
bur | +0.017 |
ppa | +0.017 |
rying | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
apy | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ppa | +0.114 |
bur | +0.114 |
rying | +0.114 |
ind | +0.112 |
i | +0.107 |
Neg logit contributions | |
Everyone | -0.035 |
vows | -0.035 |
apy | -0.033 |
cakes | -0.030 |
Everybody | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
ind | +0.006 |
i | +0.006 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
rying | +0.072 |
bur | +0.070 |
ppa | +0.069 |
i | +0.069 |
ind | +0.068 |
Neg logit contributions | |
vows | -0.025 |
apy | -0.021 |
contest | -0.021 |
prize | -0.021 |
ades | -0.020 |
Token | Mill |
Token ID | 22603 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
bur | +0.056 |
rying | +0.054 |
ppa | +0.052 |
i | +0.052 |
ior | +0.050 |
Neg logit contributions | |
vows | -0.054 |
apy | -0.051 |
contest | -0.048 |
cakes | -0.048 |
Everyone | -0.048 |
Token | ie |
Token ID | 494 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
property | +0.205 |
territory | +0.197 |
spine | +0.190 |
rying | +0.186 |
wood | +0.185 |
Neg logit contributions | |
were | -0.139 |
vows | -0.129 |
are | -0.117 |
danced | -0.110 |
tea | -0.108 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
bur | +0.143 |
rying | +0.137 |
ind | +0.132 |
ppa | +0.130 |
umper | +0.129 |
Neg logit contributions | |
vows | -0.081 |
apy | -0.066 |
were | -0.065 |
joke | -0.065 |
case | -0.065 |
Token | too |
Token ID | 1165 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
bur | +0.067 |
rying | +0.065 |
ppa | +0.065 |
ior | +0.064 |
ety | +0.063 |
Neg logit contributions | |
vows | -0.049 |
apy | -0.043 |
contest | -0.043 |
prize | -0.042 |
laugh | -0.042 |
Token | curious |
Token ID | 11040 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
bur | +0.095 |
rying | +0.089 |
ppa | +0.088 |
ior | +0.086 |
oscope | +0.086 |
Neg logit contributions | |
apy | -0.060 |
vows | -0.054 |
great | -0.054 |
laugh | -0.053 |
lot | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
bur | +0.049 |
ppa | +0.049 |
rying | +0.048 |
ind | +0.046 |
cker | +0.045 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.032 |
contest | -0.031 |
trophy | -0.030 |
cakes | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
vows | +0.032 |
trophy | +0.027 |
prize | +0.027 |
apy | +0.026 |
cakes | +0.026 |
Neg logit contributions | |
rying | -0.035 |
i | -0.034 |
bur | -0.034 |
ppa | -0.034 |
ind | -0.032 |
Token | friendly |
Token ID | 8030 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
bur | +0.077 |
rying | +0.075 |
ppa | +0.075 |
ety | +0.071 |
ior | +0.070 |
Neg logit contributions | |
vows | -0.065 |
contest | -0.062 |
prize | -0.061 |
joke | -0.058 |
lot | -0.057 |
Token | ducks |
Token ID | 39694 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.019 |
contest | -0.019 |
trophy | -0.019 |
cakes | -0.018 |
Token | came |
Token ID | 1625 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.019 |
i | +0.018 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ppa | +0.038 |
bur | +0.037 |
rying | +0.035 |
ior | +0.035 |
ind | +0.034 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.031 |
contest | -0.031 |
trophy | -0.030 |
apy | -0.029 |
Token | Gig |
Token ID | 19525 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
rying | +0.028 |
bur | +0.028 |
ppa | +0.028 |
ind | +0.027 |
i | +0.027 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.019 |
contest | -0.019 |
trophy | -0.018 |
cakes | -0.018 |
Token | i |
Token ID | 72 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
asured | +0.113 |
oscope | +0.112 |
property | +0.103 |
axe | +0.102 |
beh | +0.095 |
Neg logit contributions | |
vows | -0.233 |
tea | -0.209 |
they | -0.206 |
are | -0.204 |
were | -0.202 |
Token | 's |
Token ID | 338 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
bur | +0.064 |
ppa | +0.063 |
rying | +0.062 |
ind | +0.061 |
ior | +0.060 |
Neg logit contributions | |
vows | -0.053 |
prize | -0.048 |
contest | -0.047 |
trophy | -0.047 |
are | -0.046 |
Token | rescue |
Token ID | 9992 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ppa | +0.054 |
bur | +0.053 |
rying | +0.052 |
i | +0.049 |
umper | +0.049 |
Neg logit contributions | |
vows | -0.055 |
prize | -0.050 |
contest | -0.048 |
trophy | -0.047 |
joke | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bur | +0.041 |
rying | +0.040 |
ppa | +0.040 |
ind | +0.039 |
ety | +0.038 |
Neg logit contributions | |
vows | -0.031 |
prize | -0.028 |
contest | -0.027 |
trophy | -0.026 |
cakes | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
rying | +0.050 |
bur | +0.050 |
ppa | +0.049 |
ind | +0.048 |
i | +0.046 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.038 |
cakes | -0.037 |
contest | -0.037 |
apy | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
rying | +0.093 |
bur | +0.093 |
cker | +0.091 |
ppa | +0.090 |
ind | +0.090 |
Neg logit contributions | |
vows | -0.046 |
prize | -0.039 |
are | -0.038 |
contest | -0.037 |
tea | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
bur | +0.076 |
rying | +0.075 |
ind | +0.075 |
ppa | +0.074 |
i | +0.073 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.013 |
apy | -0.013 |
Token | What |
Token ID | 2061 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
rying | +0.147 |
ior | +0.145 |
ishing | +0.145 |
owing | +0.144 |
asured | +0.143 |
Neg logit contributions | |
Mine | -0.085 |
vows | -0.079 |
Me | -0.078 |
tag | -0.077 |
contest | -0.076 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
vows | +0.030 |
prize | +0.026 |
cakes | +0.026 |
contest | +0.026 |
trophy | +0.026 |
Neg logit contributions | |
bur | -0.031 |
ppa | -0.030 |
i | -0.030 |
rying | -0.029 |
ety | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
bur | +0.093 |
ppa | +0.093 |
rying | +0.089 |
ind | +0.088 |
ior | +0.087 |
Neg logit contributions | |
contest | -0.051 |
vows | -0.050 |
prize | -0.049 |
trophy | -0.048 |
joke | -0.045 |
Token | Gig |
Token ID | 19525 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
rying | +0.035 |
bur | +0.034 |
ppa | +0.033 |
ind | +0.032 |
cker | +0.032 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.041 |
trophy | -0.039 |
contest | -0.039 |
cakes | -0.038 |
Token | i |
Token ID | 72 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
oscope | +0.117 |
keeping | +0.109 |
rying | +0.105 |
umbling | +0.103 |
property | +0.100 |
Neg logit contributions | |
vows | -0.229 |
are | -0.204 |
they | -0.196 |
tea | -0.195 |
were | -0.193 |
Token | ? |
Token ID | 30 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
bur | +0.109 |
rying | +0.105 |
ind | +0.103 |
ppa | +0.103 |
ior | +0.102 |
Neg logit contributions | |
vows | -0.085 |
contest | -0.084 |
are | -0.084 |
prize | -0.078 |
trophy | -0.078 |
Token | Are |
Token ID | 4231 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
bur | +0.080 |
rying | +0.079 |
ppa | +0.076 |
ind | +0.075 |
i | +0.074 |
Neg logit contributions | |
vows | -0.056 |
apy | -0.052 |
cakes | -0.050 |
contest | -0.049 |
case | -0.049 |
Token | you |
Token ID | 345 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
rying | +0.074 |
bur | +0.072 |
ind | +0.071 |
ior | +0.070 |
cker | +0.069 |
Neg logit contributions | |
vows | -0.056 |
contest | -0.053 |
prize | -0.053 |
are | -0.052 |
trophy | -0.052 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ior | +0.099 |
bur | +0.098 |
rying | +0.096 |
ind | +0.094 |
ppa | +0.092 |
Neg logit contributions | |
vows | -0.076 |
are | -0.074 |
apy | -0.074 |
prize | -0.073 |
celebrate | -0.073 |
Token | were |
Token ID | 547 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
vows | +0.059 |
Prize | +0.050 |
prize | +0.050 |
trophy | +0.049 |
contest | +0.047 |
Neg logit contributions | |
i | -0.113 |
bur | -0.110 |
my | -0.109 |
rying | -0.106 |
ppa | -0.106 |
Token | so |
Token ID | 523 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
vows | +0.062 |
apy | +0.056 |
trophy | +0.056 |
prize | +0.056 |
Prize | +0.056 |
Neg logit contributions | |
bur | -0.070 |
i | -0.068 |
ppa | -0.067 |
ind | -0.066 |
rying | -0.066 |
Token | colorful |
Token ID | 20239 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Prize | +0.096 |
mat | +0.096 |
vows | +0.096 |
trophy | +0.096 |
prize | +0.095 |
Neg logit contributions | |
ind | -0.105 |
i | -0.094 |
my | -0.093 |
ppa | -0.087 |
ety | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
vows | +0.068 |
apy | +0.061 |
Prize | +0.060 |
contest | +0.060 |
trophy | +0.060 |
Neg logit contributions | |
i | -0.045 |
rying | -0.045 |
bur | -0.044 |
ind | -0.042 |
ppa | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
vows | +0.031 |
prize | +0.027 |
contest | +0.027 |
trophy | +0.026 |
ades | +0.026 |
Neg logit contributions | |
bur | -0.045 |
ppa | -0.044 |
rying | -0.044 |
i | -0.044 |
ind | -0.043 |
Token | stories |
Token ID | 3923 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
cakes | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Prize | +0.187 |
vows | +0.183 |
coach | +0.181 |
ades | +0.179 |
apy | +0.174 |
Neg logit contributions | |
my | -0.160 |
i | -0.150 |
since | -0.147 |
bur | -0.142 |
owl | -0.142 |
Token | so |
Token ID | 523 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
vows | +0.056 |
apy | +0.051 |
contest | +0.051 |
Prize | +0.051 |
trophy | +0.050 |
Neg logit contributions | |
bur | -0.065 |
i | -0.062 |
rying | -0.061 |
ppa | -0.061 |
ind | -0.060 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
vows | +0.092 |
Prize | +0.092 |
trophy | +0.091 |
contest | +0.091 |
prize | +0.091 |
Neg logit contributions | |
ind | -0.105 |
i | -0.095 |
my | -0.091 |
ppa | -0.088 |
rying | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
vows | +0.059 |
apy | +0.053 |
trophy | +0.052 |
Prize | +0.052 |
contest | +0.052 |
Neg logit contributions | |
rying | -0.046 |
bur | -0.044 |
i | -0.043 |
ind | -0.042 |
ppa | -0.041 |
Token | She |
Token ID | 1375 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.006 |
trophy | +0.005 |
contest | +0.005 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.010 |
rying | -0.010 |
ppa | -0.010 |
i | -0.009 |
ind | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
vows | +0.010 |
prize | +0.009 |
contest | +0.009 |
trophy | +0.009 |
apy | +0.009 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.009 |
ppa | -0.009 |
i | -0.009 |
ind | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
trophy | +0.010 |
contest | +0.010 |
cakes | +0.009 |
Neg logit contributions | |
bur | -0.016 |
rying | -0.015 |
ppa | -0.015 |
ind | -0.015 |
i | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
vows | +0.042 |
prize | +0.037 |
trophy | +0.036 |
contest | +0.036 |
tea | +0.035 |
Neg logit contributions | |
bur | -0.037 |
ind | -0.035 |
rying | -0.035 |
my | -0.034 |
ppa | -0.034 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
apy | +0.075 |
vows | +0.070 |
ades | +0.065 |
� | +0.064 |
Mine | +0.064 |
Neg logit contributions | |
bur | -0.038 |
ppa | -0.038 |
ind | -0.037 |
owl | -0.037 |
my | -0.037 |
Token | played |
Token ID | 2826 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
vows | +0.072 |
prize | +0.065 |
apy | +0.065 |
ades | +0.064 |
trophy | +0.064 |
Neg logit contributions | |
i | -0.075 |
rying | -0.074 |
bur | -0.072 |
ppa | -0.071 |
my | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
vows | +0.174 |
apy | +0.161 |
cakes | +0.153 |
Mine | +0.153 |
� | +0.150 |
Neg logit contributions | |
rying | -0.109 |
asking | -0.101 |
ishing | -0.099 |
forth | -0.097 |
ting | -0.094 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
apy | +0.159 |
vows | +0.149 |
cakes | +0.148 |
� | +0.146 |
Both | +0.141 |
Neg logit contributions | |
ind | -0.208 |
nie | -0.167 |
rying | -0.165 |
ppa | -0.163 |
ich | -0.159 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
vows | +0.062 |
apy | +0.055 |
Mine | +0.053 |
trophy | +0.052 |
prize | +0.051 |
Neg logit contributions | |
rying | -0.042 |
bur | -0.041 |
ppa | -0.039 |
i | -0.039 |
ind | -0.039 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
vows | +0.067 |
apy | +0.058 |
cakes | +0.054 |
� | +0.053 |
coach | +0.049 |
Neg logit contributions | |
rying | -0.102 |
ind | -0.101 |
ishing | -0.097 |
my | -0.097 |
ior | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
vows | +0.091 |
Mine | +0.078 |
cakes | +0.072 |
trophy | +0.071 |
apy | +0.071 |
Neg logit contributions | |
rying | -0.094 |
ind | -0.088 |
i | -0.087 |
ishing | -0.087 |
ise | -0.086 |
Token | interesting |
Token ID | 3499 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
vows | +0.021 |
trophy | +0.019 |
prize | +0.019 |
ades | +0.019 |
contest | +0.018 |
Neg logit contributions | |
bur | -0.026 |
rying | -0.026 |
i | -0.026 |
ppa | -0.025 |
ind | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
vows | +0.067 |
Prize | +0.062 |
contest | +0.061 |
prize | +0.060 |
trophy | +0.059 |
Neg logit contributions | |
bur | -0.074 |
i | -0.073 |
ppa | -0.072 |
ind | -0.070 |
rying | -0.068 |
Token | funny |
Token ID | 8258 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
vows | +0.060 |
cakes | +0.054 |
Prize | +0.053 |
contest | +0.053 |
uits | +0.052 |
Neg logit contributions | |
ind | -0.088 |
ppa | -0.086 |
bur | -0.085 |
cker | -0.084 |
i | -0.082 |
Token | face |
Token ID | 1986 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
vows | +0.061 |
contest | +0.056 |
Prize | +0.055 |
cakes | +0.054 |
uits | +0.053 |
Neg logit contributions | |
i | -0.071 |
bur | -0.070 |
ind | -0.070 |
cker | -0.070 |
ppa | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
vows | +0.042 |
prize | +0.038 |
contest | +0.037 |
Prize | +0.037 |
trophy | +0.037 |
Neg logit contributions | |
rying | -0.035 |
bur | -0.035 |
i | -0.035 |
ppa | -0.035 |
ind | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
trophy | +0.084 |
prize | +0.081 |
contest | +0.081 |
ades | +0.079 |
vows | +0.079 |
Neg logit contributions | |
ior | -0.072 |
ety | -0.063 |
gie | -0.062 |
i | -0.062 |
ind | -0.061 |
Token | sandwiches |
Token ID | 29777 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
vows | +0.022 |
apy | +0.019 |
contest | +0.019 |
Prize | +0.018 |
prize | +0.018 |
Neg logit contributions | |
bur | -0.036 |
ppa | -0.035 |
i | -0.034 |
rying | -0.034 |
ind | -0.034 |
Token | are |
Token ID | 389 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Prize | +0.156 |
igsaw | +0.151 |
vows | +0.150 |
ival | +0.148 |
ades | +0.135 |
Neg logit contributions | |
forth | -0.195 |
i | -0.192 |
my | -0.186 |
bur | -0.182 |
bruised | -0.173 |
Token | spicy |
Token ID | 26880 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
vows | +0.037 |
contest | +0.033 |
Prize | +0.033 |
prize | +0.032 |
trophy | +0.031 |
Neg logit contributions | |
bur | -0.045 |
ppa | -0.043 |
i | -0.043 |
rying | -0.043 |
ind | -0.042 |
Token | ! |
Token ID | 0 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
vows | +0.022 |
contest | +0.019 |
prize | +0.019 |
trophy | +0.019 |
apy | +0.019 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
i | -0.018 |
ppa | -0.018 |
ind | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
vows | +0.085 |
prize | +0.084 |
trophy | +0.084 |
contest | +0.083 |
ades | +0.076 |
Neg logit contributions | |
ior | -0.084 |
ppa | -0.074 |
ety | -0.074 |
bur | -0.074 |
ind | -0.072 |
Token | have |
Token ID | 423 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
vows | +0.074 |
cakes | +0.072 |
ades | +0.072 |
contest | +0.068 |
Prize | +0.065 |
Neg logit contributions | |
i | -0.111 |
bur | -0.108 |
cker | -0.105 |
ppa | -0.103 |
rying | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
vows | +0.033 |
prize | +0.029 |
trophy | +0.028 |
contest | +0.027 |
cakes | +0.026 |
Neg logit contributions | |
bur | -0.036 |
ppa | -0.035 |
rying | -0.034 |
ind | -0.033 |
ety | -0.033 |
Token | Da |
Token ID | 26531 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
vows | +0.053 |
prize | +0.047 |
trophy | +0.046 |
contest | +0.044 |
cakes | +0.043 |
Neg logit contributions | |
ppa | -0.042 |
ind | -0.040 |
bur | -0.040 |
rying | -0.040 |
ety | -0.038 |
Token | isy |
Token ID | 13560 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
bur | +0.028 |
rying | +0.027 |
ppa | +0.026 |
ind | +0.025 |
i | +0.025 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.025 |
cakes | -0.025 |
Token | started |
Token ID | 2067 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
vows | +0.057 |
prize | +0.054 |
trophy | +0.053 |
cakes | +0.053 |
contest | +0.053 |
Neg logit contributions | |
i | -0.057 |
ppa | -0.055 |
rying | -0.055 |
bur | -0.054 |
ind | -0.053 |
Token | making |
Token ID | 1642 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
vows | +0.064 |
cakes | +0.060 |
trophy | +0.059 |
prize | +0.059 |
ades | +0.059 |
Neg logit contributions | |
rying | -0.041 |
i | -0.040 |
ind | -0.039 |
bur | -0.039 |
ppa | -0.037 |
Token | videos |
Token ID | 5861 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
vows | +0.091 |
trophy | +0.081 |
Prize | +0.080 |
cakes | +0.080 |
case | +0.079 |
Neg logit contributions | |
i | -0.092 |
ind | -0.088 |
rying | -0.087 |
bur | -0.085 |
ppa | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
vows | +0.268 |
Mine | +0.241 |
apy | +0.239 |
Prize | +0.230 |
ades | +0.226 |
Neg logit contributions | |
my | -0.114 |
owl | -0.098 |
since | -0.093 |
rying | -0.093 |
ting | -0.090 |
Token | put |
Token ID | 1234 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
trophy | +0.019 |
contest | +0.019 |
ades | +0.019 |
Neg logit contributions | |
rying | -0.024 |
bur | -0.024 |
ppa | -0.023 |
i | -0.023 |
ind | -0.023 |
Token | them |
Token ID | 606 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
vows | +0.050 |
apy | +0.044 |
trophy | +0.043 |
Prize | +0.043 |
prize | +0.043 |
Neg logit contributions | |
bur | -0.059 |
i | -0.056 |
ppa | -0.056 |
rying | -0.056 |
ind | -0.055 |
Token | up |
Token ID | 510 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
vows | +0.123 |
Prize | +0.113 |
apy | +0.112 |
Mine | +0.111 |
cakes | +0.111 |
Neg logit contributions | |
rying | -0.087 |
bur | -0.085 |
i | -0.080 |
ppa | -0.079 |
ind | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.016 |
trophy | +0.016 |
cakes | +0.016 |
contest | +0.016 |
Neg logit contributions | |
bur | -0.017 |
rying | -0.017 |
ppa | -0.016 |
i | -0.016 |
ind | -0.016 |
Token | characters |
Token ID | 3435 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.031 |
ades | +0.024 |
cakes | +0.024 |
uits | +0.023 |
Neg logit contributions | |
bur | -0.063 |
ind | -0.062 |
rying | -0.061 |
my | -0.061 |
gie | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
vows | +0.138 |
ades | +0.125 |
apy | +0.125 |
Prize | +0.121 |
Mine | +0.120 |
Neg logit contributions | |
rying | -0.092 |
i | -0.091 |
bur | -0.085 |
ppa | -0.081 |
my | -0.080 |
Token | watching |
Token ID | 4964 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
contest | +0.006 |
trophy | +0.006 |
cakes | +0.006 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
i | -0.007 |
ind | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
vows | +0.095 |
apy | +0.087 |
Prize | +0.085 |
prize | +0.084 |
case | +0.084 |
Neg logit contributions | |
i | -0.102 |
ind | -0.101 |
rying | -0.097 |
my | -0.096 |
bur | -0.095 |
Token | funny |
Token ID | 8258 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
apy | +0.052 |
vows | +0.052 |
uits | +0.044 |
ades | +0.041 |
ves | +0.039 |
Neg logit contributions | |
ind | -0.098 |
my | -0.095 |
bur | -0.093 |
rying | -0.090 |
owl | -0.090 |
Token | video |
Token ID | 2008 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
apy | +0.075 |
vows | +0.072 |
uits | +0.071 |
case | +0.065 |
Prize | +0.064 |
Neg logit contributions | |
ind | -0.116 |
my | -0.111 |
i | -0.111 |
ping | -0.110 |
gie | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
vows | +0.232 |
apy | +0.215 |
Mine | +0.209 |
Prize | +0.208 |
disco | +0.204 |
Neg logit contributions | |
my | -0.124 |
rying | -0.122 |
i | -0.119 |
forth | -0.112 |
ting | -0.108 |
Token | She |
Token ID | 1375 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
vows | +0.047 |
trophy | +0.044 |
prize | +0.043 |
ades | +0.042 |
contest | +0.041 |
Neg logit contributions | |
bur | -0.044 |
my | -0.043 |
ety | -0.043 |
i | -0.043 |
rying | -0.042 |
Token | went |
Token ID | 1816 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.031 |
contest | +0.031 |
cakes | +0.030 |
apy | +0.030 |
Neg logit contributions | |
bur | -0.032 |
i | -0.031 |
ppa | -0.031 |
rying | -0.031 |
ind | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
vows | +0.033 |
apy | +0.030 |
trophy | +0.029 |
prize | +0.029 |
contest | +0.029 |
Neg logit contributions | |
rying | -0.022 |
bur | -0.021 |
ppa | -0.020 |
ind | -0.020 |
i | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
vows | +0.044 |
ades | +0.040 |
cakes | +0.040 |
apy | +0.039 |
ves | +0.035 |
Neg logit contributions | |
bur | -0.050 |
rying | -0.049 |
i | -0.047 |
ind | -0.047 |
my | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.005 |
contest | +0.005 |
trophy | +0.005 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
i | -0.008 |
ety | -0.008 |
Token | played |
Token ID | 2826 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
vows | +0.048 |
prize | +0.046 |
contest | +0.045 |
trophy | +0.045 |
apy | +0.045 |
Neg logit contributions | |
ppa | -0.037 |
i | -0.037 |
bur | -0.036 |
rying | -0.035 |
ind | -0.034 |
Token | games |
Token ID | 1830 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
vows | +0.179 |
apy | +0.154 |
Mine | +0.148 |
cakes | +0.147 |
Prize | +0.146 |
Neg logit contributions | |
owl | -0.089 |
asking | -0.087 |
rying | -0.085 |
forth | -0.083 |
ishing | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
vows | +0.183 |
apy | +0.173 |
Mine | +0.161 |
ades | +0.161 |
Sorry | +0.159 |
Neg logit contributions | |
my | -0.078 |
rying | -0.069 |
owl | -0.068 |
since | -0.067 |
bur | -0.065 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
vows | +0.016 |
prize | +0.014 |
trophy | +0.014 |
ades | +0.014 |
contest | +0.014 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.019 |
i | -0.018 |
ind | -0.018 |
Token | videos |
Token ID | 5861 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
vows | +0.095 |
Prize | +0.088 |
case | +0.083 |
ades | +0.082 |
� | +0.081 |
Neg logit contributions | |
ind | -0.073 |
rying | -0.072 |
asking | -0.071 |
i | -0.071 |
ting | -0.070 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
vows | +0.257 |
apy | +0.241 |
Mine | +0.233 |
ades | +0.222 |
Prize | +0.220 |
Neg logit contributions | |
my | -0.105 |
ting | -0.101 |
since | -0.088 |
forth | -0.085 |
owl | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
vows | +0.065 |
apy | +0.058 |
ades | +0.057 |
Prize | +0.056 |
cakes | +0.056 |
Neg logit contributions | |
ind | -0.053 |
bur | -0.052 |
i | -0.051 |
ppa | -0.049 |
my | -0.048 |
Token | computer |
Token ID | 3644 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
vows | +0.026 |
apy | +0.023 |
prize | +0.022 |
contest | +0.021 |
Prize | +0.021 |
Neg logit contributions | |
ind | -0.034 |
bur | -0.034 |
rying | -0.034 |
ppa | -0.033 |
ior | -0.032 |
Token | all |
Token ID | 477 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
vows | +0.125 |
apy | +0.115 |
ades | +0.109 |
prize | +0.106 |
Prize | +0.105 |
Neg logit contributions | |
my | -0.088 |
rying | -0.088 |
i | -0.083 |
bur | -0.083 |
forth | -0.079 |
Token | day |
Token ID | 1110 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.013 |
i | +0.013 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.011 |
Token | cheered |
Token ID | 34767 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
vows | +0.059 |
ades | +0.056 |
prize | +0.054 |
contest | +0.053 |
cakes | +0.053 |
Neg logit contributions | |
i | -0.061 |
bur | -0.057 |
ppa | -0.057 |
forth | -0.057 |
rying | -0.057 |
Token | very |
Token ID | 845 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
vows | +0.096 |
apy | +0.091 |
cakes | +0.090 |
case | +0.090 |
Prize | +0.089 |
Neg logit contributions | |
rying | -0.049 |
i | -0.047 |
ind | -0.045 |
my | -0.041 |
forth | -0.041 |
Token | loudly |
Token ID | 23112 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
cakes | +0.099 |
� | +0.095 |
vows | +0.094 |
uits | +0.092 |
Mine | +0.091 |
Neg logit contributions | |
ind | -0.118 |
i | -0.110 |
rying | -0.110 |
ppa | -0.103 |
aware | -0.096 |
Token | because |
Token ID | 780 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
vows | +0.077 |
apy | +0.073 |
trophy | +0.071 |
ades | +0.070 |
prize | +0.070 |
Neg logit contributions | |
rying | -0.055 |
i | -0.051 |
ind | -0.049 |
bur | -0.048 |
gie | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
vows | +0.038 |
ades | +0.029 |
prize | +0.027 |
Prize | +0.027 |
cakes | +0.027 |
Neg logit contributions | |
bur | -0.073 |
rying | -0.071 |
my | -0.071 |
ind | -0.070 |
owl | -0.069 |
Token | dance |
Token ID | 9280 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
vows | +0.080 |
apy | +0.079 |
ades | +0.074 |
cakes | +0.073 |
uits | +0.067 |
Neg logit contributions | |
owl | -0.098 |
rying | -0.096 |
my | -0.094 |
forth | -0.093 |
ind | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
vows | +0.185 |
apy | +0.180 |
Mine | +0.174 |
ades | +0.169 |
uits | +0.163 |
Neg logit contributions | |
rying | -0.143 |
i | -0.143 |
ting | -0.133 |
my | -0.132 |
row | -0.131 |
Token | so |
Token ID | 523 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
vows | +0.076 |
cakes | +0.067 |
Mine | +0.066 |
apy | +0.066 |
prize | +0.066 |
Neg logit contributions | |
bur | -0.063 |
rying | -0.062 |
my | -0.057 |
ppa | -0.057 |
i | -0.056 |
Token | good |
Token ID | 922 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
vows | +0.110 |
� | +0.108 |
tray | +0.105 |
mat | +0.100 |
prize | +0.099 |
Neg logit contributions | |
ind | -0.095 |
rying | -0.087 |
ety | -0.086 |
aware | -0.083 |
my | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
vows | +0.051 |
apy | +0.046 |
Mine | +0.044 |
prize | +0.044 |
Prize | +0.044 |
Neg logit contributions | |
rying | -0.038 |
i | -0.036 |
bur | -0.036 |
ind | -0.034 |
ppa | -0.034 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
vows | +0.053 |
trophy | +0.047 |
prize | +0.046 |
apy | +0.046 |
ades | +0.043 |
Neg logit contributions | |
ior | -0.064 |
bur | -0.064 |
my | -0.064 |
ety | -0.063 |
gie | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
vows | +0.037 |
prize | +0.032 |
trophy | +0.032 |
contest | +0.030 |
ades | +0.030 |
Neg logit contributions | |
bur | -0.047 |
ety | -0.046 |
ior | -0.045 |
rying | -0.045 |
gie | -0.044 |
Token | shared |
Token ID | 4888 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
vows | +0.065 |
apy | +0.062 |
prize | +0.062 |
ades | +0.061 |
trophy | +0.060 |
Neg logit contributions | |
i | -0.054 |
bur | -0.054 |
ppa | -0.054 |
rying | -0.054 |
my | -0.050 |
Token | food |
Token ID | 2057 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
� | +0.075 |
vows | +0.075 |
Prize | +0.074 |
apy | +0.073 |
contest | +0.072 |
Neg logit contributions | |
bur | -0.078 |
my | -0.077 |
i | -0.074 |
ppa | -0.073 |
ind | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
vows | +0.102 |
Mine | +0.097 |
Prize | +0.097 |
apy | +0.096 |
contest | +0.093 |
Neg logit contributions | |
bur | -0.055 |
i | -0.054 |
ppa | -0.052 |
rying | -0.051 |
my | -0.048 |
Token | laughed |
Token ID | 13818 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
contest | +0.006 |
trophy | +0.006 |
apy | +0.006 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.011 |
i | -0.010 |
ind | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
vows | +0.140 |
Prize | +0.135 |
Mine | +0.135 |
contest | +0.135 |
prize | +0.132 |
Neg logit contributions | |
rying | -0.066 |
i | -0.065 |
ind | -0.060 |
ping | -0.060 |
since | -0.059 |
Token | lot |
Token ID | 1256 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
cakes | +0.135 |
vows | +0.133 |
apy | +0.127 |
hips | +0.126 |
progressed | +0.126 |
Neg logit contributions | |
ind | -0.163 |
my | -0.155 |
owl | -0.154 |
bur | -0.150 |
ppa | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
vows | +0.051 |
apy | +0.046 |
Mine | +0.046 |
contest | +0.045 |
Prize | +0.044 |
Neg logit contributions | |
rying | -0.038 |
ppa | -0.036 |
i | -0.035 |
bur | -0.035 |
ind | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.031 |
trophy | +0.031 |
contest | +0.030 |
ades | +0.029 |
Neg logit contributions | |
bur | -0.039 |
ior | -0.037 |
rying | -0.037 |
ety | -0.036 |
my | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.020 |
trophy | +0.019 |
contest | +0.019 |
cakes | +0.019 |
Neg logit contributions | |
bur | -0.028 |
ppa | -0.027 |
rying | -0.027 |
ind | -0.026 |
i | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
vows | +0.065 |
prize | +0.059 |
trophy | +0.058 |
cakes | +0.057 |
contest | +0.056 |
Neg logit contributions | |
ind | -0.041 |
bur | -0.040 |
ppa | -0.039 |
rying | -0.039 |
cker | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
vows | +0.005 |
prize | +0.005 |
contest | +0.005 |
trophy | +0.005 |
cakes | +0.005 |
Neg logit contributions | |
bur | -0.007 |
rying | -0.007 |
ppa | -0.007 |
i | -0.007 |
ind | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
vows | +0.005 |
apy | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
ind | -0.008 |
i | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
vows | +0.131 |
Prize | +0.118 |
Mine | +0.116 |
apy | +0.115 |
ades | +0.114 |
Neg logit contributions | |
my | -0.065 |
i | -0.063 |
rying | -0.061 |
bur | -0.059 |
owl | -0.059 |
Token | said |
Token ID | 531 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.011 |
ind | +0.011 |
i | +0.011 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
Mine | +0.133 |
� | +0.132 |
vows | +0.128 |
case | +0.126 |
blast | +0.126 |
Neg logit contributions | |
i | -0.082 |
owl | -0.081 |
Owl | -0.075 |
ppa | -0.073 |
asking | -0.070 |
Token | names |
Token ID | 3891 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
vows | +0.025 |
apy | +0.024 |
ades | +0.022 |
cakes | +0.022 |
trophy | +0.021 |
Neg logit contributions | |
bur | -0.035 |
ppa | -0.034 |
rying | -0.034 |
ind | -0.034 |
i | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
� | +0.208 |
Prize | +0.207 |
vows | +0.206 |
apy | +0.200 |
Mine | +0.199 |
Neg logit contributions | |
my | -0.133 |
i | -0.121 |
owl | -0.111 |
bur | -0.106 |
ie | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
vows | +0.047 |
apy | +0.043 |
cakes | +0.043 |
ades | +0.042 |
case | +0.041 |
Neg logit contributions | |
bur | -0.049 |
i | -0.047 |
ind | -0.047 |
ppa | -0.046 |
rying | -0.045 |
Token | things |
Token ID | 1243 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
vows | +0.019 |
apy | +0.017 |
trophy | +0.016 |
cakes | +0.016 |
prize | +0.016 |
Neg logit contributions | |
bur | -0.026 |
rying | -0.026 |
ppa | -0.026 |
ind | -0.026 |
i | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
vows | +0.155 |
Prize | +0.145 |
apy | +0.140 |
blast | +0.138 |
Mine | +0.137 |
Neg logit contributions | |
i | -0.120 |
my | -0.112 |
rying | -0.109 |
bur | -0.107 |
owl | -0.105 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.015 |
cakes | -0.014 |
Token | funny |
Token ID | 8258 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
vows | +0.081 |
apy | +0.080 |
ades | +0.067 |
ves | +0.066 |
Prize | +0.064 |
Neg logit contributions | |
my | -0.102 |
bur | -0.096 |
owl | -0.093 |
ind | -0.089 |
axe | -0.089 |
Token | animals |
Token ID | 4695 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
vows | +0.077 |
apy | +0.070 |
Prize | +0.067 |
contest | +0.067 |
prize | +0.067 |
Neg logit contributions | |
my | -0.105 |
ind | -0.099 |
ior | -0.098 |
ping | -0.098 |
oscope | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
vows | +0.108 |
Mine | +0.099 |
apy | +0.097 |
Prize | +0.095 |
prize | +0.095 |
Neg logit contributions | |
i | -0.063 |
rying | -0.060 |
bur | -0.060 |
my | -0.057 |
ppa | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
vows | +0.021 |
prize | +0.020 |
contest | +0.019 |
trophy | +0.019 |
ades | +0.018 |
Neg logit contributions | |
bur | -0.026 |
ppa | -0.026 |
i | -0.026 |
rying | -0.025 |
ety | -0.025 |
Token | silly |
Token ID | 14397 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
vows | +0.043 |
apy | +0.039 |
prize | +0.037 |
cakes | +0.037 |
ades | +0.036 |
Neg logit contributions | |
bur | -0.042 |
ind | -0.040 |
rying | -0.040 |
my | -0.039 |
gie | -0.039 |
Token | jokes |
Token ID | 14532 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
vows | +0.052 |
apy | +0.049 |
prize | +0.048 |
trophy | +0.047 |
contest | +0.047 |
Neg logit contributions | |
i | -0.048 |
ind | -0.048 |
bur | -0.047 |
rying | -0.047 |
gie | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
vows | +0.221 |
igsaw | +0.216 |
Prize | +0.215 |
Mine | +0.211 |
ades | +0.208 |
Neg logit contributions | |
i | -0.113 |
ting | -0.107 |
my | -0.103 |
owl | -0.097 |
ping | -0.097 |
Token | But |
Token ID | 887 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
vows | +0.040 |
prize | +0.035 |
trophy | +0.035 |
contest | +0.034 |
apy | +0.033 |
Neg logit contributions | |
bur | -0.044 |
ety | -0.043 |
my | -0.043 |
ior | -0.042 |
rying | -0.040 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
rying | +0.035 |
bur | +0.034 |
ppa | +0.034 |
ind | +0.033 |
i | +0.032 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.026 |
trophy | -0.025 |
apy | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
vows | +0.035 |
cakes | +0.030 |
ades | +0.029 |
prize | +0.029 |
trophy | +0.028 |
Neg logit contributions | |
i | -0.062 |
bur | -0.061 |
ppa | -0.059 |
rying | -0.059 |
my | -0.058 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
vows | +0.056 |
prize | +0.052 |
ades | +0.050 |
cakes | +0.050 |
apy | +0.049 |
Neg logit contributions | |
bur | -0.054 |
i | -0.053 |
ppa | -0.051 |
ety | -0.051 |
rying | -0.050 |
Token | taught |
Token ID | 7817 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
contest | +0.019 |
cakes | +0.019 |
trophy | +0.019 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.022 |
ppa | -0.022 |
i | -0.022 |
ind | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
rying | +0.029 |
bur | +0.029 |
ppa | +0.029 |
ind | +0.028 |
cker | +0.027 |
Neg logit contributions | |
vows | -0.019 |
prize | -0.017 |
contest | -0.016 |
trophy | -0.016 |
cakes | -0.015 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
vows | +0.077 |
Prize | +0.070 |
contest | +0.069 |
Mine | +0.068 |
prize | +0.066 |
Neg logit contributions | |
i | -0.055 |
my | -0.054 |
owl | -0.053 |
ppa | -0.053 |
axe | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
vows | +0.122 |
Prize | +0.107 |
contest | +0.106 |
prize | +0.106 |
apy | +0.106 |
Neg logit contributions | |
my | -0.080 |
i | -0.078 |
rying | -0.078 |
bur | -0.073 |
ind | -0.071 |
Token | her |
Token ID | 607 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.013 |
contest | +0.012 |
trophy | +0.012 |
cakes | +0.012 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.019 |
i | -0.019 |
ind | -0.018 |
Token | sisters |
Token ID | 15153 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
vows | +0.088 |
Prize | +0.079 |
Mine | +0.079 |
apy | +0.078 |
cakes | +0.078 |
Neg logit contributions | |
owl | -0.053 |
axe | -0.052 |
rying | -0.051 |
my | -0.050 |
i | -0.050 |
Token | how |
Token ID | 703 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
vows | +0.199 |
Prize | +0.181 |
apy | +0.174 |
disco | +0.173 |
Bang | +0.173 |
Neg logit contributions | |
my | -0.155 |
aware | -0.153 |
rying | -0.146 |
i | -0.134 |
asking | -0.133 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
vows | +0.053 |
prize | +0.047 |
trophy | +0.045 |
Prize | +0.045 |
contest | +0.045 |
Neg logit contributions | |
rying | -0.038 |
i | -0.034 |
ppa | -0.034 |
ety | -0.034 |
ind | -0.033 |
Token | build |
Token ID | 1382 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
vows | +0.005 |
prize | +0.004 |
contest | +0.004 |
cakes | +0.004 |
trophy | +0.004 |
Neg logit contributions | |
bur | -0.007 |
rying | -0.007 |
ppa | -0.006 |
i | -0.006 |
ind | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
vows | +0.098 |
Prize | +0.080 |
cakes | +0.079 |
trophy | +0.078 |
apy | +0.077 |
Neg logit contributions | |
rying | -0.085 |
bur | -0.081 |
my | -0.080 |
i | -0.080 |
ishing | -0.077 |
Token | too |
Token ID | 1165 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
vows | +0.117 |
Prize | +0.094 |
Mine | +0.094 |
apy | +0.092 |
cakes | +0.091 |
Neg logit contributions | |
rying | -0.099 |
my | -0.085 |
forth | -0.085 |
bur | -0.083 |
ishing | -0.082 |
Token | diamond |
Token ID | 15291 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
vows | +0.086 |
cakes | +0.083 |
ades | +0.076 |
apy | +0.073 |
ves | +0.070 |
Neg logit contributions | |
owl | -0.104 |
bur | -0.099 |
cker | -0.099 |
axe | -0.098 |
my | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
vows | +0.077 |
apy | +0.071 |
Mine | +0.070 |
cakes | +0.070 |
ades | +0.069 |
Neg logit contributions | |
i | -0.061 |
rying | -0.059 |
bur | -0.059 |
cker | -0.058 |
gie | -0.056 |
Token | They |
Token ID | 1119 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
vows | +0.023 |
trophy | +0.021 |
prize | +0.020 |
contest | +0.020 |
cakes | +0.018 |
Neg logit contributions | |
bur | -0.035 |
ety | -0.034 |
ppa | -0.034 |
rying | -0.034 |
i | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
vows | +0.085 |
cakes | +0.082 |
apy | +0.080 |
ades | +0.079 |
prize | +0.079 |
Neg logit contributions | |
i | -0.096 |
bur | -0.094 |
my | -0.093 |
ppa | -0.089 |
ety | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
� | +0.165 |
case | +0.154 |
cakes | +0.149 |
Mine | +0.148 |
books | +0.146 |
Neg logit contributions | |
i | -0.082 |
owl | -0.080 |
Owl | -0.072 |
asking | -0.070 |
ener | -0.067 |
Token | names |
Token ID | 3891 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
vows | +0.037 |
apy | +0.034 |
cakes | +0.034 |
ades | +0.031 |
uits | +0.029 |
Neg logit contributions | |
bur | -0.048 |
rying | -0.047 |
owl | -0.046 |
my | -0.046 |
cker | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
vows | +0.207 |
� | +0.204 |
Prize | +0.196 |
apy | +0.191 |
Mine | +0.191 |
Neg logit contributions | |
my | -0.132 |
i | -0.121 |
owl | -0.112 |
ie | -0.107 |
ener | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
vows | +0.056 |
cakes | +0.052 |
case | +0.051 |
apy | +0.050 |
prize | +0.048 |
Neg logit contributions | |
bur | -0.054 |
i | -0.054 |
ind | -0.053 |
rying | -0.051 |
ppa | -0.050 |
Token | shapes |
Token ID | 15268 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
vows | +0.034 |
apy | +0.031 |
cakes | +0.030 |
ades | +0.028 |
uits | +0.027 |
Neg logit contributions | |
bur | -0.044 |
rying | -0.044 |
my | -0.043 |
ind | -0.043 |
owl | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
vows | +0.226 |
Mine | +0.220 |
Goal | +0.218 |
� | +0.218 |
apy | +0.218 |
Neg logit contributions | |
i | -0.126 |
my | -0.117 |
rying | -0.106 |
owl | -0.102 |
cker | -0.101 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.012 |
contest | +0.012 |
cakes | +0.012 |
trophy | +0.012 |
Neg logit contributions | |
bur | -0.020 |
rying | -0.020 |
ppa | -0.019 |
i | -0.019 |
ind | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
vows | +0.037 |
apy | +0.033 |
prize | +0.033 |
cakes | +0.032 |
contest | +0.032 |
Neg logit contributions | |
bur | -0.030 |
rying | -0.030 |
ppa | -0.029 |
i | -0.029 |
ind | -0.027 |
Token | arrows |
Token ID | 20507 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
vows | +0.013 |
contest | +0.012 |
cakes | +0.012 |
prize | +0.011 |
trophy | +0.011 |
Neg logit contributions | |
bur | -0.019 |
ppa | -0.019 |
rying | -0.018 |
i | -0.018 |
ind | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
vows | +0.059 |
apy | +0.053 |
cakes | +0.053 |
Prize | +0.051 |
prize | +0.051 |
Neg logit contributions | |
bur | -0.043 |
rying | -0.042 |
i | -0.041 |
ppa | -0.041 |
cker | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
vows | +0.044 |
apy | +0.038 |
prize | +0.038 |
trophy | +0.038 |
contest | +0.036 |
Neg logit contributions | |
bur | -0.060 |
ety | -0.060 |
ior | -0.059 |
my | -0.058 |
rying | -0.058 |
Token | made |
Token ID | 925 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
vows | +0.039 |
cakes | +0.036 |
prize | +0.035 |
apy | +0.034 |
ades | +0.034 |
Neg logit contributions | |
bur | -0.035 |
ppa | -0.034 |
i | -0.034 |
ety | -0.033 |
rying | -0.032 |
Token | them |
Token ID | 606 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
vows | +0.062 |
� | +0.057 |
cakes | +0.057 |
contest | +0.055 |
apy | +0.054 |
Neg logit contributions | |
ind | -0.076 |
rying | -0.074 |
bur | -0.073 |
i | -0.073 |
ppa | -0.072 |
Token | from |
Token ID | 422 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
vows | +0.183 |
� | +0.180 |
cakes | +0.178 |
books | +0.166 |
apy | +0.164 |
Neg logit contributions | |
my | -0.176 |
forth | -0.164 |
rying | -0.164 |
ety | -0.163 |
i | -0.160 |
Token | sticks |
Token ID | 16461 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
bur | +0.036 |
rying | +0.035 |
ppa | +0.035 |
i | +0.034 |
ind | +0.033 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.019 |
contest | -0.019 |
trophy | -0.019 |
Prize | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
vows | +0.033 |
cakes | +0.029 |
prize | +0.029 |
apy | +0.029 |
contest | +0.029 |
Neg logit contributions | |
bur | -0.022 |
rying | -0.022 |
ppa | -0.020 |
i | -0.020 |
ind | -0.020 |
Token | strings |
Token ID | 13042 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
apy | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
vows | +0.077 |
cakes | +0.069 |
apy | +0.068 |
Prize | +0.068 |
prize | +0.067 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.051 |
i | -0.049 |
ppa | -0.048 |
cker | -0.047 |
Token | fan |
Token ID | 4336 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
vows | +0.072 |
Prize | +0.057 |
cakes | +0.057 |
apy | +0.056 |
uits | +0.055 |
Neg logit contributions | |
bur | -0.082 |
my | -0.076 |
axe | -0.075 |
ind | -0.074 |
owl | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.027 |
prize | +0.027 |
trophy | +0.027 |
cakes | +0.027 |
Neg logit contributions | |
rying | -0.029 |
bur | -0.029 |
i | -0.028 |
ppa | -0.027 |
ind | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
vows | +0.056 |
trophy | +0.049 |
prize | +0.047 |
contest | +0.046 |
festival | +0.045 |
Neg logit contributions | |
gie | -0.067 |
bur | -0.064 |
my | -0.063 |
ety | -0.063 |
ior | -0.063 |
Token | pretend |
Token ID | 16614 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
cakes | +0.109 |
vows | +0.107 |
ades | +0.102 |
apy | +0.093 |
ival | +0.088 |
Neg logit contributions | |
my | -0.116 |
bur | -0.114 |
forth | -0.110 |
i | -0.110 |
ety | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
vows | +0.107 |
Prize | +0.098 |
� | +0.097 |
Mine | +0.095 |
prize | +0.092 |
Neg logit contributions | |
bur | -0.070 |
rying | -0.069 |
owl | -0.069 |
forth | -0.068 |
i | -0.068 |
Token | shapes |
Token ID | 15268 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
vows | +0.070 |
apy | +0.061 |
cakes | +0.059 |
Prize | +0.058 |
uits | +0.058 |
Neg logit contributions | |
bur | -0.086 |
my | -0.079 |
owl | -0.078 |
axe | -0.077 |
forth | -0.075 |
Token | are |
Token ID | 389 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
vows | +0.197 |
� | +0.188 |
Prize | +0.186 |
ival | +0.184 |
cakes | +0.183 |
Neg logit contributions | |
i | -0.142 |
my | -0.136 |
rying | -0.136 |
cker | -0.135 |
forth | -0.131 |
Token | flying |
Token ID | 7348 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.020 |
cakes | +0.020 |
trophy | +0.020 |
contest | +0.020 |
Neg logit contributions | |
bur | -0.020 |
rying | -0.020 |
ppa | -0.019 |
i | -0.018 |
ind | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
vows | +0.064 |
cakes | +0.057 |
apy | +0.057 |
trophy | +0.054 |
prize | +0.054 |
Neg logit contributions | |
rying | -0.040 |
bur | -0.039 |
i | -0.037 |
ind | -0.037 |
ety | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
vows | +0.052 |
trophy | +0.047 |
prize | +0.044 |
contest | +0.042 |
festival | +0.042 |
Neg logit contributions | |
gie | -0.066 |
ety | -0.064 |
bur | -0.064 |
my | -0.063 |
rying | -0.062 |
Token | have |
Token ID | 423 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
cakes | +0.118 |
vows | +0.111 |
ades | +0.108 |
apy | +0.100 |
ival | +0.095 |
Neg logit contributions | |
my | -0.130 |
bur | -0.129 |
i | -0.126 |
forth | -0.124 |
cker | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
vows | +0.114 |
cakes | +0.095 |
apy | +0.095 |
Mine | +0.094 |
Prize | +0.093 |
Neg logit contributions | |
rying | -0.060 |
owl | -0.055 |
ishing | -0.053 |
bur | -0.051 |
ppa | -0.050 |
Token | game |
Token ID | 983 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
vows | +0.101 |
uits | +0.091 |
apy | +0.088 |
Both | +0.086 |
cakes | +0.086 |
Neg logit contributions | |
ind | -0.171 |
rying | -0.152 |
owl | -0.151 |
ppa | -0.151 |
ich | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
vows | +0.091 |
apy | +0.075 |
trophy | +0.074 |
Prize | +0.073 |
prize | +0.073 |
Neg logit contributions | |
rying | -0.065 |
bur | -0.060 |
my | -0.059 |
ppa | -0.057 |
i | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
trophy | +0.010 |
contest | +0.010 |
ades | +0.010 |
Neg logit contributions | |
bur | -0.014 |
ppa | -0.014 |
rying | -0.014 |
ety | -0.014 |
i | -0.014 |
Token | won |
Token ID | 1839 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
ind | +0.007 |
i | +0.007 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
vows | +0.044 |
trophy | +0.038 |
ades | +0.036 |
apy | +0.036 |
prize | +0.036 |
Neg logit contributions | |
bur | -0.041 |
rying | -0.039 |
ppa | -0.039 |
i | -0.038 |
my | -0.037 |
Token | prize |
Token ID | 11596 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
uits | +0.128 |
vows | +0.120 |
apy | +0.116 |
are | +0.106 |
widened | +0.099 |
Neg logit contributions | |
ind | -0.205 |
ety | -0.194 |
owl | -0.191 |
rying | -0.190 |
ppa | -0.184 |
Token | ! |
Token ID | 0 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
vows | +0.059 |
apy | +0.052 |
ades | +0.049 |
Mine | +0.049 |
trophy | +0.048 |
Neg logit contributions | |
rying | -0.041 |
bur | -0.040 |
i | -0.039 |
ppa | -0.039 |
ety | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.015 |
trophy | +0.015 |
contest | +0.015 |
ades | +0.015 |
Neg logit contributions | |
bur | -0.022 |
ety | -0.021 |
ppa | -0.021 |
rying | -0.021 |
my | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
vows | +0.074 |
apy | +0.064 |
prize | +0.063 |
ades | +0.063 |
uits | +0.063 |
Neg logit contributions | |
bur | -0.059 |
my | -0.057 |
i | -0.057 |
rying | -0.055 |
ety | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
vows | +0.055 |
ades | +0.047 |
trophy | +0.046 |
apy | +0.046 |
cakes | +0.045 |
Neg logit contributions | |
bur | -0.046 |
ppa | -0.042 |
i | -0.042 |
rying | -0.042 |
my | -0.041 |
Token | talked |
Token ID | 6619 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
vows | +0.070 |
prize | +0.069 |
trophy | +0.068 |
contest | +0.068 |
apy | +0.066 |
Neg logit contributions | |
ppa | -0.055 |
i | -0.054 |
bur | -0.052 |
ety | -0.049 |
my | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
vows | +0.134 |
� | +0.133 |
Prize | +0.131 |
apy | +0.130 |
trophy | +0.129 |
Neg logit contributions | |
my | -0.056 |
bur | -0.047 |
rying | -0.047 |
ppa | -0.047 |
i | -0.047 |
Token | them |
Token ID | 606 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
vows | +0.017 |
prize | +0.015 |
trophy | +0.015 |
contest | +0.015 |
cakes | +0.015 |
Neg logit contributions | |
bur | -0.025 |
ppa | -0.025 |
i | -0.025 |
rying | -0.025 |
ind | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
vows | +0.169 |
apy | +0.169 |
Mine | +0.162 |
Prize | +0.160 |
� | +0.157 |
Neg logit contributions | |
i | -0.075 |
my | -0.073 |
rying | -0.072 |
bur | -0.063 |
owl | -0.062 |
Token | made |
Token ID | 925 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
vows | +0.032 |
prize | +0.029 |
ades | +0.029 |
contest | +0.029 |
trophy | +0.029 |
Neg logit contributions | |
bur | -0.030 |
ppa | -0.030 |
rying | -0.029 |
i | -0.029 |
ety | -0.028 |
Token | them |
Token ID | 606 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
vows | +0.055 |
Prize | +0.051 |
prize | +0.051 |
trophy | +0.051 |
contest | +0.050 |
Neg logit contributions | |
i | -0.074 |
ind | -0.074 |
rying | -0.073 |
bur | -0.073 |
ppa | -0.072 |
Token | talk |
Token ID | 1561 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
� | +0.162 |
Prize | +0.154 |
vows | +0.149 |
Mine | +0.144 |
ival | +0.140 |
Neg logit contributions | |
my | -0.189 |
rying | -0.185 |
i | -0.171 |
ety | -0.166 |
bur | -0.164 |
Token | back |
Token ID | 736 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
apy | +0.147 |
� | +0.146 |
vows | +0.141 |
Prize | +0.141 |
Mine | +0.140 |
Neg logit contributions | |
my | -0.066 |
rying | -0.065 |
ind | -0.062 |
i | -0.060 |
owl | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.029 |
contest | +0.029 |
prize | +0.029 |
trophy | +0.029 |
Neg logit contributions | |
rying | -0.027 |
bur | -0.027 |
ind | -0.027 |
i | -0.026 |
ppa | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.022 |
trophy | +0.022 |
contest | +0.021 |
cakes | +0.020 |
Neg logit contributions | |
bur | -0.030 |
ppa | -0.029 |
rying | -0.028 |
ety | -0.028 |
i | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.020 |
i | +0.019 |
ind | +0.019 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | dolls |
Token ID | 36062 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
apy | +0.035 |
vows | +0.034 |
ades | +0.032 |
cakes | +0.031 |
trophy | +0.030 |
Neg logit contributions | |
bur | -0.049 |
ppa | -0.048 |
rying | -0.047 |
ind | -0.047 |
i | -0.046 |
Token | ' |
Token ID | 6 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
vows | +0.060 |
apy | +0.054 |
Prize | +0.054 |
Mine | +0.054 |
contest | +0.053 |
Neg logit contributions | |
rying | -0.043 |
bur | -0.042 |
ppa | -0.041 |
i | -0.041 |
ind | -0.039 |
Token | hands |
Token ID | 2832 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.006 |
contest | +0.005 |
trophy | +0.005 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
ind | -0.008 |
i | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
bur | +0.002 |
rying | +0.002 |
ppa | +0.002 |
i | +0.002 |
ind | +0.002 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
vows | +0.026 |
prize | +0.023 |
contest | +0.023 |
trophy | +0.023 |
ades | +0.023 |
Neg logit contributions | |
bur | -0.028 |
ppa | -0.028 |
i | -0.027 |
rying | -0.027 |
ety | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
� | +0.075 |
vows | +0.075 |
trophy | +0.071 |
Prize | +0.071 |
contest | +0.070 |
Neg logit contributions | |
i | -0.092 |
ind | -0.092 |
rying | -0.090 |
ppa | -0.090 |
bur | -0.089 |
Token | say |
Token ID | 910 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
� | +0.153 |
Prize | +0.135 |
Mine | +0.133 |
vows | +0.130 |
cakes | +0.124 |
Neg logit contributions | |
rying | -0.192 |
my | -0.190 |
i | -0.187 |
aware | -0.173 |
bur | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Mine | +0.185 |
case | +0.167 |
� | +0.166 |
trophy | +0.158 |
igsaw | +0.157 |
Neg logit contributions | |
i | -0.120 |
owl | -0.109 |
asking | -0.106 |
ppa | -0.106 |
rying | -0.101 |
Token | " |
Token ID | 366 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
vows | +0.071 |
prize | +0.065 |
trophy | +0.063 |
contest | +0.062 |
case | +0.062 |
Neg logit contributions | |
gie | -0.089 |
rying | -0.088 |
bur | -0.086 |
ppa | -0.085 |
owl | -0.084 |
Token | I |
Token ID | 40 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
vows | +0.031 |
trophy | +0.028 |
prize | +0.028 |
apy | +0.028 |
contest | +0.027 |
Neg logit contributions | |
bur | -0.039 |
ppa | -0.037 |
ind | -0.037 |
ety | -0.036 |
i | -0.036 |
Token | do |
Token ID | 466 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
cakes | +0.092 |
apy | +0.089 |
ades | +0.089 |
trophy | +0.088 |
vows | +0.087 |
Neg logit contributions | |
i | -0.081 |
bur | -0.080 |
my | -0.075 |
rying | -0.074 |
ppa | -0.074 |
Token | takes |
Token ID | 2753 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
apy | +0.123 |
vows | +0.120 |
contest | +0.115 |
prize | +0.113 |
Prize | +0.112 |
Neg logit contributions | |
i | -0.091 |
rying | -0.089 |
my | -0.087 |
bur | -0.087 |
ind | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
vows | +0.019 |
prize | +0.016 |
trophy | +0.016 |
Prize | +0.016 |
contest | +0.016 |
Neg logit contributions | |
bur | -0.020 |
rying | -0.019 |
ppa | -0.019 |
i | -0.019 |
my | -0.019 |
Token | sip |
Token ID | 31145 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
vows | +0.093 |
Prize | +0.068 |
parties | +0.067 |
Everybody | +0.066 |
Everyone | +0.065 |
Neg logit contributions | |
my | -0.120 |
ety | -0.116 |
rying | -0.109 |
bur | -0.108 |
row | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
vows | +0.085 |
Prize | +0.078 |
prize | +0.075 |
contest | +0.074 |
trophy | +0.073 |
Neg logit contributions | |
i | -0.050 |
my | -0.048 |
rying | -0.047 |
bur | -0.046 |
ety | -0.044 |
Token | The |
Token ID | 383 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
vows | +0.083 |
prize | +0.078 |
trophy | +0.076 |
contest | +0.073 |
festival | +0.071 |
Neg logit contributions | |
bur | -0.065 |
gie | -0.064 |
Owl | -0.064 |
ior | -0.064 |
ety | -0.062 |
Token | juice |
Token ID | 13135 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
vows | +0.070 |
Prize | +0.063 |
ival | +0.061 |
ades | +0.061 |
case | +0.060 |
Neg logit contributions | |
my | -0.080 |
bur | -0.074 |
ety | -0.073 |
i | -0.071 |
ener | -0.069 |
Token | is |
Token ID | 318 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ival | +0.203 |
Prize | +0.199 |
vows | +0.192 |
igsaw | +0.183 |
ades | +0.179 |
Neg logit contributions | |
my | -0.127 |
i | -0.126 |
forth | -0.119 |
rying | -0.116 |
bur | -0.112 |
Token | sweet |
Token ID | 6029 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
vows | +0.042 |
Prize | +0.037 |
contest | +0.037 |
prize | +0.037 |
trophy | +0.036 |
Neg logit contributions | |
bur | -0.048 |
ppa | -0.047 |
i | -0.046 |
rying | -0.046 |
ety | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
i | +0.006 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
apy | -0.005 |
Token | cold |
Token ID | 4692 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
vows | +0.007 |
contest | +0.006 |
prize | +0.006 |
trophy | +0.006 |
cakes | +0.006 |
Neg logit contributions | |
bur | -0.010 |
rying | -0.010 |
ppa | -0.010 |
i | -0.010 |
ind | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
apy | +0.004 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.004 |
i | -0.004 |
ind | -0.004 |
Token | pushed |
Token ID | 7121 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
vows | +0.067 |
prize | +0.063 |
trophy | +0.060 |
contest | +0.059 |
Prize | +0.058 |
Neg logit contributions | |
ppa | -0.056 |
my | -0.056 |
i | -0.056 |
rying | -0.055 |
bur | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.015 |
ppa | +0.015 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | buttons |
Token ID | 12163 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
vows | +0.046 |
apy | +0.044 |
ades | +0.038 |
prize | +0.038 |
ves | +0.038 |
Neg logit contributions | |
my | -0.074 |
ind | -0.073 |
rying | -0.073 |
ener | -0.072 |
bur | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
vows | +0.086 |
Prize | +0.074 |
prize | +0.073 |
cakes | +0.072 |
contest | +0.072 |
Neg logit contributions | |
rying | -0.054 |
bur | -0.052 |
i | -0.050 |
my | -0.048 |
gie | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.013 |
trophy | +0.013 |
contest | +0.013 |
ades | +0.012 |
Neg logit contributions | |
bur | -0.015 |
rying | -0.015 |
ppa | -0.014 |
i | -0.014 |
gie | -0.014 |
Token | images |
Token ID | 4263 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
vows | +0.072 |
apy | +0.067 |
ades | +0.065 |
Prize | +0.065 |
ves | +0.064 |
Neg logit contributions | |
my | -0.058 |
ener | -0.057 |
owl | -0.057 |
ind | -0.056 |
rying | -0.056 |
Token | changed |
Token ID | 3421 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
vows | +0.180 |
Prize | +0.177 |
festival | +0.154 |
coach | +0.154 |
prize | +0.154 |
Neg logit contributions | |
rying | -0.156 |
forth | -0.155 |
i | -0.152 |
my | -0.149 |
ener | -0.144 |
Token | back |
Token ID | 736 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
vows | +0.048 |
prize | +0.044 |
contest | +0.043 |
trophy | +0.043 |
cakes | +0.043 |
Neg logit contributions | |
rying | -0.043 |
bur | -0.041 |
i | -0.041 |
ind | -0.040 |
ppa | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
ind | +0.005 |
i | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
vows | +0.046 |
cakes | +0.042 |
ades | +0.041 |
trophy | +0.040 |
apy | +0.039 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.051 |
ind | -0.051 |
i | -0.049 |
my | -0.049 |
Token | way |
Token ID | 835 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
vows | +0.031 |
apy | +0.029 |
prize | +0.026 |
ves | +0.025 |
ades | +0.025 |
Neg logit contributions | |
ind | -0.052 |
rying | -0.051 |
bur | -0.050 |
my | -0.050 |
ppa | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
vows | +0.133 |
Prize | +0.123 |
apy | +0.121 |
cakes | +0.120 |
prize | +0.118 |
Neg logit contributions | |
rying | -0.072 |
i | -0.069 |
my | -0.066 |
bur | -0.063 |
cker | -0.062 |
Token | They |
Token ID | 1119 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
vows | +0.090 |
prize | +0.084 |
trophy | +0.083 |
kin | +0.082 |
ades | +0.082 |
Neg logit contributions | |
ior | -0.090 |
ety | -0.079 |
my | -0.077 |
gie | -0.076 |
bur | -0.074 |
Token | both |
Token ID | 1111 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
vows | +0.070 |
cakes | +0.069 |
apy | +0.064 |
ades | +0.064 |
ves | +0.063 |
Neg logit contributions | |
my | -0.094 |
i | -0.094 |
bur | -0.092 |
rying | -0.088 |
ppa | -0.088 |
Token | think |
Token ID | 892 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
vows | +0.052 |
cakes | +0.051 |
ades | +0.048 |
apy | +0.046 |
prize | +0.044 |
Neg logit contributions | |
i | -0.082 |
my | -0.081 |
rying | -0.081 |
bur | -0.080 |
cker | -0.079 |
Token | their |
Token ID | 511 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
vows | +0.102 |
Prize | +0.092 |
Mine | +0.089 |
� | +0.088 |
cakes | +0.084 |
Neg logit contributions | |
i | -0.080 |
rying | -0.075 |
my | -0.075 |
owl | -0.074 |
ind | -0.074 |
Token | shapes |
Token ID | 15268 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
cakes | +0.081 |
ades | +0.071 |
apy | +0.071 |
ival | +0.070 |
Prize | +0.070 |
Neg logit contributions | |
ind | -0.081 |
i | -0.074 |
owl | -0.072 |
bur | -0.070 |
ener | -0.070 |
Token | are |
Token ID | 389 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
vows | +0.133 |
Prize | +0.128 |
apy | +0.120 |
cakes | +0.119 |
ival | +0.119 |
Neg logit contributions | |
my | -0.212 |
i | -0.202 |
cker | -0.197 |
rying | -0.193 |
bur | -0.190 |
Token | good |
Token ID | 922 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
vows | +0.059 |
cakes | +0.054 |
apy | +0.052 |
Prize | +0.051 |
contest | +0.051 |
Neg logit contributions | |
bur | -0.068 |
rying | -0.067 |
i | -0.066 |
ppa | -0.066 |
cker | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
vows | +0.040 |
apy | +0.036 |
ades | +0.035 |
cakes | +0.035 |
trophy | +0.034 |
Neg logit contributions | |
rying | -0.030 |
i | -0.029 |
bur | -0.029 |
ppa | -0.028 |
ety | -0.028 |
Token | But |
Token ID | 887 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
vows | +0.040 |
prize | +0.037 |
trophy | +0.037 |
contest | +0.035 |
ades | +0.033 |
Neg logit contributions | |
ior | -0.055 |
ety | -0.053 |
bur | -0.053 |
my | -0.051 |
ind | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.005 |
contest | +0.005 |
trophy | +0.005 |
cakes | +0.005 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
i | -0.008 |
ind | -0.008 |
Token | feels |
Token ID | 5300 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
bur | +0.002 |
rying | +0.002 |
ppa | +0.002 |
i | +0.002 |
ind | +0.002 |
Neg logit contributions | |
vows | -0.001 |
prize | -0.001 |
contest | -0.001 |
trophy | -0.001 |
cakes | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
bur | +0.023 |
rying | +0.023 |
ppa | +0.022 |
ind | +0.022 |
i | +0.022 |
Neg logit contributions | |
vows | -0.019 |
prize | -0.016 |
contest | -0.016 |
apy | -0.016 |
trophy | -0.016 |
Token | burn |
Token ID | 4245 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.017 |
ppa | +0.017 |
i | +0.016 |
ind | +0.016 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.010 |
apy | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ppa | +0.051 |
bur | +0.051 |
rying | +0.049 |
ind | +0.048 |
ety | +0.048 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.033 |
contest | -0.032 |
trophy | -0.032 |
are | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
rying | +0.043 |
ppa | +0.042 |
bur | +0.041 |
ind | +0.040 |
i | +0.040 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.025 |
apy | -0.024 |
trophy | -0.024 |
contest | -0.024 |
Token | tum |
Token ID | 11814 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
rying | +0.033 |
bur | +0.032 |
ppa | +0.032 |
ind | +0.030 |
i | +0.030 |
Neg logit contributions | |
vows | -0.031 |
prize | -0.028 |
contest | -0.028 |
trophy | -0.027 |
apy | -0.027 |
Token | my |
Token ID | 1820 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
rying | +0.129 |
ind | +0.124 |
lamb | +0.121 |
cker | +0.110 |
ppa | +0.109 |
Neg logit contributions | |
are | -0.175 |
cakes | -0.164 |
ades | -0.154 |
were | -0.154 |
books | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
bur | +0.082 |
rying | +0.081 |
ppa | +0.079 |
ind | +0.079 |
umper | +0.075 |
Neg logit contributions | |
vows | -0.049 |
are | -0.046 |
prize | -0.046 |
trophy | -0.044 |
contest | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
rying | +0.025 |
bur | +0.025 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.018 |
contest | -0.018 |
apy | -0.018 |
trophy | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.012 |
Token | angry |
Token ID | 7954 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
bur | +0.058 |
rying | +0.057 |
ppa | +0.055 |
i | +0.054 |
ior | +0.054 |
Neg logit contributions | |
vows | -0.043 |
apy | -0.039 |
contest | -0.038 |
tea | -0.038 |
prize | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.020 |
trophy | +0.020 |
contest | +0.020 |
apy | +0.020 |
Neg logit contributions | |
bur | -0.029 |
ppa | -0.027 |
rying | -0.027 |
i | -0.027 |
gie | -0.026 |
Token | washed |
Token ID | 18989 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.030 |
Prize | +0.029 |
trophy | +0.029 |
contest | +0.029 |
Neg logit contributions | |
bur | -0.035 |
rying | -0.033 |
ppa | -0.033 |
i | -0.031 |
ind | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
bur | +0.025 |
rying | +0.025 |
ppa | +0.025 |
ind | +0.024 |
i | +0.023 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.015 |
apy | -0.015 |
Token | dried |
Token ID | 16577 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
bur | +0.039 |
ppa | +0.038 |
rying | +0.038 |
ind | +0.037 |
ior | +0.036 |
Neg logit contributions | |
vows | -0.027 |
apy | -0.025 |
prize | -0.024 |
contest | -0.024 |
trophy | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
bur | +0.067 |
rying | +0.065 |
ppa | +0.065 |
ety | +0.063 |
cker | +0.062 |
Neg logit contributions | |
vows | -0.042 |
apy | -0.037 |
prize | -0.035 |
trophy | -0.032 |
are | -0.032 |
Token | Ang |
Token ID | 2895 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
bur | +0.049 |
rying | +0.049 |
ppa | +0.048 |
ind | +0.046 |
cker | +0.046 |
Neg logit contributions | |
vows | -0.047 |
apy | -0.045 |
prize | -0.044 |
contest | -0.042 |
trophy | -0.041 |
Token | ie |
Token ID | 494 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
territory | +0.146 |
ior | +0.138 |
Owl | +0.133 |
property | +0.132 |
afar | +0.128 |
Neg logit contributions | |
vows | -0.135 |
were | -0.118 |
are | -0.116 |
tea | -0.114 |
kin | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
rying | +0.061 |
bur | +0.060 |
ppa | +0.060 |
ind | +0.060 |
ior | +0.057 |
Neg logit contributions | |
vows | -0.028 |
apy | -0.024 |
prize | -0.023 |
trophy | -0.022 |
contest | -0.021 |
Token | mum |
Token ID | 25682 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
vows | +0.010 |
contest | +0.009 |
prize | +0.009 |
cakes | +0.009 |
trophy | +0.009 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.011 |
i | -0.011 |
ind | -0.011 |
Token | headed |
Token ID | 9153 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.012 |
ppa | +0.012 |
ind | +0.011 |
i | +0.011 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
bur | +0.100 |
ppa | +0.099 |
ior | +0.098 |
rying | +0.096 |
ind | +0.096 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.044 |
prize | -0.042 |
are | -0.040 |
trophy | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
bur | +0.034 |
rying | +0.034 |
ppa | +0.034 |
ind | +0.033 |
i | +0.032 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.014 |
cakes | -0.014 |
trophy | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
bur | +0.033 |
rying | +0.033 |
ppa | +0.032 |
i | +0.031 |
ind | +0.031 |
Neg logit contributions | |
vows | -0.024 |
contest | -0.022 |
prize | -0.021 |
trophy | -0.021 |
apy | -0.021 |
Token | Hi |
Token ID | 17250 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
rying | +0.029 |
ppa | +0.028 |
bur | +0.028 |
ind | +0.028 |
i | +0.027 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.026 |
cakes | -0.025 |
trophy | -0.025 |
Token | Tweet |
Token ID | 18752 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
ppa | +0.074 |
rying | +0.074 |
bur | +0.072 |
ind | +0.071 |
cker | +0.070 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.040 |
contest | -0.037 |
trophy | -0.036 |
Prize | -0.034 |
Token | ie |
Token ID | 494 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
rying | +0.132 |
oscope | +0.128 |
keeping | +0.127 |
ind | +0.123 |
bur | +0.121 |
Neg logit contributions | |
are | -0.163 |
prize | -0.162 |
team | -0.158 |
trophy | -0.156 |
laugh | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
bur | +0.178 |
rying | +0.178 |
ind | +0.174 |
ppa | +0.171 |
umper | +0.169 |
Neg logit contributions | |
prize | -0.051 |
are | -0.047 |
contest | -0.046 |
vows | -0.046 |
trophy | -0.043 |
Token | do |
Token ID | 466 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
bur | +0.022 |
rying | +0.022 |
ppa | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
cakes | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
vows | +0.036 |
trophy | +0.032 |
prize | +0.032 |
cakes | +0.032 |
contest | +0.031 |
Neg logit contributions | |
bur | -0.023 |
ppa | -0.023 |
rying | -0.023 |
i | -0.022 |
ind | -0.022 |
Token | want |
Token ID | 765 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
bur | +0.024 |
ppa | +0.024 |
rying | +0.024 |
ind | +0.023 |
i | +0.023 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.017 |
contest | -0.016 |
trophy | -0.016 |
joke | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
vows | +0.036 |
trophy | +0.029 |
prize | +0.029 |
contest | +0.028 |
apy | +0.028 |
Neg logit contributions | |
my | -0.054 |
bur | -0.053 |
rying | -0.052 |
i | -0.052 |
ety | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.014 |
trophy | +0.014 |
contest | +0.014 |
apy | +0.013 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.012 |
i | -0.011 |
ind | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
bur | +0.017 |
ppa | +0.017 |
rying | +0.016 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
cakes | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
vows | +0.035 |
ades | +0.029 |
contest | +0.029 |
trophy | +0.028 |
apy | +0.028 |
Neg logit contributions | |
bur | -0.036 |
rying | -0.034 |
ppa | -0.034 |
ety | -0.033 |
i | -0.033 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rying | +0.098 |
ind | +0.097 |
bur | +0.096 |
ppa | +0.094 |
gie | +0.090 |
Neg logit contributions | |
contest | -0.068 |
vows | -0.064 |
trophy | -0.063 |
prize | -0.062 |
case | -0.060 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
rying | +0.063 |
bur | +0.061 |
ind | +0.060 |
ppa | +0.060 |
cker | +0.056 |
Neg logit contributions | |
vows | -0.030 |
apy | -0.030 |
contest | -0.028 |
prize | -0.027 |
cakes | -0.026 |
Token | called |
Token ID | 1444 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ind | +0.190 |
rying | +0.184 |
ishing | +0.172 |
property | +0.171 |
bur | +0.170 |
Neg logit contributions | |
tag | -0.101 |
laugh | -0.099 |
g | -0.098 |
joke | -0.094 |
cl | -0.094 |
Token | out |
Token ID | 503 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
vows | +0.026 |
trophy | +0.022 |
prize | +0.022 |
ades | +0.022 |
apy | +0.021 |
Neg logit contributions | |
rying | -0.026 |
bur | -0.026 |
ppa | -0.025 |
i | -0.024 |
ety | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
vows | +0.089 |
Prize | +0.078 |
trophy | +0.078 |
Mine | +0.078 |
ades | +0.077 |
Neg logit contributions | |
rying | -0.053 |
owl | -0.051 |
Owl | -0.050 |
i | -0.050 |
my | -0.049 |
Token | He |
Token ID | 679 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
vows | +0.011 |
prize | +0.009 |
trophy | +0.009 |
contest | +0.009 |
ades | +0.009 |
Neg logit contributions | |
bur | -0.015 |
rying | -0.015 |
ppa | -0.015 |
ety | -0.014 |
gie | -0.014 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
bur | +0.036 |
rying | +0.036 |
ppa | +0.034 |
ind | +0.034 |
ior | +0.032 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.025 |
contest | -0.025 |
trophy | -0.025 |
apy | -0.024 |
Token | walking |
Token ID | 6155 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.017 |
i | +0.016 |
Neg logit contributions | |
vows | -0.025 |
contest | -0.023 |
prize | -0.023 |
trophy | -0.023 |
cakes | -0.022 |
Token | down |
Token ID | 866 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
vows | +0.002 |
prize | +0.002 |
contest | +0.002 |
trophy | +0.002 |
cakes | +0.002 |
Neg logit contributions | |
bur | -0.002 |
rying | -0.002 |
ppa | -0.002 |
i | -0.002 |
ind | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
vows | +0.047 |
trophy | +0.040 |
joke | +0.039 |
ades | +0.038 |
prize | +0.038 |
Neg logit contributions | |
bur | -0.039 |
rying | -0.035 |
my | -0.035 |
i | -0.034 |
ety | -0.034 |
Token | aisle |
Token ID | 28960 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
rying | +0.016 |
bur | +0.016 |
ppa | +0.016 |
i | +0.016 |
ind | +0.015 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
cakes | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
bur | +0.042 |
rying | +0.042 |
ppa | +0.042 |
ind | +0.041 |
i | +0.040 |
Neg logit contributions | |
vows | -0.021 |
contest | -0.019 |
prize | -0.019 |
trophy | -0.018 |
cakes | -0.017 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.027 |
trophy | +0.027 |
contest | +0.026 |
ades | +0.026 |
Neg logit contributions | |
bur | -0.042 |
rying | -0.040 |
gie | -0.040 |
i | -0.040 |
ety | -0.040 |
Token | my |
Token ID | 1820 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
predators | +0.149 |
rying | +0.147 |
ind | +0.141 |
cker | +0.135 |
iously | +0.135 |
Neg logit contributions | |
were | -0.155 |
are | -0.148 |
team | -0.138 |
case | -0.138 |
game | -0.137 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
rying | +0.160 |
bur | +0.150 |
ind | +0.149 |
ior | +0.142 |
cker | +0.140 |
Neg logit contributions | |
vows | -0.078 |
they | -0.075 |
contest | -0.073 |
were | -0.073 |
case | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
ind | +0.006 |
i | +0.006 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
vows | +0.042 |
cakes | +0.035 |
apy | +0.035 |
uits | +0.034 |
prize | +0.033 |
Neg logit contributions | |
bur | -0.053 |
ppa | -0.052 |
ind | -0.052 |
rying | -0.051 |
owl | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.012 |
apy | +0.012 |
cakes | +0.012 |
contest | +0.012 |
Neg logit contributions | |
bur | -0.016 |
rying | -0.016 |
ppa | -0.016 |
ind | -0.015 |
i | -0.015 |
Token | But |
Token ID | 887 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
bur | +0.104 |
ppa | +0.103 |
rying | +0.103 |
ind | +0.100 |
i | +0.098 |
Neg logit contributions | |
vows | -0.064 |
Everyone | -0.061 |
prize | -0.058 |
Prize | -0.057 |
contest | -0.056 |
Token | first |
Token ID | 717 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ppa | +0.153 |
ior | +0.148 |
ind | +0.146 |
bur | +0.145 |
rying | +0.140 |
Neg logit contributions | |
prize | -0.088 |
contest | -0.081 |
trophy | -0.080 |
are | -0.078 |
thank | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
bur | +0.093 |
ppa | +0.092 |
ind | +0.092 |
rying | +0.090 |
ior | +0.088 |
Neg logit contributions | |
prize | -0.036 |
vows | -0.034 |
contest | -0.033 |
are | -0.033 |
trophy | -0.033 |
Token | let |
Token ID | 1309 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ppa | +0.111 |
ind | +0.110 |
bur | +0.110 |
ior | +0.106 |
rying | +0.106 |
Neg logit contributions | |
prize | -0.070 |
vows | -0.066 |
contest | -0.066 |
are | -0.064 |
trophy | -0.064 |
Token | 's |
Token ID | 338 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
rying | +0.074 |
bur | +0.071 |
ppa | +0.071 |
cker | +0.071 |
ind | +0.070 |
Neg logit contributions | |
vows | -0.045 |
are | -0.043 |
prize | -0.043 |
contest | -0.042 |
Everyone | -0.041 |
Token | find |
Token ID | 1064 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
rying | +0.072 |
ppa | +0.071 |
bur | +0.071 |
ind | +0.068 |
cker | +0.067 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.036 |
contest | -0.034 |
apy | -0.034 |
tea | -0.033 |
Token | food |
Token ID | 2057 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
bur | +0.022 |
rying | +0.022 |
ppa | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.015 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
vows | +0.011 |
prize | +0.010 |
contest | +0.009 |
trophy | +0.009 |
apy | +0.009 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.009 |
ppa | -0.009 |
i | -0.009 |
ind | -0.008 |
Token | your |
Token ID | 534 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
rying | +0.059 |
bur | +0.057 |
ppa | +0.055 |
cker | +0.054 |
ety | +0.054 |
Neg logit contributions | |
vows | -0.049 |
prize | -0.048 |
contest | -0.045 |
apy | -0.044 |
trophy | -0.044 |
Token | tum |
Token ID | 11814 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
rying | +0.053 |
bur | +0.053 |
ppa | +0.052 |
ind | +0.050 |
i | +0.050 |
Neg logit contributions | |
vows | -0.042 |
prize | -0.038 |
contest | -0.037 |
trophy | -0.036 |
joke | -0.035 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
bur | +0.053 |
rying | +0.053 |
ppa | +0.052 |
ind | +0.049 |
i | +0.047 |
Neg logit contributions | |
vows | -0.053 |
prize | -0.050 |
contest | -0.050 |
trophy | -0.050 |
apy | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.013 |
i | +0.013 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
rying | +0.068 |
bur | +0.067 |
ppa | +0.066 |
i | +0.065 |
ior | +0.064 |
Neg logit contributions | |
vows | -0.040 |
contest | -0.035 |
prize | -0.035 |
trophy | -0.034 |
apy | -0.034 |
Token | sad |
Token ID | 6507 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
ind | +0.008 |
i | +0.008 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
bur | +0.040 |
ppa | +0.039 |
rying | +0.038 |
ind | +0.037 |
ety | +0.036 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.027 |
trophy | -0.026 |
contest | -0.026 |
apy | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
rying | +0.075 |
ind | +0.073 |
bur | +0.073 |
ppa | +0.072 |
ishing | +0.070 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.041 |
trophy | -0.040 |
apy | -0.040 |
contest | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
bur | +0.038 |
rying | +0.038 |
ppa | +0.036 |
ind | +0.036 |
i | +0.034 |
Neg logit contributions | |
vows | -0.036 |
prize | -0.032 |
trophy | -0.031 |
contest | -0.031 |
apy | -0.030 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rying | +0.021 |
bur | +0.021 |
ppa | +0.021 |
ind | +0.020 |
i | +0.020 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.019 |
contest | -0.019 |
trophy | -0.018 |
apy | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
rying | +0.069 |
ppa | +0.068 |
ind | +0.067 |
bur | +0.066 |
i | +0.064 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.042 |
contest | -0.041 |
trophy | -0.039 |
joke | -0.037 |
Token | hang |
Token ID | 8181 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
vows | +0.013 |
cakes | +0.011 |
contest | +0.011 |
apy | +0.011 |
prize | +0.011 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.019 |
i | -0.018 |
ind | -0.018 |
Token | out |
Token ID | 448 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
ind | +0.009 |
i | +0.009 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.008 |
Token | rock |
Token ID | 3881 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
i | +0.013 |
ind | +0.013 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
cakes | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
ppa | +0.066 |
bur | +0.066 |
rying | +0.064 |
ind | +0.064 |
ior | +0.063 |
Neg logit contributions | |
vows | -0.049 |
contest | -0.045 |
prize | -0.045 |
trophy | -0.044 |
cakes | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.019 |
i | +0.018 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.011 |
apy | -0.011 |
Token | lizard |
Token ID | 42406 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.018 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.015 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
vows | +0.051 |
cakes | +0.046 |
prize | +0.045 |
apy | +0.045 |
contest | +0.045 |
Neg logit contributions | |
i | -0.055 |
rying | -0.054 |
bur | -0.054 |
ppa | -0.052 |
cker | -0.052 |
Token | green |
Token ID | 4077 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
rying | +0.058 |
bur | +0.057 |
ppa | +0.056 |
ior | +0.054 |
ind | +0.054 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.035 |
contest | -0.034 |
trophy | -0.034 |
apy | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
ppa | +0.066 |
bur | +0.066 |
rying | +0.064 |
ind | +0.061 |
ior | +0.060 |
Neg logit contributions | |
vows | -0.047 |
prize | -0.045 |
trophy | -0.044 |
contest | -0.043 |
are | -0.041 |
Token | has |
Token ID | 468 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
bur | +0.022 |
rying | +0.022 |
ppa | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
rying | +0.031 |
bur | +0.031 |
ppa | +0.030 |
ind | +0.029 |
i | +0.029 |
Neg logit contributions | |
vows | -0.019 |
prize | -0.017 |
contest | -0.016 |
trophy | -0.016 |
apy | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
vows | +0.007 |
contest | +0.006 |
cakes | +0.006 |
prize | +0.006 |
trophy | +0.006 |
Neg logit contributions | |
bur | -0.010 |
rying | -0.010 |
ppa | -0.010 |
ind | -0.009 |
i | -0.009 |
Token | tail |
Token ID | 7894 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
rying | +0.055 |
bur | +0.054 |
ppa | +0.053 |
ind | +0.051 |
ior | +0.049 |
Neg logit contributions | |
vows | -0.052 |
prize | -0.047 |
trophy | -0.046 |
contest | -0.045 |
apy | -0.045 |
Token | surface |
Token ID | 4417 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
bur | +0.022 |
rying | +0.021 |
ppa | +0.021 |
i | +0.020 |
ind | +0.020 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.013 |
trophy | -0.013 |
apy | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.016 |
ppa | +0.016 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.018 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
cakes | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.019 |
ind | +0.019 |
i | +0.018 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.015 |
apy | -0.015 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
vows | +0.044 |
cakes | +0.039 |
Mine | +0.039 |
prize | +0.038 |
contest | +0.038 |
Neg logit contributions | |
rying | -0.051 |
i | -0.050 |
ppa | -0.050 |
bur | -0.048 |
ener | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
bur | +0.109 |
umper | +0.107 |
ppa | +0.105 |
ind | +0.105 |
rying | +0.103 |
Neg logit contributions | |
vows | -0.061 |
prize | -0.053 |
contest | -0.048 |
trophy | -0.047 |
they | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
rying | +0.053 |
ppa | +0.053 |
bur | +0.053 |
ind | +0.052 |
ety | +0.050 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.026 |
trophy | -0.025 |
contest | -0.024 |
are | -0.022 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
vows | +0.021 |
cakes | +0.018 |
apy | +0.018 |
ades | +0.017 |
contest | +0.017 |
Neg logit contributions | |
rying | -0.026 |
bur | -0.026 |
ppa | -0.025 |
i | -0.025 |
ind | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.009 |
ind | +0.009 |
i | +0.009 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | off |
Token ID | 572 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
vows | +0.015 |
contest | +0.014 |
prize | +0.014 |
trophy | +0.013 |
apy | +0.013 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.010 |
i | -0.010 |
ind | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
bur | +0.099 |
rying | +0.099 |
umper | +0.096 |
ppa | +0.095 |
ind | +0.095 |
Neg logit contributions | |
vows | -0.063 |
prize | -0.052 |
contest | -0.048 |
trophy | -0.048 |
cakes | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
bur | +0.001 |
rying | +0.001 |
ppa | +0.001 |
i | +0.001 |
ind | +0.001 |
Neg logit contributions | |
vows | -0.001 |
prize | -0.001 |
contest | -0.001 |
trophy | -0.001 |
cakes | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.018 |
ppa | +0.018 |
ind | +0.017 |
i | +0.017 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.015 |
apy | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
bur | +0.027 |
ppa | +0.027 |
rying | +0.027 |
i | +0.026 |
ind | +0.026 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.027 |
contest | -0.026 |
trophy | -0.026 |
cakes | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
ind | +0.008 |
i | +0.008 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.007 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | way |
Token ID | 835 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
rying | +0.044 |
bur | +0.043 |
ppa | +0.043 |
i | +0.041 |
ind | +0.041 |
Neg logit contributions | |
vows | -0.032 |
prize | -0.029 |
contest | -0.028 |
trophy | -0.028 |
joke | -0.026 |
Token | feeling |
Token ID | 4203 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ppa | +0.060 |
bur | +0.060 |
rying | +0.059 |
ind | +0.058 |
ior | +0.058 |
Neg logit contributions | |
vows | -0.036 |
prize | -0.034 |
trophy | -0.032 |
contest | -0.032 |
apy | -0.030 |
Token | strong |
Token ID | 1913 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.010 |
ind | +0.010 |
i | +0.010 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ppa | +0.134 |
bur | +0.133 |
ety | +0.127 |
ind | +0.126 |
rying | +0.125 |
Neg logit contributions | |
prize | -0.066 |
vows | -0.066 |
contest | -0.061 |
are | -0.061 |
trophy | -0.060 |
Token | full |
Token ID | 1336 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
bur | +0.110 |
ppa | +0.109 |
ind | +0.106 |
umper | +0.105 |
rying | +0.103 |
Neg logit contributions | |
vows | -0.062 |
apy | -0.057 |
prize | -0.056 |
contest | -0.055 |
laugh | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
trophy | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.011 |
i | -0.011 |
ind | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.003 |
trophy | +0.003 |
apy | +0.003 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.003 |
i | -0.003 |
ind | -0.003 |
Token | Jack |
Token ID | 3619 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
vows | +0.089 |
prize | +0.079 |
ves | +0.075 |
apy | +0.074 |
trophy | +0.073 |
Neg logit contributions | |
my | -0.072 |
ior | -0.066 |
ety | -0.065 |
bur | -0.064 |
umper | -0.060 |
Token | y |
Token ID | 88 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
rying | +0.019 |
bur | +0.019 |
ppa | +0.018 |
ind | +0.018 |
i | +0.017 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
cakes | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
vows | +0.046 |
prize | +0.043 |
contest | +0.042 |
apy | +0.041 |
trophy | +0.041 |
Neg logit contributions | |
i | -0.039 |
ppa | -0.039 |
bur | -0.038 |
rying | -0.038 |
my | -0.037 |
Token | excited |
Token ID | 6568 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
vows | +0.029 |
prize | +0.025 |
ades | +0.024 |
cakes | +0.024 |
trophy | +0.024 |
Neg logit contributions | |
bur | -0.026 |
rying | -0.026 |
ppa | -0.026 |
i | -0.025 |
my | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
bur | +0.034 |
ppa | +0.034 |
rying | +0.034 |
ind | +0.033 |
cker | +0.032 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.027 |
contest | -0.027 |
trophy | -0.026 |
cakes | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
vows | +0.042 |
prize | +0.038 |
contest | +0.037 |
trophy | +0.036 |
apy | +0.035 |
Neg logit contributions | |
bur | -0.038 |
my | -0.038 |
ety | -0.037 |
ior | -0.037 |
rying | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
vows | +0.025 |
prize | +0.022 |
trophy | +0.021 |
contest | +0.021 |
Prize | +0.020 |
Neg logit contributions | |
bur | -0.030 |
ppa | -0.028 |
rying | -0.028 |
ind | -0.028 |
i | -0.028 |
Token | Jack |
Token ID | 14295 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
vows | +0.059 |
prize | +0.054 |
apy | +0.050 |
contest | +0.049 |
Prize | +0.049 |
Neg logit contributions | |
my | -0.051 |
ind | -0.050 |
ppa | -0.049 |
bur | -0.048 |
ety | -0.047 |
Token | y |
Token ID | 88 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
rying | +0.055 |
bur | +0.051 |
ppa | +0.051 |
ind | +0.049 |
gie | +0.047 |
Neg logit contributions | |
vows | -0.085 |
trophy | -0.074 |
are | -0.074 |
contest | -0.074 |
cakes | -0.074 |
Token | took |
Token ID | 1718 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.014 |
contest | +0.013 |
trophy | +0.013 |
apy | +0.013 |
Neg logit contributions | |
bur | -0.012 |
ppa | -0.012 |
rying | -0.012 |
i | -0.011 |
ind | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
ind | +0.008 |
i | +0.008 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
cakes | -0.009 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
bur | +0.028 |
rying | +0.027 |
ppa | +0.027 |
ind | +0.027 |
i | +0.026 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.025 |
contest | -0.025 |
apy | -0.024 |
trophy | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.011 |
contest | +0.011 |
trophy | +0.011 |
cakes | +0.010 |
Neg logit contributions | |
bur | -0.017 |
ppa | -0.017 |
rying | -0.017 |
i | -0.017 |
ind | -0.016 |
Token | fluffy |
Token ID | 39145 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
vows | +0.063 |
cakes | +0.055 |
apy | +0.052 |
uits | +0.051 |
contest | +0.050 |
Neg logit contributions | |
ind | -0.085 |
bur | -0.083 |
owl | -0.082 |
ppa | -0.082 |
rying | -0.080 |
Token | brown |
Token ID | 7586 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
ind | +0.005 |
i | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | puppy |
Token ID | 26188 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
ind | +0.006 |
i | +0.006 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
vows | +0.002 |
prize | +0.002 |
contest | +0.002 |
trophy | +0.002 |
cakes | +0.002 |
Neg logit contributions | |
bur | -0.002 |
rying | -0.002 |
ppa | -0.002 |
i | -0.002 |
ind | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.012 |
apy | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
i | +0.006 |
ind | +0.006 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | puppy |
Token ID | 26188 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
ind | +0.005 |
i | +0.005 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | w |
Token ID | 266 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
vows | +0.027 |
contest | +0.024 |
prize | +0.024 |
trophy | +0.024 |
cakes | +0.023 |
Neg logit contributions | |
bur | -0.029 |
ppa | -0.028 |
i | -0.028 |
rying | -0.028 |
gie | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
bur | +0.027 |
rying | +0.026 |
ppa | +0.026 |
ind | +0.025 |
i | +0.025 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
cakes | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
bur | +0.030 |
rying | +0.030 |
ppa | +0.029 |
ind | +0.028 |
ety | +0.028 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.021 |
Token | kingdom |
Token ID | 13239 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
cakes | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
apy | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
rying | +0.047 |
bur | +0.047 |
ppa | +0.046 |
ind | +0.045 |
i | +0.044 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.023 |
contest | -0.023 |
trophy | -0.023 |
apy | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.015 |
cakes | -0.015 |
Token | loyal |
Token ID | 9112 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
bur | +0.032 |
rying | +0.031 |
ppa | +0.031 |
ind | +0.030 |
i | +0.030 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
bur | +0.044 |
rying | +0.043 |
ppa | +0.043 |
ind | +0.041 |
cker | +0.040 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.036 |
contest | -0.034 |
trophy | -0.034 |
cakes | -0.032 |
Token | brave |
Token ID | 14802 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
bur | +0.038 |
rying | +0.037 |
ppa | +0.036 |
ind | +0.035 |
i | +0.035 |
Neg logit contributions | |
vows | -0.032 |
prize | -0.029 |
contest | -0.028 |
trophy | -0.028 |
apy | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
bur | +0.079 |
ppa | +0.076 |
rying | +0.074 |
ind | +0.073 |
cker | +0.072 |
Neg logit contributions | |
vows | -0.061 |
prize | -0.056 |
trophy | -0.053 |
contest | -0.052 |
are | -0.049 |
Token | had |
Token ID | 550 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
bur | +0.046 |
rying | +0.045 |
ppa | +0.044 |
ind | +0.043 |
i | +0.042 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.033 |
contest | -0.032 |
trophy | -0.032 |
apy | -0.032 |
Token | trusts |
Token ID | 31976 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
vows | +0.038 |
apy | +0.035 |
prize | +0.034 |
contest | +0.033 |
trophy | +0.033 |
Neg logit contributions | |
bur | -0.039 |
rying | -0.038 |
i | -0.038 |
my | -0.038 |
ior | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
rying | +0.087 |
ind | +0.084 |
ppa | +0.083 |
bur | +0.081 |
cker | +0.081 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.027 |
contest | -0.026 |
trophy | -0.024 |
tea | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
apy | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
trophy | +0.007 |
ades | +0.006 |
Neg logit contributions | |
bur | -0.006 |
rying | -0.006 |
ppa | -0.006 |
ety | -0.006 |
ior | -0.006 |
Token | moves |
Token ID | 6100 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
vows | +0.073 |
apy | +0.072 |
contest | +0.068 |
prize | +0.067 |
cakes | +0.067 |
Neg logit contributions | |
bur | -0.062 |
i | -0.062 |
rying | -0.059 |
ppa | -0.058 |
my | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
rying | +0.029 |
bur | +0.029 |
ppa | +0.028 |
i | +0.027 |
ind | +0.027 |
Neg logit contributions | |
vows | -0.030 |
prize | -0.028 |
trophy | -0.027 |
contest | -0.027 |
joke | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
bur | +0.060 |
ppa | +0.059 |
rying | +0.058 |
ind | +0.057 |
i | +0.055 |
Neg logit contributions | |
vows | -0.045 |
contest | -0.041 |
prize | -0.041 |
trophy | -0.040 |
apy | -0.039 |
Token | shows |
Token ID | 2523 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.012 |
contest | +0.012 |
cakes | +0.012 |
trophy | +0.012 |
Neg logit contributions | |
bur | -0.017 |
rying | -0.017 |
ppa | -0.016 |
i | -0.016 |
ind | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.013 |
ind | +0.013 |
i | +0.013 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.008 |
cakes | -0.008 |
Token | work |
Token ID | 670 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
vows | +0.006 |
contest | +0.006 |
prize | +0.005 |
cakes | +0.005 |
trophy | +0.005 |
Neg logit contributions | |
bur | -0.007 |
rying | -0.007 |
ppa | -0.007 |
ind | -0.006 |
i | -0.006 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
vows | +0.086 |
cakes | +0.080 |
ades | +0.080 |
trophy | +0.078 |
prize | +0.078 |
Neg logit contributions | |
bur | -0.060 |
ppa | -0.058 |
i | -0.058 |
my | -0.058 |
rying | -0.057 |
Token | that |
Token ID | 326 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
vows | +0.045 |
Prize | +0.039 |
apy | +0.039 |
trophy | +0.038 |
ades | +0.038 |
Neg logit contributions | |
i | -0.057 |
rying | -0.055 |
bur | -0.054 |
ppa | -0.052 |
ety | -0.052 |
Token | Amy |
Token ID | 14235 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
vows | +0.087 |
ades | +0.084 |
cakes | +0.076 |
apy | +0.076 |
� | +0.073 |
Neg logit contributions | |
my | -0.111 |
i | -0.108 |
owl | -0.106 |
asking | -0.106 |
forth | -0.105 |
Token | helped |
Token ID | 4193 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
vows | +0.036 |
contest | +0.033 |
prize | +0.033 |
apy | +0.033 |
trophy | +0.033 |
Neg logit contributions | |
bur | -0.035 |
i | -0.035 |
ppa | -0.035 |
rying | -0.034 |
ind | -0.033 |
Token | them |
Token ID | 606 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
vows | +0.041 |
apy | +0.038 |
trophy | +0.036 |
Prize | +0.035 |
prize | +0.035 |
Neg logit contributions | |
rying | -0.043 |
bur | -0.043 |
i | -0.043 |
ppa | -0.042 |
my | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
vows | +0.093 |
apy | +0.081 |
cakes | +0.079 |
Prize | +0.078 |
contest | +0.077 |
Neg logit contributions | |
rying | -0.074 |
my | -0.068 |
bur | -0.066 |
i | -0.065 |
ety | -0.062 |
Token | play |
Token ID | 711 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
vows | +0.032 |
cakes | +0.029 |
apy | +0.028 |
contest | +0.027 |
prize | +0.026 |
Neg logit contributions | |
bur | -0.045 |
rying | -0.043 |
ppa | -0.042 |
i | -0.041 |
ind | -0.041 |
Token | together |
Token ID | 1978 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
vows | +0.147 |
apy | +0.133 |
cakes | +0.125 |
Prize | +0.122 |
ades | +0.118 |
Neg logit contributions | |
rying | -0.079 |
my | -0.070 |
ishing | -0.068 |
ind | -0.066 |
asking | -0.063 |
Token | again |
Token ID | 757 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
vows | +0.081 |
apy | +0.077 |
cakes | +0.074 |
ades | +0.070 |
Prize | +0.069 |
Neg logit contributions | |
rying | -0.055 |
i | -0.052 |
bur | -0.052 |
ppa | -0.050 |
ind | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
bur | +0.032 |
rying | +0.031 |
ppa | +0.031 |
ind | +0.030 |
i | +0.030 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
vows | +0.063 |
trophy | +0.057 |
prize | +0.057 |
contest | +0.055 |
ades | +0.054 |
Neg logit contributions | |
my | -0.063 |
bur | -0.062 |
ior | -0.062 |
ety | -0.060 |
rying | -0.058 |
Token | celebrate |
Token ID | 10648 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
vows | +0.014 |
apy | +0.012 |
cakes | +0.012 |
prize | +0.012 |
trophy | +0.012 |
Neg logit contributions | |
bur | -0.017 |
rying | -0.016 |
ppa | -0.016 |
ind | -0.015 |
i | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
vows | +0.065 |
apy | +0.060 |
contest | +0.057 |
Prize | +0.057 |
cakes | +0.057 |
Neg logit contributions | |
bur | -0.054 |
i | -0.053 |
ind | -0.052 |
rying | -0.052 |
ppa | -0.050 |
Token | him |
Token ID | 683 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
vows | +0.038 |
contest | +0.034 |
prize | +0.034 |
Prize | +0.034 |
cakes | +0.033 |
Neg logit contributions | |
bur | -0.037 |
ppa | -0.035 |
i | -0.035 |
ind | -0.034 |
my | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
vows | +0.064 |
apy | +0.058 |
contest | +0.057 |
cakes | +0.057 |
prize | +0.057 |
Neg logit contributions | |
bur | -0.050 |
i | -0.049 |
rying | -0.049 |
ppa | -0.048 |
my | -0.046 |
Token | They |
Token ID | 1119 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.020 |
apy | +0.020 |
trophy | +0.020 |
contest | +0.020 |
Neg logit contributions | |
bur | -0.034 |
ety | -0.032 |
ior | -0.031 |
rying | -0.031 |
ppa | -0.031 |
Token | played |
Token ID | 2826 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
vows | +0.073 |
apy | +0.072 |
ades | +0.072 |
prize | +0.071 |
cakes | +0.069 |
Neg logit contributions | |
i | -0.081 |
bur | -0.081 |
my | -0.079 |
ppa | -0.079 |
rying | -0.074 |
Token | games |
Token ID | 1830 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
vows | +0.134 |
apy | +0.122 |
Mine | +0.113 |
cakes | +0.112 |
disco | +0.110 |
Neg logit contributions | |
rying | -0.106 |
my | -0.106 |
forth | -0.106 |
ping | -0.106 |
ior | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
vows | +0.135 |
apy | +0.132 |
Mine | +0.127 |
ades | +0.118 |
Prize | +0.118 |
Neg logit contributions | |
my | -0.064 |
bur | -0.062 |
rying | -0.060 |
i | -0.054 |
ppa | -0.054 |
Token | ate |
Token ID | 15063 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.021 |
trophy | +0.020 |
ades | +0.020 |
contest | +0.020 |
Neg logit contributions | |
bur | -0.027 |
ppa | -0.026 |
rying | -0.026 |
i | -0.025 |
ety | -0.025 |
Token | cake |
Token ID | 12187 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
vows | +0.061 |
Prize | +0.052 |
contest | +0.050 |
apy | +0.049 |
case | +0.049 |
Neg logit contributions | |
bur | -0.078 |
ior | -0.076 |
ind | -0.074 |
i | -0.073 |
my | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
vows | +0.091 |
Mine | +0.089 |
Prize | +0.087 |
apy | +0.086 |
contest | +0.080 |
Neg logit contributions | |
bur | -0.086 |
i | -0.082 |
ppa | -0.080 |
my | -0.078 |
rying | -0.077 |
Token | who |
Token ID | 508 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
bur | +0.023 |
rying | +0.023 |
ppa | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.031 |
prize | -0.028 |
contest | -0.028 |
trophy | -0.027 |
apy | -0.027 |
Token | liked |
Token ID | 8288 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
vows | +0.097 |
prize | +0.095 |
trophy | +0.091 |
Prize | +0.090 |
ades | +0.090 |
Neg logit contributions | |
my | -0.077 |
i | -0.076 |
bur | -0.075 |
ety | -0.073 |
ppa | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
vows | +0.031 |
prize | +0.028 |
apy | +0.027 |
contest | +0.027 |
trophy | +0.027 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.022 |
ind | -0.021 |
ppa | -0.021 |
i | -0.021 |
Token | play |
Token ID | 711 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
vows | +0.073 |
cakes | +0.065 |
Prize | +0.062 |
prize | +0.062 |
ades | +0.062 |
Neg logit contributions | |
bur | -0.089 |
i | -0.087 |
my | -0.087 |
cker | -0.085 |
ety | -0.082 |
Token | outside |
Token ID | 2354 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
vows | +0.098 |
cakes | +0.084 |
Prize | +0.083 |
prize | +0.080 |
apy | +0.079 |
Neg logit contributions | |
rying | -0.051 |
ishing | -0.051 |
ind | -0.050 |
bur | -0.047 |
i | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.011 |
trophy | +0.010 |
cakes | +0.010 |
contest | +0.010 |
Neg logit contributions | |
rying | -0.011 |
bur | -0.010 |
i | -0.010 |
ind | -0.010 |
ppa | -0.010 |
Token | One |
Token ID | 1881 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
vows | +0.093 |
apy | +0.092 |
ades | +0.090 |
prize | +0.090 |
trophy | +0.090 |
Neg logit contributions | |
ior | -0.070 |
my | -0.068 |
ety | -0.065 |
bur | -0.064 |
i | -0.061 |
Token | day |
Token ID | 1110 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.012 |
ppa | +0.012 |
ind | +0.011 |
i | +0.011 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.009 |
apy | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
vows | +0.081 |
trophy | +0.076 |
prize | +0.073 |
contest | +0.073 |
case | +0.071 |
Neg logit contributions | |
i | -0.071 |
bur | -0.067 |
my | -0.065 |
ety | -0.065 |
ppa | -0.064 |
Token | they |
Token ID | 484 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
vows | +0.060 |
trophy | +0.054 |
ades | +0.054 |
contest | +0.053 |
prize | +0.052 |
Neg logit contributions | |
i | -0.108 |
bur | -0.108 |
ety | -0.105 |
my | -0.104 |
ppa | -0.104 |
Token | went |
Token ID | 1816 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.012 |
trophy | +0.012 |
contest | +0.012 |
apy | +0.011 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.009 |
ppa | -0.009 |
i | -0.009 |
ety | -0.009 |
Token | apple |
Token ID | 17180 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
rying | +0.024 |
bur | +0.023 |
ppa | +0.023 |
ind | +0.022 |
i | +0.022 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
cakes | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
vows | +0.071 |
Prize | +0.063 |
ades | +0.060 |
prize | +0.060 |
trophy | +0.060 |
Neg logit contributions | |
bur | -0.064 |
i | -0.063 |
my | -0.060 |
cker | -0.060 |
ppa | -0.059 |
Token | not |
Token ID | 407 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.015 |
ppa | +0.015 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | y |
Token ID | 331 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
bur | +0.033 |
rying | +0.033 |
ppa | +0.032 |
ind | +0.032 |
i | +0.031 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.019 |
contest | -0.018 |
trophy | -0.018 |
apy | -0.017 |
Token | ummy |
Token ID | 13513 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
bur | +0.004 |
rying | +0.004 |
ppa | +0.004 |
ind | +0.004 |
i | +0.004 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
vows | +0.000 |
prize | +0.000 |
contest | +0.000 |
trophy | +0.000 |
apy | +0.000 |
Neg logit contributions | |
bur | -0.000 |
rying | -0.000 |
ppa | -0.000 |
i | -0.000 |
ind | -0.000 |
Token | It |
Token ID | 632 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
vows | +0.102 |
trophy | +0.098 |
prize | +0.097 |
ades | +0.096 |
contest | +0.094 |
Neg logit contributions | |
ior | -0.077 |
ppa | -0.074 |
Owl | -0.073 |
my | -0.070 |
ety | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
vows | +0.057 |
prize | +0.051 |
Prize | +0.051 |
ades | +0.050 |
contest | +0.050 |
Neg logit contributions | |
bur | -0.054 |
i | -0.053 |
my | -0.051 |
ety | -0.050 |
cker | -0.050 |
Token | bitter |
Token ID | 12922 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.009 |
ppa | +0.009 |
ind | +0.009 |
i | +0.009 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.008 |
ppa | +0.008 |
ind | +0.008 |
i | +0.008 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.008 |
Token | hard |
Token ID | 1327 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
vows | +0.011 |
prize | +0.010 |
contest | +0.010 |
trophy | +0.009 |
ades | +0.009 |
Neg logit contributions | |
bur | -0.013 |
rying | -0.013 |
ppa | -0.013 |
i | -0.013 |
ind | -0.012 |
Token | kept |
Token ID | 4030 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
vows | +0.033 |
prize | +0.030 |
contest | +0.029 |
trophy | +0.029 |
apy | +0.028 |
Neg logit contributions | |
bur | -0.035 |
i | -0.034 |
ppa | -0.034 |
rying | -0.034 |
ind | -0.032 |
Token | rubbing |
Token ID | 27714 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
bur | +0.004 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
ind | +0.075 |
bur | +0.074 |
rying | +0.073 |
ppa | +0.072 |
ior | +0.069 |
Neg logit contributions | |
vows | -0.059 |
contest | -0.056 |
apy | -0.055 |
prize | -0.054 |
trophy | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
bur | +0.044 |
rying | +0.043 |
ppa | +0.043 |
ind | +0.042 |
ior | +0.040 |
Neg logit contributions | |
vows | -0.042 |
apy | -0.038 |
contest | -0.038 |
prize | -0.037 |
trophy | -0.036 |
Token | colors |
Token ID | 7577 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
bur | +0.026 |
rying | +0.025 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.015 |
trophy | -0.015 |
cakes | -0.014 |
Token | started |
Token ID | 2067 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
vows | +0.107 |
Prize | +0.101 |
prize | +0.093 |
festival | +0.091 |
contest | +0.091 |
Neg logit contributions | |
i | -0.130 |
bur | -0.124 |
my | -0.123 |
rying | -0.122 |
cker | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
vows | +0.035 |
prize | +0.031 |
trophy | +0.031 |
contest | +0.031 |
Prize | +0.030 |
Neg logit contributions | |
rying | -0.027 |
bur | -0.027 |
i | -0.026 |
ppa | -0.026 |
ind | -0.025 |
Token | look |
Token ID | 804 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
cakes | +0.010 |
contest | +0.010 |
trophy | +0.010 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.018 |
i | -0.018 |
cker | -0.018 |
Token | more |
Token ID | 517 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
vows | +0.029 |
prize | +0.026 |
contest | +0.026 |
Prize | +0.025 |
cakes | +0.025 |
Neg logit contributions | |
rying | -0.029 |
i | -0.027 |
bur | -0.027 |
ppa | -0.027 |
ind | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
bur | +0.049 |
rying | +0.047 |
ppa | +0.047 |
ind | +0.045 |
gie | +0.044 |
Neg logit contributions | |
vows | -0.032 |
prize | -0.029 |
trophy | -0.029 |
contest | -0.029 |
cakes | -0.027 |
Token | polite |
Token ID | 23507 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
bur | +0.066 |
ind | +0.064 |
rying | +0.063 |
ppa | +0.062 |
ior | +0.061 |
Neg logit contributions | |
vows | -0.046 |
prize | -0.045 |
contest | -0.044 |
trophy | -0.043 |
joke | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
rying | +0.031 |
bur | +0.031 |
ppa | +0.030 |
ind | +0.030 |
i | +0.030 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
cakes | -0.014 |
trophy | -0.013 |
Token | did |
Token ID | 750 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
rying | +0.047 |
bur | +0.046 |
ppa | +0.044 |
ind | +0.043 |
ior | +0.042 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.034 |
contest | -0.033 |
trophy | -0.033 |
joke | -0.032 |
Token | not |
Token ID | 407 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
vows | +0.044 |
cakes | +0.040 |
ades | +0.038 |
apy | +0.038 |
Prize | +0.038 |
Neg logit contributions | |
bur | -0.034 |
rying | -0.033 |
i | -0.033 |
ppa | -0.033 |
my | -0.031 |
Token | say |
Token ID | 910 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
vows | +0.003 |
prize | +0.003 |
contest | +0.003 |
apy | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.004 |
i | -0.004 |
ind | -0.004 |
Token | hello |
Token ID | 23748 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
vows | +0.116 |
cakes | +0.108 |
case | +0.103 |
apy | +0.102 |
Mine | +0.102 |
Neg logit contributions | |
owl | -0.082 |
Owl | -0.081 |
bur | -0.080 |
i | -0.078 |
ppa | -0.076 |
Token | or |
Token ID | 393 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.007 |
ppa | +0.007 |
ind | +0.007 |
i | +0.007 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.006 |
Token | please |
Token ID | 3387 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.009 |
ppa | +0.009 |
ind | +0.008 |
i | +0.008 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
vows | +0.041 |
cakes | +0.037 |
apy | +0.037 |
trophy | +0.036 |
prize | +0.036 |
Neg logit contributions | |
rying | -0.038 |
bur | -0.037 |
ppa | -0.036 |
i | -0.036 |
ety | -0.035 |
Token | thank |
Token ID | 5875 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |