Token | . |
Token ID | 13 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
ingu | +0.067 |
pistol | +0.064 |
tto | +0.061 |
ascal | +0.061 |
brand | +0.061 |
Neg logit contributions | |
Danger | -0.060 |
nine | -0.055 |
Ab | -0.054 |
thirteen | -0.053 |
arc | -0.051 |
Token | Eleven |
Token ID | 37339 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
nine | +0.009 |
thirteen | +0.009 |
Danger | +0.009 |
arc | +0.008 |
� | +0.008 |
Neg logit contributions | |
ingu | -0.008 |
hockey | -0.007 |
tto | -0.007 |
pistol | -0.007 |
brand | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
Danger | +0.064 |
nine | +0.060 |
� | +0.058 |
Ab | +0.056 |
thirteen | +0.055 |
Neg logit contributions | |
ingu | -0.096 |
tto | -0.089 |
affle | -0.087 |
pistol | -0.087 |
ascal | -0.087 |
Token | twelve |
Token ID | 14104 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Ab | +0.025 |
Danger | +0.024 |
Suz | +0.024 |
Jess | +0.022 |
adies | +0.022 |
Neg logit contributions | |
pron | -0.032 |
brand | -0.031 |
pistol | -0.030 |
hockey | -0.030 |
handsome | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Danger | +0.185 |
� | +0.164 |
Ab | +0.161 |
nine | +0.154 |
Sylv | +0.146 |
Neg logit contributions | |
ingu | -0.203 |
ravings | -0.191 |
affle | -0.186 |
brand | -0.183 |
pistol | -0.182 |
Token | thirteen |
Token ID | 28306 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Danger | +0.024 |
Ab | +0.023 |
Suz | +0.022 |
Jess | +0.020 |
Sylv | +0.018 |
Neg logit contributions | |
pron | -0.033 |
brand | -0.033 |
hockey | -0.032 |
pistol | -0.031 |
handsome | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
Danger | +0.290 |
� | +0.261 |
nine | +0.255 |
Ab | +0.246 |
arc | +0.225 |
Neg logit contributions | |
ingu | -0.450 |
tto | -0.427 |
ravings | -0.416 |
pistol | -0.414 |
ascal | -0.413 |
Token | fourteen |
Token ID | 29167 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Danger | +0.024 |
Ab | +0.020 |
� | +0.020 |
Suz | +0.018 |
Jess | +0.018 |
Neg logit contributions | |
ingu | -0.037 |
brand | -0.035 |
hockey | -0.034 |
pron | -0.034 |
pistol | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Danger | +0.282 |
� | +0.231 |
nine | +0.229 |
Ab | +0.221 |
arc | +0.209 |
Neg logit contributions | |
ingu | -0.315 |
pistol | -0.290 |
brand | -0.289 |
ravings | -0.276 |
tto | -0.276 |
Token | fifteen |
Token ID | 17280 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
Danger | +0.026 |
Ab | +0.023 |
Suz | +0.022 |
Jess | +0.021 |
Sylv | +0.020 |
Neg logit contributions | |
ingu | -0.034 |
brand | -0.033 |
hockey | -0.032 |
pistol | -0.031 |
cowboy | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
Danger | +0.115 |
� | +0.100 |
Ab | +0.096 |
nine | +0.092 |
arc | +0.086 |
Neg logit contributions | |
ingu | -0.144 |
ravings | -0.131 |
tto | -0.130 |
affle | -0.130 |
brand | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Danger | +0.021 |
� | +0.018 |
Ab | +0.017 |
Sylv | +0.017 |
arc | +0.017 |
Neg logit contributions | |
ingu | -0.021 |
ittens | -0.020 |
ravings | -0.020 |
affle | -0.020 |
ishing | -0.020 |
Token | eleven |
Token ID | 22216 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Danger | +0.016 |
arc | +0.014 |
Ab | +0.013 |
Flowers | +0.013 |
Sylv | +0.013 |
Neg logit contributions | |
hockey | -0.019 |
cowboy | -0.018 |
pistol | -0.018 |
Years | -0.018 |
helmet | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Danger | +0.180 |
� | +0.156 |
nine | +0.143 |
thirteen | +0.137 |
Ab | +0.134 |
Neg logit contributions | |
ingu | -0.160 |
uddle | -0.155 |
ravings | -0.155 |
ittens | -0.153 |
ishing | -0.149 |
Token | twelve |
Token ID | 14104 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Danger | +0.016 |
Suz | +0.013 |
Ab | +0.013 |
Sylv | +0.012 |
Fourth | +0.012 |
Neg logit contributions | |
hockey | -0.020 |
pistol | -0.018 |
brand | -0.018 |
cowboy | -0.018 |
ingu | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Danger | +0.209 |
� | +0.170 |
Ev | +0.155 |
Ab | +0.154 |
nine | +0.154 |
Neg logit contributions | |
ingu | -0.165 |
ravings | -0.159 |
uddle | -0.155 |
ishing | -0.154 |
affle | -0.154 |
Token | thirteen |
Token ID | 28306 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Danger | +0.016 |
Ab | +0.013 |
Suz | +0.013 |
adies | +0.012 |
Ev | +0.011 |
Neg logit contributions | |
hockey | -0.021 |
brand | -0.020 |
ingu | -0.020 |
pistol | -0.020 |
zed | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Danger | +0.309 |
� | +0.268 |
nine | +0.256 |
Ab | +0.249 |
arc | +0.233 |
Neg logit contributions | |
ingu | -0.433 |
tto | -0.415 |
ravings | -0.402 |
affle | -0.400 |
ascal | -0.398 |
Token | fourteen |
Token ID | 29167 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Danger | +0.017 |
� | +0.013 |
Ab | +0.012 |
Suz | +0.012 |
arc | +0.012 |
Neg logit contributions | |
ingu | -0.026 |
ip | -0.023 |
tto | -0.023 |
zed | -0.023 |
brand | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
Danger | +0.287 |
nine | +0.227 |
� | +0.226 |
Ab | +0.219 |
arc | +0.211 |
Neg logit contributions | |
ingu | -0.300 |
pistol | -0.276 |
brand | -0.276 |
tto | -0.266 |
ravings | -0.264 |
Token | fifteen |
Token ID | 17280 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
Danger | +0.017 |
Ab | +0.015 |
Suz | +0.014 |
Jess | +0.013 |
arc | +0.013 |
Neg logit contributions | |
ingu | -0.024 |
brand | -0.022 |
pistol | -0.022 |
hockey | -0.022 |
cowboy | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Danger | +0.126 |
� | +0.103 |
Ab | +0.098 |
nine | +0.093 |
Ev | +0.092 |
Neg logit contributions | |
ingu | -0.124 |
affle | -0.115 |
ravings | -0.115 |
iflower | -0.112 |
brand | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Danger | +0.021 |
� | +0.019 |
Ab | +0.019 |
nine | +0.017 |
Sylv | +0.017 |
Neg logit contributions | |
ingu | -0.022 |
ravings | -0.021 |
ascal | -0.020 |
pistol | -0.020 |
affle | -0.020 |
Token | eleven |
Token ID | 22216 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Danger | +0.019 |
Suz | +0.017 |
Ab | +0.016 |
� | +0.015 |
arc | +0.015 |
Neg logit contributions | |
Years | -0.019 |
hockey | -0.018 |
cowboy | -0.017 |
brand | -0.016 |
Days | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Danger | +0.153 |
� | +0.140 |
nine | +0.130 |
Ab | +0.130 |
thirteen | +0.122 |
Neg logit contributions | |
ingu | -0.205 |
ravings | -0.188 |
tto | -0.186 |
pistol | -0.184 |
brand | -0.184 |
Token | twelve |
Token ID | 14104 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Danger | +0.019 |
Ab | +0.017 |
Suz | +0.017 |
Sylv | +0.015 |
Jess | +0.014 |
Neg logit contributions | |
brand | -0.019 |
hockey | -0.018 |
Years | -0.018 |
pron | -0.017 |
zed | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Danger | +0.188 |
� | +0.162 |
Ab | +0.156 |
nine | +0.145 |
Sylv | +0.142 |
Neg logit contributions | |
ingu | -0.205 |
ravings | -0.189 |
brand | -0.185 |
affle | -0.182 |
pistol | -0.180 |
Token | thirteen |
Token ID | 28306 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Danger | +0.019 |
Ab | +0.016 |
Suz | +0.016 |
� | +0.014 |
Sylv | +0.014 |
Neg logit contributions | |
brand | -0.020 |
hockey | -0.019 |
ingu | -0.019 |
Years | -0.019 |
zed | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Danger | +0.303 |
� | +0.270 |
nine | +0.259 |
Ab | +0.254 |
arc | +0.234 |
Neg logit contributions | |
ingu | -0.436 |
tto | -0.413 |
ravings | -0.403 |
ascal | -0.400 |
affle | -0.398 |
Token | fourteen |
Token ID | 29167 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Danger | +0.018 |
� | +0.014 |
Ab | +0.014 |
Suz | +0.013 |
Sylv | +0.012 |
Neg logit contributions | |
ingu | -0.026 |
brand | -0.023 |
zed | -0.023 |
hockey | -0.022 |
udd | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Danger | +0.283 |
� | +0.226 |
Ab | +0.223 |
nine | +0.216 |
adies | +0.204 |
Neg logit contributions | |
ingu | -0.308 |
brand | -0.284 |
pistol | -0.279 |
ravings | -0.270 |
tto | -0.267 |
Token | fifteen |
Token ID | 17280 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
Danger | +0.019 |
Ab | +0.018 |
Suz | +0.016 |
Jess | +0.016 |
Sylv | +0.016 |
Neg logit contributions | |
ingu | -0.023 |
brand | -0.022 |
hockey | -0.021 |
pistol | -0.020 |
handsome | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Danger | +0.111 |
� | +0.097 |
Ab | +0.094 |
nine | +0.088 |
Sylv | +0.082 |
Neg logit contributions | |
ingu | -0.139 |
ravings | -0.127 |
brand | -0.126 |
affle | -0.126 |
tto | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +8.54e-05 |
Pos logit contributions | |
Ab | +0.014 |
thirteen | +0.013 |
nine | +0.013 |
Danger | +0.013 |
� | +0.012 |
Neg logit contributions | |
pistol | -0.011 |
ingu | -0.011 |
ravings | -0.010 |
hockey | -0.010 |
brand | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
� | +0.000 |
nine | +0.000 |
Danger | +0.000 |
thirteen | +0.000 |
arc | +0.000 |
Neg logit contributions | |
ingu | -0.000 |
pistol | -0.000 |
ravings | -0.000 |
tto | -0.000 |
affle | -0.000 |
Token | says |
Token ID | 1139 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ingu | +0.077 |
tto | +0.074 |
pistol | +0.073 |
brand | +0.071 |
ravings | +0.071 |
Neg logit contributions | |
Danger | -0.050 |
nine | -0.047 |
Ab | -0.046 |
� | -0.046 |
thirteen | -0.043 |
Token | " |
Token ID | 366 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Danger | +0.094 |
nine | +0.092 |
� | +0.091 |
thirteen | +0.085 |
arc | +0.085 |
Neg logit contributions | |
ingu | -0.101 |
tto | -0.095 |
pistol | -0.094 |
ascal | -0.092 |
brand | -0.091 |
Token | L |
Token ID | 43 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
tto | +0.035 |
ingu | +0.035 |
Years | +0.034 |
ascal | +0.034 |
pistol | +0.033 |
Neg logit contributions | |
nine | -0.031 |
Ab | -0.029 |
Danger | -0.029 |
thirteen | -0.028 |
Jen | -0.028 |
Token | adies |
Token ID | 50192 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
� | +0.032 |
nine | +0.028 |
arc | +0.028 |
thirteen | +0.027 |
Danger | +0.027 |
Neg logit contributions | |
affle | -0.036 |
tto | -0.034 |
ingu | -0.034 |
ascal | -0.032 |
ogo | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Danger | +0.318 |
� | +0.305 |
nine | +0.289 |
thirteen | +0.278 |
Ab | +0.273 |
Neg logit contributions | |
ingu | -0.401 |
tto | -0.373 |
ascal | -0.372 |
ravings | -0.370 |
pistol | -0.365 |
Token | gentlemen |
Token ID | 28527 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ingu | +0.015 |
pistol | +0.014 |
hockey | +0.013 |
handsome | +0.013 |
brand | +0.013 |
Neg logit contributions | |
Danger | -0.016 |
arc | -0.015 |
Ab | -0.015 |
thirteen | -0.014 |
ago | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Danger | +0.144 |
Ab | +0.135 |
thirteen | +0.131 |
arc | +0.129 |
nine | +0.128 |
Neg logit contributions | |
ingu | -0.180 |
affle | -0.159 |
tto | -0.159 |
pistol | -0.157 |
ravings | -0.156 |
Token | boys |
Token ID | 6510 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
arc | +0.021 |
Danger | +0.020 |
thirteen | +0.019 |
ind | +0.019 |
Ab | +0.018 |
Neg logit contributions | |
ingu | -0.032 |
pistol | -0.029 |
hockey | -0.029 |
cowboy | -0.028 |
brand | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
Danger | +0.019 |
thirteen | +0.017 |
Ab | +0.016 |
� | +0.016 |
nine | +0.016 |
Neg logit contributions | |
ingu | -0.022 |
tto | -0.020 |
pistol | -0.020 |
affle | -0.020 |
ravings | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ingu | +0.034 |
tto | +0.034 |
ravings | +0.033 |
ascal | +0.033 |
affle | +0.033 |
Neg logit contributions | |
� | -0.016 |
nine | -0.016 |
Danger | -0.016 |
Ab | -0.014 |
Jen | -0.014 |
Token | hand |
Token ID | 1021 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
Danger | +0.056 |
nine | +0.054 |
� | +0.053 |
thirteen | +0.051 |
Ab | +0.050 |
Neg logit contributions | |
ingu | -0.055 |
tto | -0.052 |
pistol | -0.050 |
ravings | -0.049 |
ascal | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
Danger | +0.008 |
nine | +0.007 |
thirteen | +0.007 |
arc | +0.006 |
� | +0.006 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.009 |
pistol | -0.009 |
brand | -0.008 |
pron | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
Danger | +0.030 |
thirteen | +0.030 |
nine | +0.030 |
arc | +0.028 |
paint | +0.026 |
Neg logit contributions | |
ingu | -0.038 |
tto | -0.034 |
brand | -0.034 |
ravings | -0.034 |
hockey | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ingu | +0.029 |
tto | +0.028 |
ascal | +0.027 |
ravings | +0.026 |
pistol | +0.026 |
Neg logit contributions | |
Danger | -0.027 |
nine | -0.026 |
thirteen | -0.025 |
� | -0.025 |
Ab | -0.024 |
Token | CR |
Token ID | 9419 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
tto | +0.029 |
Years | +0.028 |
ingu | +0.027 |
scar | +0.027 |
pron | +0.027 |
Neg logit contributions | |
thirteen | -0.031 |
Danger | -0.031 |
nine | -0.031 |
Ab | -0.031 |
arc | -0.030 |
Token | ASH |
Token ID | 11211 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Danger | +0.309 |
� | +0.270 |
Ab | +0.260 |
thirteen | +0.260 |
volcan | +0.249 |
Neg logit contributions | |
ingu | -0.389 |
ravings | -0.372 |
tto | -0.367 |
pistol | -0.366 |
ascal | -0.360 |
Token | ! |
Token ID | 0 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Danger | +0.026 |
nine | +0.025 |
� | +0.023 |
thirteen | +0.023 |
Ab | +0.023 |
Neg logit contributions | |
ingu | -0.028 |
tto | -0.027 |
ravings | -0.026 |
pistol | -0.025 |
brand | -0.025 |
Token | The |
Token ID | 383 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ingu | +0.036 |
tto | +0.035 |
pistol | +0.033 |
pron | +0.033 |
hockey | +0.033 |
Neg logit contributions | |
thirteen | -0.041 |
arc | -0.039 |
nine | -0.038 |
ind | -0.035 |
adies | -0.035 |
Token | tower |
Token ID | 10580 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Danger | +0.034 |
� | +0.032 |
nine | +0.031 |
Ab | +0.030 |
thirteen | +0.029 |
Neg logit contributions | |
pistol | -0.034 |
ingu | -0.033 |
pron | -0.032 |
tto | -0.031 |
affle | -0.031 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Danger | +0.072 |
Ab | +0.069 |
nine | +0.066 |
Am | +0.063 |
adies | +0.062 |
Neg logit contributions | |
pistol | -0.060 |
zed | -0.059 |
tto | -0.059 |
brand | -0.059 |
uddle | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
Danger | +0.005 |
nine | +0.005 |
� | +0.004 |
thirteen | +0.004 |
Ab | +0.004 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.008 |
ascal | -0.008 |
pistol | -0.008 |
ravings | -0.008 |
Token | want |
Token ID | 765 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
ingu | +0.017 |
pistol | +0.016 |
affle | +0.015 |
cowboy | +0.015 |
armor | +0.015 |
Neg logit contributions | |
Danger | -0.012 |
Ab | -0.012 |
Jen | -0.011 |
arc | -0.011 |
nine | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
� | +0.153 |
Danger | +0.148 |
thirteen | +0.148 |
nine | +0.145 |
arc | +0.145 |
Neg logit contributions | |
ingu | -0.106 |
pistol | -0.100 |
brand | -0.099 |
ravings | -0.091 |
Years | -0.089 |
Token | write |
Token ID | 3551 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
thirteen | +0.012 |
nine | +0.012 |
� | +0.012 |
Ab | +0.012 |
Danger | +0.011 |
Neg logit contributions | |
ingu | -0.014 |
pistol | -0.013 |
brand | -0.012 |
pron | -0.012 |
affle | -0.012 |
Token | about |
Token ID | 546 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
ingu | +0.130 |
brand | +0.125 |
pistol | +0.125 |
tto | +0.120 |
pron | +0.118 |
Neg logit contributions | |
Danger | -0.107 |
nine | -0.101 |
� | -0.099 |
Ab | -0.097 |
thirteen | -0.093 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
brand | +0.087 |
pistol | +0.086 |
ingu | +0.084 |
hockey | +0.076 |
steak | +0.075 |
Neg logit contributions | |
� | -0.093 |
Danger | -0.092 |
thirteen | -0.089 |
nine | -0.088 |
arc | -0.083 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
Danger | +0.181 |
nine | +0.175 |
� | +0.171 |
Ab | +0.153 |
thirteen | +0.147 |
Neg logit contributions | |
ingu | -0.534 |
tto | -0.512 |
ascal | -0.504 |
ravings | -0.496 |
pistol | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
Danger | +0.058 |
nine | +0.053 |
Ab | +0.052 |
thirteen | +0.050 |
� | +0.050 |
Neg logit contributions | |
ingu | -0.064 |
pistol | -0.063 |
tto | -0.059 |
ascal | -0.058 |
ravings | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Danger | +0.007 |
nine | +0.007 |
� | +0.006 |
thirteen | +0.006 |
Ab | +0.006 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.009 |
pistol | -0.008 |
ascal | -0.008 |
ravings | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ingu | +0.033 |
ravings | +0.032 |
ascal | +0.031 |
pistol | +0.031 |
tto | +0.030 |
Neg logit contributions | |
� | -0.015 |
Danger | -0.014 |
nine | -0.013 |
Ab | -0.012 |
Jen | -0.012 |
Token | They |
Token ID | 2990 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
tto | +0.023 |
ingu | +0.023 |
pron | +0.021 |
Years | +0.021 |
scar | +0.021 |
Neg logit contributions | |
Danger | -0.022 |
nine | -0.021 |
Ab | -0.021 |
thirteen | -0.021 |
arc | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Danger | +0.096 |
� | +0.086 |
nine | +0.086 |
Ab | +0.081 |
thirteen | +0.079 |
Neg logit contributions | |
ingu | -0.136 |
tto | -0.130 |
ravings | -0.128 |
affle | -0.127 |
ascal | -0.127 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Danger | +0.031 |
Ab | +0.026 |
otion | +0.024 |
Suz | +0.024 |
Ev | +0.023 |
Neg logit contributions | |
cowboy | -0.036 |
brand | -0.035 |
hockey | -0.035 |
pistol | -0.034 |
helmet | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
Danger | +0.213 |
nine | +0.190 |
� | +0.189 |
Ab | +0.180 |
thirteen | +0.177 |
Neg logit contributions | |
ingu | -0.310 |
tto | -0.296 |
ravings | -0.291 |
affle | -0.289 |
ascal | -0.288 |
Token | eight |
Token ID | 3624 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
Danger | +0.028 |
Ab | +0.025 |
arc | +0.023 |
Fourth | +0.023 |
Suz | +0.023 |
Neg logit contributions | |
cowboy | -0.037 |
ingu | -0.036 |
pistol | -0.036 |
hockey | -0.036 |
brand | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Danger | +0.146 |
Ab | +0.125 |
� | +0.125 |
nine | +0.123 |
arc | +0.121 |
Neg logit contributions | |
ingu | -0.159 |
pistol | -0.151 |
ravings | -0.150 |
affle | -0.150 |
tto | -0.148 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Danger | +0.026 |
Ab | +0.021 |
arc | +0.020 |
Suz | +0.020 |
Sylv | +0.019 |
Neg logit contributions | |
Years | -0.039 |
cowboy | -0.038 |
hockey | -0.038 |
helmet | -0.037 |
zed | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
Danger | +0.340 |
� | +0.301 |
Ab | +0.285 |
nine | +0.285 |
arc | +0.280 |
Neg logit contributions | |
ingu | -0.347 |
ravings | -0.331 |
affle | -0.326 |
zed | -0.319 |
ittens | -0.318 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
arc | +0.030 |
Danger | +0.029 |
� | +0.027 |
Ab | +0.027 |
Flowers | +0.026 |
Neg logit contributions | |
Years | -0.035 |
cowboy | -0.033 |
ingu | -0.032 |
hockey | -0.032 |
Days | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
Danger | +0.026 |
� | +0.024 |
Ab | +0.022 |
nine | +0.022 |
arc | +0.022 |
Neg logit contributions | |
ingu | -0.032 |
affle | -0.030 |
tto | -0.030 |
ravings | -0.030 |
ascal | -0.030 |
Token | Ready |
Token ID | 23432 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ingu | +0.038 |
hockey | +0.035 |
Rudolph | +0.034 |
Jeremy | +0.032 |
Jeremy | +0.031 |
Neg logit contributions | |
paint | -0.030 |
arc | -0.029 |
spr | -0.027 |
ostr | -0.027 |
ind | -0.027 |
Token | or |
Token ID | 393 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
thirteen | +0.188 |
Danger | +0.185 |
arc | +0.180 |
� | +0.178 |
nine | +0.173 |
Neg logit contributions | |
ingu | -0.227 |
tto | -0.215 |
affle | -0.209 |
zed | -0.201 |
ravings | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
Danger | +0.132 |
nine | +0.128 |
Ab | +0.122 |
� | +0.122 |
thirteen | +0.114 |
Neg logit contributions | |
ingu | -0.171 |
pistol | -0.165 |
tto | -0.162 |
ravings | -0.160 |
ascal | -0.158 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
nine | +0.005 |
Danger | +0.005 |
thirteen | +0.005 |
� | +0.005 |
Ab | +0.004 |
Neg logit contributions | |
ingu | -0.007 |
brand | -0.007 |
ravings | -0.007 |
pistol | -0.007 |
tto | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
Danger | +0.006 |
Ab | +0.005 |
nine | +0.005 |
thirteen | +0.005 |
arc | +0.005 |
Neg logit contributions | |
ingu | -0.006 |
tto | -0.006 |
pistol | -0.006 |
ravings | -0.006 |
ascal | -0.006 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
tto | +0.019 |
ingu | +0.019 |
brand | +0.019 |
ravings | +0.018 |
ascal | +0.018 |
Neg logit contributions | |
nine | -0.011 |
Danger | -0.011 |
� | -0.011 |
Jen | -0.010 |
Ab | -0.010 |
Token | think |
Token ID | 892 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
pistol | +0.161 |
ingu | +0.160 |
affle | +0.145 |
handsome | +0.143 |
tto | +0.143 |
Neg logit contributions | |
Ab | -0.108 |
Danger | -0.104 |
Jen | -0.102 |
nine | -0.101 |
Sylv | -0.094 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Danger | +0.095 |
nine | +0.095 |
� | +0.090 |
thirteen | +0.089 |
arc | +0.086 |
Neg logit contributions | |
ingu | -0.106 |
pistol | -0.105 |
brand | -0.104 |
zed | -0.100 |
tto | -0.098 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Danger | +0.204 |
nine | +0.201 |
� | +0.196 |
Ab | +0.177 |
thirteen | +0.175 |
Neg logit contributions | |
ingu | -0.506 |
tto | -0.484 |
ascal | -0.475 |
pistol | -0.467 |
ravings | -0.467 |
Token | are |
Token ID | 389 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
nine | +0.026 |
Danger | +0.026 |
Ab | +0.024 |
thirteen | +0.021 |
� | +0.021 |
Neg logit contributions | |
ingu | -0.094 |
pistol | -0.092 |
tto | -0.091 |
brand | -0.089 |
ascal | -0.089 |
Token | cool |
Token ID | 3608 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
Danger | +0.180 |
nine | +0.174 |
� | +0.171 |
Ab | +0.165 |
arc | +0.160 |
Neg logit contributions | |
ingu | -0.153 |
tto | -0.143 |
pistol | -0.143 |
brand | -0.141 |
ascal | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
ingu | +0.013 |
pistol | +0.013 |
ravings | +0.012 |
brand | +0.012 |
ascal | +0.012 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.012 |
Ab | -0.012 |
� | -0.011 |
thirteen | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
Danger | +0.005 |
nine | +0.005 |
� | +0.004 |
thirteen | +0.004 |
Ab | +0.004 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.008 |
ascal | -0.008 |
pistol | -0.008 |
ravings | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
nine | +0.004 |
Danger | +0.004 |
� | +0.004 |
thirteen | +0.003 |
Ab | +0.003 |
Neg logit contributions | |
ingu | -0.008 |
tto | -0.008 |
pistol | -0.008 |
ravings | -0.008 |
ascal | -0.008 |
Token | book |
Token ID | 1492 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
Danger | +0.035 |
� | +0.034 |
nine | +0.034 |
Ab | +0.033 |
thirteen | +0.032 |
Neg logit contributions | |
ingu | -0.029 |
tto | -0.027 |
pistol | -0.027 |
brand | -0.026 |
ravings | -0.026 |
Token | has |
Token ID | 468 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
ingu | +0.018 |
pistol | +0.017 |
tto | +0.017 |
brand | +0.017 |
ravings | +0.016 |
Neg logit contributions | |
Danger | -0.013 |
Ab | -0.012 |
nine | -0.012 |
thirteen | -0.011 |
� | -0.011 |
Token | pictures |
Token ID | 5986 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Danger | +0.108 |
Ab | +0.106 |
� | +0.105 |
arc | +0.105 |
Suz | +0.097 |
Neg logit contributions | |
ingu | -0.082 |
brand | -0.079 |
pistol | -0.074 |
ravings | -0.071 |
zed | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
Danger | +0.106 |
Ab | +0.102 |
nine | +0.097 |
thirteen | +0.092 |
� | +0.091 |
Neg logit contributions | |
ingu | -0.115 |
brand | -0.114 |
pistol | -0.112 |
pron | -0.105 |
ravings | -0.105 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Danger | +0.144 |
� | +0.140 |
nine | +0.139 |
thirteen | +0.131 |
Ab | +0.129 |
Neg logit contributions | |
ingu | -0.172 |
pistol | -0.161 |
brand | -0.158 |
tto | -0.155 |
ascal | -0.154 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
Danger | +0.188 |
� | +0.179 |
nine | +0.179 |
Ab | +0.159 |
thirteen | +0.151 |
Neg logit contributions | |
ingu | -0.525 |
tto | -0.502 |
ascal | -0.494 |
ravings | -0.488 |
affle | -0.482 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
Danger | +0.054 |
nine | +0.052 |
Ab | +0.049 |
thirteen | +0.048 |
� | +0.047 |
Neg logit contributions | |
ingu | -0.067 |
pistol | -0.065 |
tto | -0.064 |
ravings | -0.062 |
brand | -0.061 |
Token | Vol |
Token ID | 4709 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
nine | +0.003 |
Danger | +0.003 |
� | +0.003 |
thirteen | +0.003 |
Ab | +0.003 |
Neg logit contributions | |
ingu | -0.006 |
ravings | -0.006 |
tto | -0.006 |
pistol | -0.006 |
brand | -0.006 |
Token | can |
Token ID | 5171 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
nine | +0.014 |
Ab | +0.013 |
Danger | +0.013 |
� | +0.013 |
thirteen | +0.012 |
Neg logit contributions | |
tto | -0.020 |
ingu | -0.020 |
ascal | -0.019 |
scar | -0.019 |
pistol | -0.019 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
thirteen | +0.124 |
nine | +0.120 |
Danger | +0.118 |
arc | +0.116 |
Ab | +0.112 |
Neg logit contributions | |
ingu | -0.142 |
pistol | -0.130 |
tto | -0.128 |
ravings | -0.125 |
ascal | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Danger | +0.094 |
nine | +0.084 |
� | +0.083 |
Ab | +0.076 |
thirteen | +0.076 |
Neg logit contributions | |
ingu | -0.138 |
tto | -0.133 |
ascal | -0.131 |
affle | -0.130 |
ravings | -0.129 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Danger | +0.028 |
Ab | +0.023 |
otion | +0.021 |
Sylv | +0.021 |
arc | +0.021 |
Neg logit contributions | |
brand | -0.037 |
pistol | -0.036 |
pron | -0.036 |
hockey | -0.036 |
cowboy | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Danger | +0.226 |
nine | +0.192 |
� | +0.191 |
arc | +0.182 |
Ab | +0.178 |
Neg logit contributions | |
ingu | -0.293 |
affle | -0.276 |
tto | -0.276 |
ravings | -0.276 |
ascal | -0.273 |
Token | eight |
Token ID | 3624 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Danger | +0.026 |
Ab | +0.022 |
adies | +0.021 |
Sylv | +0.021 |
arc | +0.021 |
Neg logit contributions | |
pistol | -0.037 |
ingu | -0.037 |
brand | -0.037 |
hockey | -0.037 |
pron | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Danger | +0.148 |
� | +0.120 |
arc | +0.119 |
nine | +0.119 |
Ab | +0.118 |
Neg logit contributions | |
ingu | -0.169 |
affle | -0.159 |
ravings | -0.159 |
ascal | -0.159 |
pistol | -0.158 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Danger | +0.027 |
Ab | +0.020 |
Sylv | +0.019 |
arc | +0.018 |
Warning | +0.018 |
Neg logit contributions | |
Years | -0.038 |
brand | -0.037 |
hockey | -0.036 |
ingu | -0.035 |
pron | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
Danger | +0.340 |
� | +0.280 |
nine | +0.275 |
arc | +0.273 |
Sylv | +0.268 |
Neg logit contributions | |
ingu | -0.350 |
ravings | -0.337 |
affle | -0.329 |
brand | -0.328 |
ascal | -0.324 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Danger | +0.028 |
arc | +0.025 |
Sylv | +0.024 |
Ab | +0.024 |
Flowers | +0.023 |
Neg logit contributions | |
Years | -0.034 |
hockey | -0.033 |
cowboy | -0.032 |
brand | -0.031 |
ingu | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
Danger | +0.026 |
� | +0.022 |
nine | +0.022 |
Ab | +0.021 |
arc | +0.021 |
Neg logit contributions | |
ingu | -0.035 |
affle | -0.033 |
tto | -0.033 |
ascal | -0.033 |
ravings | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
Danger | +0.060 |
nine | +0.060 |
thirteen | +0.057 |
� | +0.054 |
arc | +0.054 |
Neg logit contributions | |
ingu | -0.066 |
tto | -0.063 |
pistol | -0.062 |
brand | -0.061 |
ascal | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
ingu | +0.015 |
tto | +0.015 |
ravings | +0.014 |
ascal | +0.014 |
pistol | +0.014 |
Neg logit contributions | |
Danger | -0.009 |
� | -0.009 |
nine | -0.009 |
Ab | -0.008 |
thirteen | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
ingu | +0.060 |
tto | +0.057 |
ascal | +0.055 |
pistol | +0.054 |
ravings | +0.054 |
Neg logit contributions | |
Danger | -0.052 |
nine | -0.051 |
� | -0.050 |
Ab | -0.047 |
thirteen | -0.046 |
Token | understand |
Token ID | 1833 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
ingu | +0.038 |
ascal | +0.037 |
tto | +0.036 |
pistol | +0.036 |
affle | +0.035 |
Neg logit contributions | |
nine | -0.028 |
Danger | -0.028 |
Ab | -0.026 |
thirteen | -0.026 |
arc | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
ingu | +0.005 |
pistol | +0.004 |
ascal | +0.004 |
tto | +0.004 |
brand | +0.004 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
� | -0.003 |
thirteen | -0.003 |
Ab | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
nine | +0.008 |
Danger | +0.008 |
thirteen | +0.008 |
� | +0.008 |
Ab | +0.007 |
Neg logit contributions | |
ingu | -0.011 |
ravings | -0.011 |
ascal | -0.011 |
pistol | -0.011 |
brand | -0.010 |
Token | like |
Token ID | 588 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ingu | +0.021 |
tto | +0.021 |
pistol | +0.020 |
affle | +0.020 |
ravings | +0.019 |
Neg logit contributions | |
Danger | -0.011 |
nine | -0.011 |
arc | -0.010 |
thirteen | -0.010 |
Ab | -0.010 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
� | +0.057 |
Danger | +0.053 |
arc | +0.051 |
thirteen | +0.051 |
nine | +0.051 |
Neg logit contributions | |
ingu | -0.059 |
ascal | -0.055 |
ravings | -0.055 |
brand | -0.055 |
pistol | -0.052 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
Danger | +0.197 |
nine | +0.190 |
� | +0.190 |
Ab | +0.167 |
thirteen | +0.164 |
Neg logit contributions | |
ingu | -0.514 |
tto | -0.496 |
ascal | -0.488 |
ravings | -0.479 |
pistol | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
Danger | +0.044 |
nine | +0.042 |
� | +0.040 |
Ab | +0.038 |
thirteen | +0.038 |
Neg logit contributions | |
ingu | -0.072 |
tto | -0.069 |
pistol | -0.068 |
ascal | -0.067 |
ravings | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
nine | +0.010 |
thirteen | +0.010 |
� | +0.009 |
Danger | +0.009 |
adies | +0.009 |
Neg logit contributions | |
ingu | -0.010 |
ravings | -0.010 |
brand | -0.010 |
ascal | -0.010 |
pistol | -0.009 |
Token | think |
Token ID | 892 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ingu | +0.019 |
pistol | +0.018 |
tto | +0.018 |
affle | +0.018 |
ravings | +0.017 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.012 |
arc | -0.012 |
Ab | -0.012 |
thirteen | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Danger | +0.105 |
� | +0.104 |
arc | +0.096 |
nine | +0.095 |
thirteen | +0.095 |
Neg logit contributions | |
brand | -0.102 |
ingu | -0.097 |
zed | -0.092 |
pistol | -0.090 |
Years | -0.088 |
Token | They |
Token ID | 1119 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
nine | +0.003 |
� | +0.003 |
Danger | +0.003 |
thirteen | +0.003 |
arc | +0.003 |
Neg logit contributions | |
ingu | -0.005 |
ravings | -0.005 |
tto | -0.005 |
pistol | -0.005 |
brand | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ingu | +0.026 |
tto | +0.024 |
pistol | +0.023 |
ascal | +0.023 |
pron | +0.023 |
Neg logit contributions | |
Danger | -0.026 |
� | -0.024 |
nine | -0.024 |
thirteen | -0.023 |
Ab | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Danger | +0.015 |
nine | +0.014 |
� | +0.014 |
thirteen | +0.013 |
Ab | +0.013 |
Neg logit contributions | |
ingu | -0.021 |
pistol | -0.019 |
brand | -0.019 |
tto | -0.019 |
ascal | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
Danger | +0.021 |
nine | +0.021 |
� | +0.020 |
thirteen | +0.020 |
Ab | +0.019 |
Neg logit contributions | |
ingu | -0.020 |
pistol | -0.018 |
brand | -0.018 |
pron | -0.018 |
tto | -0.018 |
Token | L |
Token ID | 43 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
ingu | +0.040 |
ascal | +0.038 |
tto | +0.037 |
Years | +0.037 |
pron | +0.037 |
Neg logit contributions | |
Danger | -0.040 |
Ab | -0.039 |
Jen | -0.037 |
nine | -0.037 |
ago | -0.036 |
Token | adies |
Token ID | 50192 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
� | +0.020 |
Ab | +0.020 |
Danger | +0.018 |
Am | +0.018 |
nine | +0.018 |
Neg logit contributions | |
ingu | -0.029 |
affle | -0.028 |
udd | -0.027 |
tto | -0.027 |
ascal | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Danger | +0.310 |
� | +0.296 |
nine | +0.284 |
thirteen | +0.271 |
Ab | +0.266 |
Neg logit contributions | |
ingu | -0.406 |
tto | -0.378 |
ascal | -0.375 |
ravings | -0.374 |
pistol | -0.367 |
Token | gentlemen |
Token ID | 28527 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ingu | +0.020 |
pistol | +0.017 |
brand | +0.017 |
handsome | +0.017 |
hockey | +0.016 |
Neg logit contributions | |
Danger | -0.019 |
Ab | -0.017 |
thirteen | -0.017 |
arc | -0.017 |
ago | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Danger | +0.152 |
thirteen | +0.136 |
Ab | +0.136 |
nine | +0.129 |
� | +0.128 |
Neg logit contributions | |
ingu | -0.164 |
ravings | -0.142 |
affle | -0.141 |
pron | -0.141 |
tto | -0.141 |
Token | welcome |
Token ID | 7062 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Danger | +0.017 |
thirteen | +0.016 |
� | +0.016 |
arc | +0.016 |
Ab | +0.016 |
Neg logit contributions | |
ingu | -0.024 |
brand | -0.021 |
pistol | -0.021 |
pron | -0.020 |
ascal | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
ingu | +0.025 |
ascal | +0.023 |
pistol | +0.023 |
ravings | +0.022 |
ishing | +0.022 |
Neg logit contributions | |
Danger | -0.023 |
thirteen | -0.022 |
� | -0.021 |
nine | -0.020 |
arc | -0.020 |
Token | Cars |
Token ID | 25277 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Danger | +0.010 |
nine | +0.010 |
thirteen | +0.010 |
� | +0.010 |
Ab | +0.009 |
Neg logit contributions | |
ingu | -0.016 |
ascal | -0.015 |
tto | -0.015 |
brand | -0.015 |
ravings | -0.015 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
Danger | +0.117 |
nine | +0.114 |
� | +0.107 |
Ab | +0.106 |
thirteen | +0.102 |
Neg logit contributions | |
ingu | -0.178 |
tto | -0.170 |
pistol | -0.168 |
brand | -0.164 |
ascal | -0.162 |
Token | 't |
Token ID | 470 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
ingu | +0.057 |
tto | +0.057 |
pistol | +0.056 |
brand | +0.055 |
Years | +0.053 |
Neg logit contributions | |
nine | -0.028 |
Ab | -0.027 |
Danger | -0.026 |
thirteen | -0.025 |
arc | -0.024 |
Token | fly |
Token ID | 6129 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
Danger | +0.118 |
nine | +0.115 |
� | +0.114 |
Ab | +0.106 |
thirteen | +0.105 |
Neg logit contributions | |
ingu | -0.190 |
tto | -0.180 |
pistol | -0.179 |
ascal | -0.176 |
ravings | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
Danger | +0.050 |
nine | +0.049 |
� | +0.048 |
thirteen | +0.044 |
Ab | +0.044 |
Neg logit contributions | |
ingu | -0.088 |
tto | -0.085 |
ascal | -0.082 |
ravings | -0.081 |
affle | -0.081 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Danger | +0.013 |
� | +0.013 |
nine | +0.013 |
thirteen | +0.012 |
Ab | +0.012 |
Neg logit contributions | |
ingu | -0.019 |
pistol | -0.018 |
tto | -0.018 |
brand | -0.018 |
ascal | -0.018 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Danger | +0.146 |
nine | +0.143 |
� | +0.133 |
thirteen | +0.114 |
Ab | +0.113 |
Neg logit contributions | |
ingu | -0.560 |
tto | -0.548 |
pistol | -0.530 |
ascal | -0.529 |
ravings | -0.528 |
Token | . |
Token ID | 13 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
Danger | +0.045 |
nine | +0.042 |
� | +0.040 |
Ab | +0.039 |
thirteen | +0.039 |
Neg logit contributions | |
ingu | -0.075 |
pistol | -0.072 |
tto | -0.072 |
ascal | -0.070 |
brand | -0.070 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
nine | +0.012 |
Danger | +0.012 |
� | +0.011 |
thirteen | +0.011 |
arc | +0.010 |
Neg logit contributions | |
ingu | -0.019 |
ascal | -0.018 |
ravings | -0.017 |
brand | -0.017 |
tto | -0.017 |
Token | L |
Token ID | 43 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Danger | +0.001 |
nine | +0.001 |
� | +0.001 |
thirteen | +0.001 |
Ab | +0.001 |
Neg logit contributions | |
ingu | -0.002 |
tto | -0.002 |
ascal | -0.002 |
pistol | -0.002 |
ravings | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
Danger | +0.027 |
� | +0.026 |
nine | +0.026 |
thirteen | +0.024 |
Ab | +0.023 |
Neg logit contributions | |
ingu | -0.052 |
tto | -0.049 |
ascal | -0.047 |
affle | -0.047 |
ravings | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Danger | +0.110 |
� | +0.093 |
Ab | +0.087 |
nine | +0.086 |
arc | +0.084 |
Neg logit contributions | |
ingu | -0.112 |
affle | -0.108 |
ravings | -0.107 |
ittens | -0.106 |
tto | -0.105 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Danger | +0.031 |
Ab | +0.026 |
Suz | +0.026 |
otion | +0.025 |
Jess | +0.024 |
Neg logit contributions | |
hockey | -0.032 |
cowboy | -0.032 |
pron | -0.031 |
brand | -0.031 |
pistol | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Danger | +0.260 |
� | +0.219 |
Ab | +0.209 |
Ev | +0.207 |
arc | +0.206 |
Neg logit contributions | |
ingu | -0.243 |
ravings | -0.233 |
affle | -0.229 |
ittens | -0.226 |
hockey | -0.223 |
Token | eight |
Token ID | 3624 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
Danger | +0.026 |
Ab | +0.023 |
Suz | +0.022 |
adies | +0.022 |
arc | +0.021 |
Neg logit contributions | |
hockey | -0.035 |
pistol | -0.034 |
cowboy | -0.034 |
ingu | -0.033 |
pron | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Danger | +0.167 |
Ab | +0.134 |
Sylv | +0.134 |
� | +0.134 |
arc | +0.132 |
Neg logit contributions | |
ingu | -0.135 |
hockey | -0.135 |
pistol | -0.131 |
ravings | -0.130 |
ittens | -0.129 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Danger | +0.023 |
Ab | +0.017 |
Suz | +0.017 |
Sylv | +0.016 |
Flowers | +0.016 |
Neg logit contributions | |
hockey | -0.039 |
Years | -0.039 |
cowboy | -0.037 |
pron | -0.036 |
pistol | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Danger | +0.390 |
� | +0.327 |
Sylv | +0.313 |
arc | +0.310 |
Ab | +0.309 |
Neg logit contributions | |
ingu | -0.283 |
ravings | -0.276 |
ittens | -0.274 |
affle | -0.262 |
hockey | -0.261 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
arc | +0.028 |
Danger | +0.027 |
� | +0.025 |
Flowers | +0.025 |
Ab | +0.024 |
Neg logit contributions | |
Years | -0.033 |
cowboy | -0.031 |
hockey | -0.031 |
ingu | -0.030 |
pistol | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
Danger | +0.028 |
� | +0.023 |
Ab | +0.022 |
arc | +0.022 |
Sylv | +0.022 |
Neg logit contributions | |
ingu | -0.028 |
ravings | -0.027 |
affle | -0.027 |
tto | -0.026 |
ittens | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ostr | +0.011 |
spr | +0.011 |
gasp | +0.011 |
Ab | +0.011 |
arc | +0.010 |
Neg logit contributions | |
ingu | -0.014 |
hockey | -0.013 |
Rudolph | -0.012 |
cowboy | -0.011 |
pistol | -0.011 |
Token | slide |
Token ID | 10649 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
Danger | +0.036 |
� | +0.032 |
adies | +0.029 |
Ab | +0.029 |
Ev | +0.028 |
Neg logit contributions | |
ingu | -0.040 |
affle | -0.039 |
ravings | -0.039 |
brand | -0.039 |
pron | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Danger | +0.146 |
Ab | +0.121 |
� | +0.120 |
nine | +0.117 |
Ev | +0.114 |
Neg logit contributions | |
ingu | -0.188 |
tto | -0.179 |
ravings | -0.177 |
affle | -0.177 |
pistol | -0.176 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Danger | +0.059 |
nine | +0.049 |
arc | +0.048 |
adies | +0.047 |
Ab | +0.046 |
Neg logit contributions | |
pistol | -0.065 |
brand | -0.062 |
pron | -0.061 |
hockey | -0.061 |
ingu | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Danger | +0.239 |
� | +0.202 |
nine | +0.200 |
Ab | +0.196 |
arc | +0.194 |
Neg logit contributions | |
ingu | -0.313 |
tto | -0.301 |
affle | -0.292 |
brand | -0.289 |
pistol | -0.289 |
Token | eight |
Token ID | 3624 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Danger | +0.030 |
arc | +0.026 |
adies | +0.025 |
Ab | +0.025 |
Ev | +0.023 |
Neg logit contributions | |
pistol | -0.039 |
hockey | -0.038 |
brand | -0.037 |
pron | -0.037 |
ingu | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
Danger | +0.153 |
Ab | +0.129 |
arc | +0.125 |
� | +0.125 |
nine | +0.124 |
Neg logit contributions | |
ingu | -0.172 |
tto | -0.166 |
pistol | -0.165 |
affle | -0.163 |
ravings | -0.161 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Danger | +0.021 |
arc | +0.018 |
Ab | +0.016 |
Flowers | +0.015 |
Warning | +0.015 |
Neg logit contributions | |
hockey | -0.031 |
pistol | -0.031 |
helmet | -0.031 |
pron | -0.030 |
ingu | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
Danger | +0.344 |
� | +0.290 |
Ab | +0.283 |
arc | +0.280 |
nine | +0.275 |
Neg logit contributions | |
ingu | -0.333 |
ravings | -0.315 |
zed | -0.311 |
tto | -0.308 |
brand | -0.307 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Danger | +0.020 |
arc | +0.020 |
Flowers | +0.017 |
ind | +0.016 |
Warning | +0.016 |
Neg logit contributions | |
hockey | -0.024 |
pistol | -0.023 |
Years | -0.023 |
ingu | -0.023 |
helmet | -0.023 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
Danger | +0.024 |
� | +0.022 |
Ab | +0.021 |
arc | +0.021 |
nine | +0.020 |
Neg logit contributions | |
ingu | -0.027 |
tto | -0.026 |
affle | -0.025 |
ravings | -0.025 |
pistol | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
arc | +0.054 |
Danger | +0.053 |
thirteen | +0.052 |
nine | +0.048 |
adies | +0.047 |
Neg logit contributions | |
ingu | -0.049 |
hockey | -0.048 |
tto | -0.048 |
zed | -0.046 |
Jeremy | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
tto | +0.041 |
ingu | +0.040 |
ascal | +0.036 |
scar | +0.036 |
Years | +0.036 |
Neg logit contributions | |
Danger | -0.045 |
nine | -0.045 |
thirteen | -0.045 |
arc | -0.043 |
Ab | -0.041 |
Token | big |
Token ID | 1263 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Danger | +0.006 |
nine | +0.006 |
� | +0.006 |
paint | +0.006 |
Ab | +0.006 |
Neg logit contributions | |
ingu | -0.007 |
ascal | -0.007 |
tto | -0.006 |
ravings | -0.006 |
zed | -0.006 |
Token | book |
Token ID | 1492 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ingu | +0.033 |
pistol | +0.032 |
tto | +0.031 |
brand | +0.031 |
ravings | +0.030 |
Neg logit contributions | |
Danger | -0.034 |
nine | -0.032 |
� | -0.032 |
Ab | -0.031 |
thirteen | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ingu | +0.016 |
tto | +0.016 |
brand | +0.016 |
pistol | +0.015 |
pron | +0.015 |
Neg logit contributions | |
Danger | -0.016 |
Ab | -0.016 |
nine | -0.015 |
thirteen | -0.015 |
� | -0.014 |
Token | pictures |
Token ID | 5986 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
ingu | +0.021 |
brand | +0.021 |
pistol | +0.020 |
ravings | +0.017 |
hockey | +0.017 |
Neg logit contributions | |
Danger | -0.023 |
� | -0.022 |
arc | -0.021 |
Ab | -0.021 |
nine | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
Danger | +0.120 |
Ab | +0.116 |
thirteen | +0.108 |
nine | +0.107 |
� | +0.104 |
Neg logit contributions | |
brand | -0.096 |
pistol | -0.095 |
ingu | -0.095 |
pron | -0.089 |
ravings | -0.087 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Danger | +0.147 |
� | +0.143 |
nine | +0.140 |
thirteen | +0.134 |
Ab | +0.133 |
Neg logit contributions | |
ingu | -0.169 |
pistol | -0.159 |
brand | -0.158 |
ravings | -0.147 |
ascal | -0.147 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Danger | +0.190 |
� | +0.181 |
nine | +0.180 |
Ab | +0.157 |
thirteen | +0.152 |
Neg logit contributions | |
ingu | -0.521 |
tto | -0.500 |
ascal | -0.491 |
ravings | -0.484 |
affle | -0.479 |
Token | . |
Token ID | 13 |
Feature activation | +7.16e-03 |
Pos logit contributions | |
Danger | +0.060 |
nine | +0.057 |
thirteen | +0.054 |
Ab | +0.053 |
� | +0.052 |
Neg logit contributions | |
pistol | -0.060 |
ingu | -0.059 |
tto | -0.056 |
brand | -0.054 |
ravings | -0.054 |
Token | Vol |
Token ID | 4709 |
Feature activation | +9.76e-03 |
Pos logit contributions | |
Danger | +0.008 |
nine | +0.008 |
� | +0.008 |
thirteen | +0.008 |
arc | +0.007 |
Neg logit contributions | |
ingu | -0.014 |
tto | -0.013 |
ravings | -0.013 |
brand | -0.013 |
pistol | -0.013 |
Token | can |
Token ID | 5171 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
nine | +0.013 |
Ab | +0.012 |
Danger | +0.012 |
� | +0.012 |
thirteen | +0.011 |
Neg logit contributions | |
tto | -0.018 |
ingu | -0.018 |
ascal | -0.017 |
scar | -0.017 |
pistol | -0.017 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
thirteen | +0.127 |
nine | +0.123 |
Danger | +0.121 |
arc | +0.118 |
Ab | +0.112 |
Neg logit contributions | |
ingu | -0.135 |
pistol | -0.124 |
tto | -0.122 |
ables | -0.118 |
ravings | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
Danger | +0.049 |
nine | +0.046 |
Ab | +0.045 |
thirteen | +0.043 |
� | +0.043 |
Neg logit contributions | |
ingu | -0.066 |
pistol | -0.065 |
tto | -0.064 |
ravings | -0.063 |
ascal | -0.062 |
Token | You |
Token ID | 921 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
nine | +0.008 |
arc | +0.007 |
Danger | +0.007 |
thirteen | +0.007 |
Ab | +0.007 |
Neg logit contributions | |
ascal | -0.008 |
ingu | -0.008 |
pistol | -0.008 |
ravings | -0.007 |
Rudolph | -0.007 |
Token | should |
Token ID | 815 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Ab | +0.077 |
nine | +0.073 |
arc | +0.072 |
Danger | +0.072 |
thirteen | +0.071 |
Neg logit contributions | |
ingu | -0.109 |
pistol | -0.105 |
tto | -0.102 |
ascal | -0.100 |
affle | -0.095 |
Token | not |
Token ID | 407 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Danger | +0.039 |
nine | +0.037 |
thirteen | +0.036 |
Ab | +0.035 |
arc | +0.035 |
Neg logit contributions | |
ingu | -0.050 |
tto | -0.049 |
pistol | -0.046 |
ascal | -0.045 |
affle | -0.045 |
Token | like |
Token ID | 588 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ingu | +0.037 |
pistol | +0.036 |
tto | +0.035 |
ascal | +0.034 |
ravings | +0.034 |
Neg logit contributions | |
nine | -0.029 |
adies | -0.029 |
Ab | -0.028 |
thirteen | -0.028 |
Danger | -0.027 |
Token | volcan |
Token ID | 17516 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
� | +0.059 |
Danger | +0.056 |
arc | +0.056 |
nine | +0.054 |
thirteen | +0.054 |
Neg logit contributions | |
ingu | -0.049 |
brand | -0.048 |
pistol | -0.048 |
ravings | -0.047 |
ascal | -0.046 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
Danger | +0.200 |
� | +0.198 |
nine | +0.195 |
Ab | +0.179 |
thirteen | +0.168 |
Neg logit contributions | |
ingu | -0.506 |
ascal | -0.482 |
tto | -0.480 |
ravings | -0.470 |
affle | -0.460 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
Danger | +0.049 |
nine | +0.046 |
Ab | +0.046 |
thirteen | +0.043 |
arc | +0.042 |
Neg logit contributions | |
pistol | -0.061 |
ingu | -0.061 |
ravings | -0.058 |
ascal | -0.058 |
tto | -0.058 |
Token | You |
Token ID | 921 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
nine | +0.008 |
arc | +0.008 |
thirteen | +0.008 |
closer | +0.007 |
bud | +0.007 |
Neg logit contributions | |
ascal | -0.009 |
ingu | -0.008 |
ravings | -0.007 |
tto | -0.007 |
pistol | -0.007 |
Token | should |
Token ID | 815 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
arc | +0.083 |
Ab | +0.083 |
nine | +0.081 |
thirteen | +0.080 |
Danger | +0.079 |
Neg logit contributions | |
ingu | -0.104 |
pistol | -0.099 |
tto | -0.098 |
ascal | -0.096 |
affle | -0.090 |
Token | like |
Token ID | 588 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Danger | +0.038 |
nine | +0.036 |
thirteen | +0.035 |
arc | +0.035 |
Ab | +0.034 |
Neg logit contributions | |
ingu | -0.051 |
tto | -0.050 |
pistol | -0.047 |
ascal | -0.047 |
affle | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
nine | +0.004 |
Danger | +0.004 |
� | +0.004 |
thirteen | +0.003 |
arc | +0.003 |
Neg logit contributions | |
ingu | -0.006 |
tto | -0.005 |
brand | -0.005 |
pistol | -0.005 |
ravings | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ingu | +0.031 |
tto | +0.029 |
ascal | +0.028 |
pistol | +0.028 |
ravings | +0.028 |
Neg logit contributions | |
Danger | -0.022 |
nine | -0.022 |
� | -0.021 |
Ab | -0.020 |
thirteen | -0.020 |
Token | " |
Token ID | 1 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
tto | +0.023 |
Years | +0.022 |
ingu | +0.022 |
Days | +0.021 |
pron | +0.021 |
Neg logit contributions | |
Ab | -0.028 |
Danger | -0.027 |
thirteen | -0.025 |
arc | -0.025 |
nine | -0.024 |
Token | Ten |
Token ID | 24893 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
Danger | +0.095 |
Ab | +0.091 |
� | +0.088 |
ago | +0.087 |
nine | +0.086 |
Neg logit contributions | |
Years | -0.103 |
ingu | -0.100 |
tto | -0.099 |
pron | -0.095 |
ascal | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Danger | +0.086 |
� | +0.078 |
Ab | +0.073 |
nine | +0.073 |
thirteen | +0.068 |
Neg logit contributions | |
ingu | -0.134 |
tto | -0.126 |
affle | -0.125 |
ascal | -0.123 |
brand | -0.123 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Danger | +0.025 |
Ab | +0.022 |
arc | +0.021 |
� | +0.020 |
Those | +0.020 |
Neg logit contributions | |
cowboy | -0.035 |
ingu | -0.034 |
brand | -0.034 |
armor | -0.034 |
pistol | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Danger | +0.342 |
� | +0.294 |
Ab | +0.291 |
Sylv | +0.278 |
arc | +0.269 |
Neg logit contributions | |
ingu | -0.355 |
brand | -0.333 |
pistol | -0.331 |
ravings | -0.326 |
affle | -0.325 |
Token | eight |
Token ID | 3624 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
arc | +0.025 |
Danger | +0.024 |
Ab | +0.023 |
� | +0.023 |
bird | +0.022 |
Neg logit contributions | |
cowboy | -0.034 |
ingu | -0.034 |
Years | -0.032 |
brand | -0.031 |
pistol | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Danger | +0.142 |
Ab | +0.120 |
� | +0.119 |
nine | +0.114 |
Sylv | +0.112 |
Neg logit contributions | |
ingu | -0.172 |
pistol | -0.163 |
tto | -0.160 |
affle | -0.158 |
ravings | -0.158 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Danger | +0.022 |
Ab | +0.018 |
arc | +0.017 |
� | +0.017 |
Sylv | +0.017 |
Neg logit contributions | |
cowboy | -0.039 |
ingu | -0.038 |
Years | -0.038 |
helmet | -0.037 |
brand | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Danger | +0.227 |
� | +0.198 |
Ab | +0.193 |
nine | +0.188 |
arc | +0.180 |
Neg logit contributions | |
ingu | -0.298 |
tto | -0.277 |
pistol | -0.273 |
ravings | -0.273 |
affle | -0.272 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
Danger | +0.096 |
� | +0.085 |
Ab | +0.082 |
nine | +0.082 |
thirteen | +0.077 |
Neg logit contributions | |
ingu | -0.131 |
tto | -0.122 |
affle | -0.121 |
brand | -0.121 |
pistol | -0.121 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Danger | +0.030 |
Ab | +0.027 |
Suz | +0.025 |
otion | +0.024 |
Sylv | +0.023 |
Neg logit contributions | |
cowboy | -0.030 |
hockey | -0.030 |
brand | -0.029 |
pron | -0.029 |
Years | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Danger | +0.229 |
� | +0.199 |
Ab | +0.197 |
nine | +0.187 |
thirteen | +0.181 |
Neg logit contributions | |
ingu | -0.287 |
ravings | -0.264 |
brand | -0.262 |
affle | -0.262 |
pistol | -0.260 |
Token | eight |
Token ID | 3624 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
Danger | +0.025 |
Ab | +0.025 |
Suz | +0.023 |
Sylv | +0.022 |
Jen | +0.021 |
Neg logit contributions | |
cowboy | -0.032 |
hockey | -0.032 |
ingu | -0.032 |
pron | -0.031 |
pistol | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Danger | +0.155 |
Ab | +0.133 |
� | +0.129 |
Sylv | +0.126 |
arc | +0.123 |
Neg logit contributions | |
ingu | -0.155 |
pistol | -0.144 |
hockey | -0.143 |
affle | -0.141 |
ravings | -0.141 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Danger | +0.023 |
Ab | +0.018 |
Suz | +0.017 |
Sylv | +0.016 |
arc | +0.016 |
Neg logit contributions | |
Years | -0.038 |
hockey | -0.036 |
ingu | -0.036 |
cowboy | -0.035 |
pron | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Danger | +0.354 |
� | +0.308 |
Ab | +0.301 |
Sylv | +0.288 |
arc | +0.282 |
Neg logit contributions | |
ingu | -0.330 |
ravings | -0.305 |
brand | -0.300 |
affle | -0.299 |
ittens | -0.297 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Danger | +0.026 |
arc | +0.025 |
� | +0.024 |
Ab | +0.023 |
Flowers | +0.023 |
Neg logit contributions | |
Years | -0.033 |
cowboy | -0.032 |
hockey | -0.031 |
ingu | -0.031 |
pistol | -0.029 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
Danger | +0.024 |
� | +0.022 |
Ab | +0.021 |
nine | +0.020 |
arc | +0.019 |
Neg logit contributions | |
ingu | -0.032 |
affle | -0.030 |
ravings | -0.030 |
pistol | -0.029 |
tto | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Danger | +0.052 |
� | +0.049 |
nine | +0.049 |
thirteen | +0.047 |
arc | +0.046 |
Neg logit contributions | |
ingu | -0.066 |
tto | -0.062 |
pistol | -0.060 |
ravings | -0.059 |
ascal | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ingu | +0.030 |
tto | +0.029 |
pistol | +0.028 |
ravings | +0.028 |
ascal | +0.028 |
Neg logit contributions | |
nine | -0.015 |
Danger | -0.015 |
� | -0.015 |
Jen | -0.014 |
Ab | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Danger | +0.096 |
� | +0.081 |
Ab | +0.080 |
nine | +0.080 |
Jen | +0.073 |
Neg logit contributions | |
ingu | -0.129 |
tto | -0.122 |
affle | -0.121 |
ascal | -0.120 |
pistol | -0.120 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Danger | +0.026 |
Ab | +0.024 |
Suz | +0.022 |
Sylv | +0.021 |
otion | +0.020 |
Neg logit contributions | |
hockey | -0.029 |
cowboy | -0.029 |
pron | -0.027 |
pistol | -0.027 |
brand | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Danger | +0.234 |
Ab | +0.198 |
� | +0.194 |
nine | +0.188 |
arc | +0.182 |
Neg logit contributions | |
ingu | -0.280 |
ravings | -0.258 |
affle | -0.257 |
pistol | -0.255 |
tto | -0.254 |
Token | eight |
Token ID | 3624 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
Danger | +0.022 |
Ab | +0.022 |
Suz | +0.020 |
Sylv | +0.019 |
Jen | +0.019 |
Neg logit contributions | |
hockey | -0.031 |
cowboy | -0.030 |
ingu | -0.030 |
pistol | -0.030 |
pron | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Danger | +0.156 |
Ab | +0.132 |
Sylv | +0.126 |
� | +0.124 |
Jen | +0.121 |
Neg logit contributions | |
ingu | -0.149 |
hockey | -0.143 |
pistol | -0.141 |
affle | -0.138 |
ravings | -0.136 |
Token | nine |
Token ID | 5193 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Danger | +0.020 |
Ab | +0.018 |
Suz | +0.016 |
Sylv | +0.016 |
Jess | +0.014 |
Neg logit contributions | |
hockey | -0.033 |
Years | -0.032 |
cowboy | -0.031 |
ingu | -0.030 |
pistol | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
Danger | +0.369 |
Ab | +0.306 |
� | +0.305 |
Sylv | +0.297 |
arc | +0.280 |
Neg logit contributions | |
ingu | -0.317 |
ravings | -0.292 |
affle | -0.291 |
hockey | -0.288 |
pistol | -0.286 |
Token | ten |
Token ID | 3478 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
Danger | +0.023 |
arc | +0.022 |
Ab | +0.022 |
� | +0.021 |
Sylv | +0.021 |
Neg logit contributions | |
Years | -0.030 |
hockey | -0.029 |
cowboy | -0.028 |
ingu | -0.028 |
pistol | -0.027 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
Danger | +0.025 |
Ab | +0.021 |
� | +0.020 |
Sylv | +0.020 |
arc | +0.019 |
Neg logit contributions | |
ingu | -0.031 |
affle | -0.029 |
tto | -0.029 |
ravings | -0.029 |
pistol | -0.029 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Danger | +0.059 |
thirteen | +0.057 |
nine | +0.056 |
arc | +0.056 |
ind | +0.053 |
Neg logit contributions | |
ingu | -0.048 |
pistol | -0.044 |
hockey | -0.043 |
tto | -0.040 |
brand | -0.040 |
Token | says |
Token ID | 1139 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ingu | +0.119 |
hockey | +0.118 |
pistol | +0.115 |
affle | +0.113 |
tricks | +0.113 |
Neg logit contributions | |
Danger | -0.130 |
Ab | -0.124 |
adies | -0.117 |
ago | -0.116 |
nine | -0.114 |
Token | would |
Token ID | 561 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ingu | +0.143 |
tto | +0.137 |
pistol | +0.132 |
ascal | +0.130 |
ravings | +0.130 |
Neg logit contributions | |
Danger | -0.130 |
nine | -0.129 |
� | -0.123 |
thirteen | -0.118 |
Ab | -0.117 |
Token | heal |
Token ID | 12035 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ingu | +0.138 |
tto | +0.133 |
pistol | +0.132 |
brand | +0.130 |
ravings | +0.126 |
Neg logit contributions | |
Danger | -0.094 |
nine | -0.092 |
thirteen | -0.083 |
arc | -0.082 |
Ab | -0.082 |
Token | soon |
Token ID | 2582 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ingu | +0.227 |
tto | +0.220 |
ravings | +0.212 |
ascal | +0.210 |
affle | +0.209 |
Neg logit contributions | |
� | -0.146 |
nine | -0.144 |
Danger | -0.143 |
Ab | -0.130 |
thirteen | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
Danger | +0.039 |
nine | +0.038 |
� | +0.036 |
Ab | +0.034 |
thirteen | +0.034 |
Neg logit contributions | |
ingu | -0.066 |
tto | -0.064 |
pistol | -0.062 |
ravings | -0.062 |
ascal | -0.061 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ingu | +0.008 |
tto | +0.008 |
pistol | +0.007 |
ascal | +0.007 |
ravings | +0.007 |
Neg logit contributions | |
Danger | -0.005 |
nine | -0.005 |
� | -0.005 |
thirteen | -0.005 |
Ab | -0.005 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ingu | +0.021 |
tto | +0.020 |
pistol | +0.019 |
brand | +0.019 |
pron | +0.018 |
Neg logit contributions | |
Danger | -0.072 |
nine | -0.072 |
� | -0.071 |
Ab | -0.068 |
thirteen | -0.067 |
Token | ers |
Token ID | 364 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
ingu | +0.341 |
tto | +0.323 |
ascal | +0.304 |
pistol | +0.301 |
ravings | +0.301 |
Neg logit contributions | |
Danger | -0.509 |
nine | -0.503 |
� | -0.494 |
Ab | -0.470 |
thirteen | -0.470 |
Token | was |
Token ID | 373 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ingu | +0.057 |
tto | +0.054 |
ascal | +0.052 |
pistol | +0.052 |
ravings | +0.052 |
Neg logit contributions | |
Danger | -0.054 |
nine | -0.053 |
� | -0.052 |
Ab | -0.049 |
thirteen | -0.049 |
Token | very |
Token ID | 845 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ingu | +0.039 |
tto | +0.037 |
ascal | +0.036 |
ravings | +0.035 |
pistol | +0.035 |
Neg logit contributions | |
� | -0.037 |
nine | -0.037 |
Danger | -0.035 |
Ab | -0.034 |
thirteen | -0.033 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ingu | +0.087 |
tto | +0.083 |
ascal | +0.080 |
ravings | +0.079 |
pistol | +0.078 |
Neg logit contributions | |
� | -0.090 |
nine | -0.088 |
Danger | -0.087 |
Ab | -0.082 |
thirteen | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
ingu | +0.032 |
tto | +0.032 |
affle | +0.030 |
ascal | +0.030 |
ravings | +0.030 |
Neg logit contributions | |
� | -0.014 |
nine | -0.014 |
Danger | -0.013 |
Ab | -0.013 |
Jen | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ingu | +0.054 |
ravings | +0.051 |
pistol | +0.051 |
tto | +0.051 |
ascal | +0.050 |
Neg logit contributions | |
� | -0.032 |
Danger | -0.032 |
nine | -0.031 |
Ab | -0.029 |
Jen | -0.027 |
Token | After |
Token ID | 3260 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
tto | +0.040 |
ingu | +0.039 |
scar | +0.036 |
ascal | +0.036 |
Years | +0.036 |
Neg logit contributions | |
Danger | -0.045 |
nine | -0.045 |
thirteen | -0.043 |
arc | -0.043 |
Ab | -0.042 |
Token | Mr |
Token ID | 1770 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
Danger | +0.114 |
nine | +0.110 |
� | +0.108 |
thirteen | +0.104 |
arc | +0.101 |
Neg logit contributions | |
ingu | -0.123 |
tto | -0.116 |
pistol | -0.113 |
brand | -0.112 |
ascal | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-03 |
Pos logit contributions | |
ingu | +0.117 |
tto | +0.113 |
ascal | +0.108 |
brand | +0.108 |
ravings | +0.108 |
Neg logit contributions | |
Danger | -0.064 |
nine | -0.063 |
� | -0.061 |
Ab | -0.057 |
thirteen | -0.056 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
ingu | +0.003 |
tto | +0.002 |
pistol | +0.002 |
ravings | +0.002 |
ascal | +0.002 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.002 |
� | -0.002 |
thirteen | -0.002 |
arc | -0.002 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ingu | +0.023 |
brand | +0.022 |
pistol | +0.021 |
pron | +0.020 |
tto | +0.020 |
Neg logit contributions | |
Danger | -0.066 |
� | -0.066 |
nine | -0.066 |
Ab | -0.063 |
Jen | -0.063 |
Token | ers |
Token ID | 364 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ingu | +0.305 |
tto | +0.296 |
ascal | +0.265 |
affle | +0.258 |
ravings | +0.255 |
Neg logit contributions | |
Danger | -0.547 |
nine | -0.534 |
� | -0.526 |
Ab | -0.505 |
arc | -0.503 |
Token | was |
Token ID | 373 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ingu | +0.058 |
tto | +0.056 |
ascal | +0.054 |
pistol | +0.053 |
ravings | +0.053 |
Neg logit contributions | |
Danger | -0.046 |
nine | -0.045 |
� | -0.044 |
Ab | -0.041 |
thirteen | -0.041 |
Token | done |
Token ID | 1760 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
ingu | +0.035 |
ascal | +0.033 |
tto | +0.033 |
pistol | +0.033 |
ravings | +0.032 |
Neg logit contributions | |
nine | -0.030 |
� | -0.030 |
Danger | -0.028 |
Ab | -0.028 |
thirteen | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ingu | +0.099 |
tto | +0.097 |
pistol | +0.094 |
brand | +0.093 |
ravings | +0.092 |
Neg logit contributions | |
Danger | -0.069 |
nine | -0.067 |
� | -0.061 |
thirteen | -0.060 |
Ab | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
ascal | +0.055 |
pron | +0.054 |
ouse | +0.053 |
uddle | +0.053 |
iflower | +0.053 |
Neg logit contributions | |
Jen | -0.029 |
Ab | -0.029 |
� | -0.027 |
nine | -0.026 |
K | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
ingu | +0.067 |
tto | +0.065 |
pistol | +0.064 |
ravings | +0.063 |
ascal | +0.063 |
Neg logit contributions | |
Danger | -0.047 |
nine | -0.046 |
� | -0.042 |
thirteen | -0.041 |
Ab | -0.040 |
Token | The |
Token ID | 383 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
ingu | +0.007 |
tto | +0.007 |
ravings | +0.006 |
ascal | +0.006 |
pistol | +0.006 |
Neg logit contributions | |
Danger | -0.006 |
nine | -0.006 |
thirteen | -0.005 |
arc | -0.005 |
paint | -0.005 |
Token | vet |
Token ID | 20202 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
Danger | +0.009 |
� | +0.008 |
nine | +0.008 |
Ab | +0.008 |
thirteen | +0.008 |
Neg logit contributions | |
ingu | -0.007 |
pistol | -0.007 |
tto | -0.006 |
ascal | -0.006 |
ravings | -0.006 |
Token | showed |
Token ID | 3751 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
ingu | +0.050 |
tto | +0.047 |
pistol | +0.045 |
pron | +0.044 |
ascal | +0.044 |
Neg logit contributions | |
Danger | -0.055 |
nine | -0.051 |
thirteen | -0.049 |
arc | -0.048 |
� | -0.047 |
Token | Wh |
Token ID | 854 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ingu | +0.017 |
tto | +0.017 |
pistol | +0.016 |
ascal | +0.016 |
ravings | +0.016 |
Neg logit contributions | |
Danger | -0.011 |
nine | -0.011 |
� | -0.010 |
thirteen | -0.010 |
Ab | -0.010 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ingu | +0.026 |
tto | +0.023 |
brand | +0.023 |
pistol | +0.022 |
ravings | +0.021 |
Neg logit contributions | |
Danger | -0.072 |
nine | -0.072 |
� | -0.071 |
Ab | -0.067 |
thirteen | -0.067 |
Token | ers |
Token ID | 364 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ingu | +0.323 |
tto | +0.309 |
ascal | +0.286 |
pistol | +0.281 |
ravings | +0.278 |
Neg logit contributions | |
Danger | -0.519 |
nine | -0.512 |
� | -0.503 |
Ab | -0.482 |
thirteen | -0.479 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ingu | +0.055 |
tto | +0.052 |
pistol | +0.050 |
brand | +0.049 |
ravings | +0.049 |
Neg logit contributions | |
Danger | -0.051 |
nine | -0.050 |
� | -0.048 |
thirteen | -0.046 |
Ab | -0.046 |
Token | x |
Token ID | 2124 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ingu | +0.020 |
pistol | +0.020 |
tto | +0.019 |
brand | +0.019 |
ravings | +0.019 |
Neg logit contributions | |
Danger | -0.025 |
� | -0.024 |
nine | -0.024 |
arc | -0.023 |
Ab | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
ingu | +0.039 |
tto | +0.036 |
ascal | +0.033 |
ravings | +0.033 |
pistol | +0.032 |
Neg logit contributions | |
Danger | -0.076 |
nine | -0.075 |
� | -0.074 |
thirteen | -0.071 |
Ab | -0.070 |
Token | ray |
Token ID | 2433 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
ingu | +0.083 |
tto | +0.082 |
pistol | +0.080 |
ascal | +0.077 |
Years | +0.076 |
Neg logit contributions | |
arc | -0.095 |
Danger | -0.091 |
nine | -0.088 |
Ab | -0.088 |
� | -0.085 |
Token | flew |
Token ID | 13112 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ingu | +0.004 |
tto | +0.004 |
pistol | +0.003 |
ascal | +0.003 |
ravings | +0.003 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
thirteen | -0.003 |
� | -0.002 |
arc | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
Danger | +0.038 |
nine | +0.035 |
� | +0.034 |
thirteen | +0.034 |
arc | +0.033 |
Neg logit contributions | |
ingu | -0.037 |
tto | -0.036 |
pistol | -0.036 |
brand | -0.035 |
ascal | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
pistol | +0.035 |
hockey | +0.034 |
brand | +0.034 |
tto | +0.033 |
Years | +0.032 |
Neg logit contributions | |
Danger | -0.049 |
thirteen | -0.048 |
arc | -0.046 |
� | -0.045 |
nine | -0.043 |
Token | scared |
Token ID | 12008 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ingu | +0.036 |
tto | +0.035 |
pistol | +0.033 |
ascal | +0.033 |
ravings | +0.033 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.032 |
� | -0.031 |
thirteen | -0.029 |
Ab | -0.029 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
Danger | +0.051 |
nine | +0.049 |
� | +0.048 |
thirteen | +0.046 |
arc | +0.045 |
Neg logit contributions | |
ingu | -0.066 |
tto | -0.062 |
pistol | -0.062 |
ascal | -0.062 |
ravings | -0.062 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ingu | +0.023 |
brand | +0.021 |
pistol | +0.021 |
tto | +0.021 |
pron | +0.020 |
Neg logit contributions | |
Danger | -0.071 |
nine | -0.069 |
� | -0.068 |
Ab | -0.067 |
Jen | -0.066 |
Token | ers |
Token ID | 364 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ingu | +0.307 |
tto | +0.298 |
ascal | +0.270 |
pistol | +0.263 |
ravings | +0.262 |
Neg logit contributions | |
Danger | -0.534 |
nine | -0.527 |
� | -0.519 |
thirteen | -0.495 |
Ab | -0.495 |
Token | away |
Token ID | 1497 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ingu | +0.058 |
pistol | +0.058 |
tto | +0.056 |
ravings | +0.056 |
brand | +0.054 |
Neg logit contributions | |
Danger | -0.051 |
nine | -0.049 |
thirteen | -0.048 |
arc | -0.047 |
Ab | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
ingu | +0.032 |
tto | +0.031 |
pistol | +0.030 |
brand | +0.030 |
ravings | +0.030 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.020 |
� | -0.020 |
thirteen | -0.019 |
arc | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
ingu | +0.008 |
tto | +0.007 |
ravings | +0.007 |
brand | +0.007 |
pistol | +0.007 |
Neg logit contributions | |
Danger | -0.005 |
nine | -0.005 |
� | -0.005 |
thirteen | -0.005 |
arc | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
ingu | +0.060 |
ravings | +0.057 |
ascal | +0.057 |
pistol | +0.057 |
tto | +0.056 |
Neg logit contributions | |
� | -0.032 |
Danger | -0.030 |
nine | -0.030 |
Ab | -0.027 |
Jen | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
ingu | +0.003 |
tto | +0.003 |
ascal | +0.003 |
ravings | +0.003 |
pistol | +0.003 |
Neg logit contributions | |
Danger | -0.002 |
nine | -0.002 |
� | -0.002 |
Ab | -0.002 |
thirteen | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.010 |
ascal | +0.009 |
affle | +0.009 |
ravings | +0.009 |
Neg logit contributions | |
Danger | -0.006 |
� | -0.006 |
nine | -0.006 |
Ab | -0.005 |
Jen | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
ravings | +0.071 |
ingu | +0.070 |
ishing | +0.069 |
ascal | +0.068 |
pistol | +0.066 |
Neg logit contributions | |
� | -0.030 |
Danger | -0.025 |
nine | -0.024 |
Jen | -0.021 |
have | -0.020 |
Token | After |
Token ID | 3260 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ingu | +0.056 |
tto | +0.053 |
ascal | +0.052 |
ravings | +0.052 |
pistol | +0.051 |
Neg logit contributions | |
� | -0.039 |
Danger | -0.038 |
nine | -0.037 |
thirteen | -0.033 |
Ab | -0.032 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Danger | +0.099 |
nine | +0.098 |
� | +0.095 |
Ab | +0.088 |
thirteen | +0.087 |
Neg logit contributions | |
ingu | -0.141 |
tto | -0.137 |
ascal | -0.131 |
ravings | -0.131 |
pistol | -0.129 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ingu | +0.021 |
tto | +0.019 |
brand | +0.019 |
pistol | +0.019 |
pron | +0.017 |
Neg logit contributions | |
Danger | -0.070 |
nine | -0.069 |
� | -0.068 |
thirteen | -0.064 |
Ab | -0.064 |
Token | ers |
Token ID | 364 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ingu | +0.302 |
tto | +0.293 |
ascal | +0.264 |
affle | +0.256 |
ravings | +0.253 |
Neg logit contributions | |
Danger | -0.539 |
nine | -0.527 |
� | -0.519 |
Ab | -0.502 |
arc | -0.498 |
Token | got |
Token ID | 1392 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
ingu | +0.059 |
tto | +0.056 |
pistol | +0.054 |
ascal | +0.054 |
ravings | +0.054 |
Neg logit contributions | |
Danger | -0.047 |
nine | -0.047 |
� | -0.044 |
thirteen | -0.043 |
Ab | -0.042 |
Token | better |
Token ID | 1365 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
tto | +0.071 |
ingu | +0.071 |
ascal | +0.070 |
affle | +0.070 |
ravings | +0.068 |
Neg logit contributions | |
nine | -0.041 |
� | -0.039 |
Ab | -0.036 |
Danger | -0.036 |
paint | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
ingu | +0.013 |
tto | +0.013 |
affle | +0.012 |
Years | +0.012 |
ravings | +0.012 |
Neg logit contributions | |
� | -0.004 |
nine | -0.004 |
Danger | -0.004 |
paint | -0.003 |
ago | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
nine | +0.011 |
� | +0.010 |
Danger | +0.010 |
Jen | +0.010 |
Ab | +0.010 |
Neg logit contributions | |
ingu | -0.016 |
tto | -0.016 |
ascal | -0.015 |
affle | -0.015 |
ravings | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
ingu | +0.054 |
tto | +0.052 |
ascal | +0.050 |
pistol | +0.050 |
brand | +0.049 |
Neg logit contributions | |
Danger | -0.029 |
nine | -0.028 |
� | -0.027 |
thirteen | -0.025 |
Ab | -0.025 |
Token | naughty |
Token ID | 45128 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ingu | +0.006 |
tto | +0.006 |
ravings | +0.006 |
zed | +0.006 |
scar | +0.005 |
Neg logit contributions | |
nine | -0.004 |
� | -0.004 |
Danger | -0.004 |
paint | -0.004 |
arc | -0.004 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ingu | +0.022 |
tto | +0.022 |
brand | +0.020 |
ravings | +0.020 |
ascal | +0.020 |
Neg logit contributions | |
Danger | -0.016 |
nine | -0.016 |
� | -0.016 |
Ab | -0.015 |
Jen | -0.015 |
Token | named |
Token ID | 3706 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ingu | +0.023 |
tto | +0.022 |
ascal | +0.021 |
ravings | +0.021 |
pistol | +0.021 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.013 |
� | -0.013 |
Ab | -0.012 |
thirteen | -0.012 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Danger | +0.031 |
nine | +0.031 |
� | +0.030 |
thirteen | +0.029 |
Ab | +0.028 |
Neg logit contributions | |
ingu | -0.032 |
tto | -0.031 |
pistol | -0.029 |
ravings | -0.029 |
ascal | -0.029 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
brand | +0.028 |
pistol | +0.025 |
ingu | +0.024 |
tto | +0.024 |
pron | +0.023 |
Neg logit contributions | |
nine | -0.063 |
Danger | -0.061 |
� | -0.059 |
Jen | -0.058 |
are | -0.057 |
Token | ers |
Token ID | 364 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ingu | +0.320 |
tto | +0.305 |
ascal | +0.282 |
ravings | +0.274 |
pistol | +0.273 |
Neg logit contributions | |
Danger | -0.523 |
nine | -0.513 |
� | -0.510 |
Ab | -0.485 |
thirteen | -0.483 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
ingu | +0.074 |
tto | +0.072 |
brand | +0.070 |
affle | +0.070 |
ravings | +0.070 |
Neg logit contributions | |
nine | -0.030 |
Danger | -0.029 |
� | -0.029 |
Ab | -0.025 |
Jen | -0.023 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.009 |
ascal | +0.009 |
ravings | +0.009 |
pistol | +0.009 |
Neg logit contributions | |
Danger | -0.007 |
nine | -0.007 |
� | -0.007 |
Ab | -0.007 |
thirteen | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.030 |
pron | +0.029 |
pistol | +0.028 |
zed | +0.026 |
handsome | +0.025 |
Neg logit contributions | |
nine | -0.050 |
are | -0.048 |
Danger | -0.048 |
� | -0.047 |
Jen | -0.046 |
Token | ers |
Token ID | 364 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ingu | +0.359 |
tto | +0.337 |
pistol | +0.326 |
brand | +0.325 |
ravings | +0.324 |
Neg logit contributions | |
Danger | -0.475 |
nine | -0.474 |
� | -0.460 |
thirteen | -0.439 |
Ab | -0.438 |
Token | Ch |
Token ID | 609 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
Danger | +0.076 |
thirteen | +0.074 |
nine | +0.074 |
arc | +0.072 |
adies | +0.067 |
Neg logit contributions | |
ingu | -0.079 |
tto | -0.075 |
pistol | -0.072 |
ascal | -0.071 |
ravings | -0.070 |
Token | ir |
Token ID | 343 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ingu | +0.011 |
tto | +0.011 |
ascal | +0.010 |
affle | +0.010 |
ravings | +0.010 |
Neg logit contributions | |
Danger | -0.007 |
nine | -0.007 |
� | -0.007 |
thirteen | -0.006 |
arc | -0.006 |
Token | py |
Token ID | 9078 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
Danger | +0.270 |
nine | +0.241 |
� | +0.238 |
arc | +0.236 |
thirteen | +0.231 |
Neg logit contributions | |
ingu | -0.213 |
ascal | -0.199 |
tto | -0.197 |
affle | -0.191 |
ongo | -0.181 |
Token | and |
Token ID | 290 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
Danger | +0.003 |
nine | +0.002 |
thirteen | +0.002 |
Ab | +0.002 |
� | +0.002 |
Neg logit contributions | |
ingu | -0.002 |
tto | -0.002 |
pistol | -0.002 |
ascal | -0.002 |
affle | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ingu | +0.012 |
pistol | +0.012 |
tto | +0.012 |
brand | +0.011 |
ascal | +0.011 |
Neg logit contributions | |
Danger | -0.010 |
nine | -0.009 |
� | -0.009 |
thirteen | -0.009 |
arc | -0.009 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ingu | +0.022 |
tto | +0.020 |
ascal | +0.019 |
affle | +0.017 |
ravings | +0.017 |
Neg logit contributions | |
Danger | -0.052 |
nine | -0.051 |
� | -0.051 |
thirteen | -0.049 |
arc | -0.048 |
Token | ers |
Token ID | 364 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ingu | +0.286 |
tto | +0.278 |
ascal | +0.250 |
affle | +0.239 |
zed | +0.239 |
Neg logit contributions | |
Danger | -0.550 |
� | -0.530 |
nine | -0.530 |
arc | -0.517 |
Ab | -0.503 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ingu | +0.045 |
pistol | +0.043 |
tto | +0.042 |
zed | +0.041 |
brand | +0.040 |
Neg logit contributions | |
Danger | -0.048 |
nine | -0.046 |
Ab | -0.044 |
Jen | -0.043 |
arc | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Danger | +0.020 |
nine | +0.019 |
� | +0.019 |
thirteen | +0.018 |
arc | +0.018 |
Neg logit contributions | |
ingu | -0.019 |
tto | -0.018 |
pistol | -0.018 |
brand | -0.017 |
ascal | -0.017 |
Token | poison |
Token ID | 8764 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
pistol | +0.133 |
ingu | +0.123 |
brand | +0.122 |
tto | +0.120 |
zed | +0.116 |
Neg logit contributions | |
nine | -0.129 |
Danger | -0.129 |
thirteen | -0.123 |
arc | -0.120 |
adies | -0.111 |
Token | was |
Token ID | 373 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Danger | +0.009 |
nine | +0.009 |
� | +0.009 |
Ab | +0.008 |
thirteen | +0.008 |
Neg logit contributions | |
ingu | -0.011 |
tto | -0.011 |
ascal | -0.011 |
pistol | -0.010 |
ravings | -0.010 |
Token | Ch |
Token ID | 609 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Danger | +0.012 |
nine | +0.012 |
thirteen | +0.012 |
arc | +0.011 |
� | +0.011 |
Neg logit contributions | |
ingu | -0.013 |
pistol | -0.013 |
tto | -0.012 |
brand | -0.012 |
ascal | -0.011 |
Token | ir |
Token ID | 343 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ingu | +0.030 |
tto | +0.029 |
ascal | +0.029 |
affle | +0.028 |
ravings | +0.028 |
Neg logit contributions | |
Danger | -0.017 |
nine | -0.017 |
� | -0.016 |
thirteen | -0.015 |
Ab | -0.015 |
Token | py |
Token ID | 9078 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
Danger | +0.287 |
� | +0.266 |
nine | +0.262 |
arc | +0.252 |
Ab | +0.252 |
Neg logit contributions | |
ingu | -0.180 |
ascal | -0.170 |
affle | -0.160 |
tto | -0.159 |
ravings | -0.155 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ingu | +0.003 |
tto | +0.003 |
ascal | +0.003 |
pistol | +0.003 |
ravings | +0.003 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
� | -0.003 |
Ab | -0.002 |
thirteen | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ingu | +0.031 |
pistol | +0.029 |
tto | +0.029 |
ascal | +0.028 |
ravings | +0.028 |
Neg logit contributions | |
Danger | -0.024 |
nine | -0.023 |
� | -0.023 |
thirteen | -0.021 |
arc | -0.021 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ingu | +0.015 |
tto | +0.013 |
ascal | +0.012 |
ravings | +0.011 |
affle | +0.010 |
Neg logit contributions | |
Danger | -0.069 |
nine | -0.068 |
� | -0.068 |
thirteen | -0.065 |
Ab | -0.065 |
Token | ers |
Token ID | 364 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ingu | +0.267 |
tto | +0.256 |
ascal | +0.228 |
zed | +0.221 |
Years | +0.217 |
Neg logit contributions | |
Danger | -0.568 |
� | -0.551 |
nine | -0.548 |
arc | -0.533 |
Ab | -0.528 |
Token | became |
Token ID | 2627 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
ingu | +0.058 |
tto | +0.055 |
pistol | +0.053 |
ascal | +0.052 |
ravings | +0.052 |
Neg logit contributions | |
Danger | -0.044 |
nine | -0.042 |
� | -0.040 |
thirteen | -0.039 |
Ab | -0.038 |
Token | good |
Token ID | 922 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
ingu | +0.053 |
tto | +0.050 |
ascal | +0.048 |
ravings | +0.047 |
pistol | +0.047 |
Neg logit contributions | |
nine | -0.053 |
Danger | -0.052 |
� | -0.052 |
Ab | -0.049 |
thirteen | -0.048 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
ingu | +0.053 |
tto | +0.051 |
brand | +0.049 |
pron | +0.048 |
ravings | +0.046 |
Neg logit contributions | |
nine | -0.071 |
Danger | -0.069 |
� | -0.069 |
Ab | -0.066 |
paint | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
ingu | +0.066 |
tto | +0.064 |
affle | +0.061 |
ascal | +0.061 |
ravings | +0.061 |
Neg logit contributions | |
� | -0.031 |
nine | -0.030 |
Danger | -0.030 |
Ab | -0.026 |
thirteen | -0.026 |
Token | j |
Token ID | 474 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ingu | +0.005 |
tto | +0.005 |
ravings | +0.005 |
zed | +0.005 |
scar | +0.005 |
Neg logit contributions | |
nine | -0.004 |
� | -0.004 |
Danger | -0.004 |
arc | -0.003 |
Ab | -0.003 |
Token | olly |
Token ID | 5098 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ingu | +0.039 |
tto | +0.037 |
brand | +0.035 |
ascal | +0.035 |
pistol | +0.035 |
Neg logit contributions | |
Danger | -0.072 |
nine | -0.070 |
� | -0.069 |
Ab | -0.066 |
arc | -0.065 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
ingu | +0.034 |
tto | +0.032 |
ravings | +0.031 |
ascal | +0.031 |
brand | +0.031 |
Neg logit contributions | |
Danger | -0.030 |
nine | -0.030 |
� | -0.030 |
Ab | -0.028 |
thirteen | -0.027 |
Token | named |
Token ID | 3706 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ingu | +0.016 |
tto | +0.015 |
ascal | +0.015 |
ravings | +0.015 |
pistol | +0.015 |
Neg logit contributions | |
Danger | -0.010 |
nine | -0.010 |
� | -0.009 |
Ab | -0.009 |
thirteen | -0.009 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
Danger | +0.034 |
nine | +0.034 |
� | +0.033 |
Ab | +0.031 |
thirteen | +0.031 |
Neg logit contributions | |
ingu | -0.041 |
tto | -0.039 |
ascal | -0.038 |
ravings | -0.037 |
pistol | -0.037 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.026 |
pistol | +0.024 |
ingu | +0.023 |
tto | +0.022 |
pron | +0.021 |
Neg logit contributions | |
nine | -0.058 |
Danger | -0.056 |
� | -0.055 |
Jen | -0.053 |
thirteen | -0.052 |
Token | ers |
Token ID | 364 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ingu | +0.310 |
tto | +0.297 |
ascal | +0.271 |
ravings | +0.261 |
affle | +0.261 |
Neg logit contributions | |
Danger | -0.532 |
nine | -0.521 |
� | -0.519 |
Ab | -0.492 |
thirteen | -0.491 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
ingu | +0.069 |
tto | +0.067 |
ravings | +0.065 |
ascal | +0.065 |
affle | +0.065 |
Neg logit contributions | |
nine | -0.030 |
Danger | -0.030 |
� | -0.030 |
Ab | -0.026 |
thirteen | -0.025 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ingu | +0.008 |
tto | +0.008 |
ascal | +0.007 |
ravings | +0.007 |
pistol | +0.007 |
Neg logit contributions | |
Danger | -0.006 |
nine | -0.006 |
� | -0.006 |
Ab | -0.005 |
thirteen | -0.005 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.030 |
pistol | +0.029 |
pron | +0.028 |
handsome | +0.026 |
zed | +0.025 |
Neg logit contributions | |
nine | -0.049 |
Danger | -0.047 |
� | -0.046 |
are | -0.046 |
Jen | -0.044 |
Token | ers |
Token ID | 364 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ingu | +0.348 |
tto | +0.327 |
pistol | +0.312 |
ascal | +0.312 |
ravings | +0.311 |
Neg logit contributions | |
Danger | -0.488 |
nine | -0.485 |
� | -0.473 |
thirteen | -0.451 |
Ab | -0.451 |
Token | was |
Token ID | 373 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ingu | +0.028 |
brand | +0.028 |
pistol | +0.028 |
tto | +0.027 |
ravings | +0.026 |
Neg logit contributions | |
Danger | -0.029 |
nine | -0.027 |
� | -0.026 |
thirteen | -0.025 |
arc | -0.025 |
Token | heading |
Token ID | 9087 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
ingu | +0.037 |
tto | +0.036 |
brand | +0.035 |
pistol | +0.035 |
ravings | +0.034 |
Neg logit contributions | |
Danger | -0.034 |
nine | -0.032 |
� | -0.032 |
thirteen | -0.030 |
Ab | -0.030 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
brand | +0.061 |
pistol | +0.061 |
ingu | +0.059 |
tto | +0.058 |
hockey | +0.056 |
Neg logit contributions | |
Danger | -0.078 |
� | -0.073 |
nine | -0.073 |
thirteen | -0.072 |
arc | -0.071 |
Token | towards |
Token ID | 3371 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ingu | +0.031 |
tto | +0.030 |
pistol | +0.029 |
ascal | +0.029 |
ravings | +0.029 |
Neg logit contributions | |
Danger | -0.022 |
nine | -0.022 |
� | -0.021 |
thirteen | -0.020 |
Ab | -0.020 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Danger | +0.055 |
nine | +0.053 |
thirteen | +0.051 |
� | +0.051 |
arc | +0.048 |
Neg logit contributions | |
ingu | -0.075 |
tto | -0.072 |
pistol | -0.072 |
brand | -0.070 |
ravings | -0.069 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ingu | +0.030 |
brand | +0.028 |
tto | +0.028 |
pistol | +0.028 |
ascal | +0.026 |
Neg logit contributions | |
Danger | -0.059 |
nine | -0.058 |
� | -0.057 |
thirteen | -0.054 |
Ab | -0.053 |
Token | ers |
Token ID | 364 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
tto | +0.261 |
ingu | +0.254 |
zed | +0.226 |
scar | +0.215 |
ascal | +0.211 |
Neg logit contributions | |
Danger | -0.565 |
nine | -0.552 |
arc | -0.550 |
� | -0.535 |
Ab | -0.528 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
ingu | +0.052 |
pistol | +0.051 |
tto | +0.050 |
ravings | +0.049 |
brand | +0.048 |
Neg logit contributions | |
Danger | -0.042 |
nine | -0.040 |
thirteen | -0.039 |
arc | -0.038 |
Ab | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ingu | +0.003 |
tto | +0.003 |
brand | +0.003 |
ravings | +0.003 |
pistol | +0.003 |
Neg logit contributions | |
Danger | -0.002 |
nine | -0.002 |
thirteen | -0.001 |
� | -0.001 |
arc | -0.001 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
� | +0.029 |
nine | +0.028 |
Danger | +0.028 |
Ab | +0.026 |
Jen | +0.024 |
Neg logit contributions | |
ingu | -0.045 |
tto | -0.043 |
ascal | -0.042 |
ravings | -0.042 |
affle | -0.041 |
Token | as |
Token ID | 355 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Danger | +0.028 |
arc | +0.026 |
thirteen | +0.025 |
nine | +0.025 |
� | +0.025 |
Neg logit contributions | |
tto | -0.029 |
ingu | -0.028 |
pistol | -0.028 |
brand | -0.027 |
Years | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ingu | +0.021 |
tto | +0.021 |
ascal | +0.020 |
affle | +0.020 |
ravings | +0.020 |
Neg logit contributions | |
Danger | -0.012 |
nine | -0.012 |
� | -0.012 |
Ab | -0.011 |
Jen | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
� | +0.011 |
nine | +0.010 |
Danger | +0.010 |
Ab | +0.010 |
Jen | +0.010 |
Neg logit contributions | |
ingu | -0.013 |
ascal | -0.013 |
tto | -0.013 |
affle | -0.012 |
ravings | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ascal | +0.037 |
ingu | +0.035 |
affle | +0.035 |
tto | +0.034 |
ravings | +0.034 |
Neg logit contributions | |
� | -0.022 |
Ab | -0.020 |
Jen | -0.020 |
nine | -0.018 |
Danger | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
ascal | +0.051 |
ingu | +0.051 |
tto | +0.050 |
ravings | +0.050 |
affle | +0.049 |
Neg logit contributions | |
� | -0.040 |
nine | -0.036 |
Danger | -0.034 |
Ab | -0.033 |
paint | -0.032 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ascal | +0.032 |
ingu | +0.032 |
brand | +0.031 |
tto | +0.031 |
ravings | +0.031 |
Neg logit contributions | |
Jen | -0.024 |
Ab | -0.023 |
� | -0.023 |
nine | -0.022 |
K | -0.021 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ingu | +0.023 |
brand | +0.023 |
pron | +0.023 |
pistol | +0.022 |
tto | +0.021 |
Neg logit contributions | |
Danger | -0.060 |
nine | -0.060 |
� | -0.059 |
are | -0.056 |
Ab | -0.056 |
Token | ers |
Token ID | 364 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
ingu | +0.331 |
tto | +0.313 |
ascal | +0.294 |
pistol | +0.290 |
ravings | +0.289 |
Neg logit contributions | |
Danger | -0.508 |
nine | -0.502 |
� | -0.493 |
Ab | -0.470 |
thirteen | -0.469 |
Token | played |
Token ID | 2826 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
ingu | +0.048 |
tto | +0.045 |
pistol | +0.044 |
brand | +0.043 |
ravings | +0.043 |
Neg logit contributions | |
Danger | -0.045 |
nine | -0.043 |
� | -0.043 |
thirteen | -0.041 |
Ab | -0.040 |
Token | with |
Token ID | 351 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ingu | +0.207 |
ascal | +0.204 |
tto | +0.202 |
scar | +0.196 |
ravings | +0.192 |
Neg logit contributions | |
nine | -0.070 |
� | -0.066 |
Danger | -0.065 |
paint | -0.060 |
are | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
tto | +0.059 |
ascal | +0.059 |
ingu | +0.058 |
pron | +0.057 |
ravings | +0.057 |
Neg logit contributions | |
nine | -0.017 |
Danger | -0.015 |
� | -0.015 |
Jen | -0.015 |
are | -0.014 |
Token | new |
Token ID | 649 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ingu | +0.013 |
tto | +0.012 |
pistol | +0.012 |
brand | +0.012 |
ravings | +0.011 |
Neg logit contributions | |
Danger | -0.014 |
nine | -0.014 |
� | -0.013 |
Ab | -0.013 |
thirteen | -0.013 |
Token | I |
Token ID | 40 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
tto | +0.044 |
ingu | +0.043 |
ascal | +0.041 |
pron | +0.041 |
scar | +0.040 |
Neg logit contributions | |
Danger | -0.042 |
nine | -0.041 |
� | -0.037 |
thirteen | -0.037 |
Ab | -0.037 |
Token | 'm |
Token ID | 1101 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
tto | +0.063 |
ingu | +0.061 |
pistol | +0.058 |
scar | +0.057 |
ravings | +0.057 |
Neg logit contributions | |
Danger | -0.037 |
nine | -0.037 |
thirteen | -0.035 |
arc | -0.034 |
Ab | -0.030 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Danger | +0.123 |
nine | +0.116 |
� | +0.114 |
thirteen | +0.111 |
arc | +0.109 |
Neg logit contributions | |
ingu | -0.098 |
tto | -0.094 |
brand | -0.091 |
ascal | -0.088 |
ravings | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ingu | +0.025 |
tto | +0.024 |
ascal | +0.023 |
ravings | +0.023 |
pistol | +0.023 |
Neg logit contributions | |
Danger | -0.011 |
nine | -0.011 |
� | -0.011 |
Ab | -0.010 |
thirteen | -0.010 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
Danger | +0.017 |
nine | +0.017 |
thirteen | +0.015 |
Ab | +0.015 |
� | +0.015 |
Neg logit contributions | |
ingu | -0.021 |
pistol | -0.020 |
brand | -0.020 |
pron | -0.019 |
ravings | -0.018 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ingu | +0.032 |
tto | +0.030 |
pistol | +0.029 |
brand | +0.029 |
ascal | +0.028 |
Neg logit contributions | |
Danger | -0.048 |
nine | -0.048 |
� | -0.047 |
Ab | -0.045 |
thirteen | -0.044 |
Token | ers |
Token ID | 364 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
ingu | +0.302 |
tto | +0.292 |
ascal | +0.264 |
affle | +0.255 |
pistol | +0.255 |
Neg logit contributions | |
Danger | -0.534 |
nine | -0.526 |
� | -0.516 |
Ab | -0.500 |
arc | -0.494 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-03 |
Pos logit contributions | |
ingu | +0.057 |
tto | +0.055 |
pistol | +0.053 |
ravings | +0.053 |
ascal | +0.052 |
Neg logit contributions | |
Danger | -0.037 |
nine | -0.035 |
� | -0.034 |
thirteen | -0.032 |
Ab | -0.032 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
nine | +0.004 |
Danger | +0.003 |
thirteen | +0.003 |
arc | +0.003 |
Ab | +0.003 |
Neg logit contributions | |
ingu | -0.007 |
pistol | -0.007 |
tto | -0.007 |
brand | -0.007 |
ascal | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
� | +0.026 |
Danger | +0.024 |
nine | +0.023 |
Ab | +0.020 |
thirteen | +0.019 |
Neg logit contributions | |
ingu | -0.067 |
tto | -0.065 |
ascal | -0.064 |
ravings | -0.063 |
affle | -0.063 |
Token | go |
Token ID | 467 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
Danger | +0.011 |
nine | +0.011 |
thirteen | +0.011 |
ago | +0.009 |
arc | +0.009 |
Neg logit contributions | |
ingu | -0.016 |
tto | -0.015 |
pistol | -0.015 |
ravings | -0.014 |
brand | -0.014 |
Token | ink |
Token ID | 16882 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
nine | +0.104 |
Danger | +0.097 |
� | +0.094 |
Ab | +0.092 |
Jen | +0.089 |
Neg logit contributions | |
ingu | -0.200 |
tto | -0.193 |
ascal | -0.191 |
ravings | -0.184 |
affle | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +6.40e-05 |
Pos logit contributions | |
nine | +0.002 |
� | +0.002 |
Danger | +0.002 |
thirteen | +0.002 |
Ab | +0.002 |
Neg logit contributions | |
ingu | -0.004 |
tto | -0.004 |
ascal | -0.004 |
affle | -0.004 |
ravings | -0.004 |
Token | Mr |
Token ID | 1770 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
nine | +0.000 |
Danger | +0.000 |
thirteen | +0.000 |
arc | +0.000 |
paint | +0.000 |
Neg logit contributions | |
ingu | -0.000 |
tto | -0.000 |
pistol | -0.000 |
ravings | -0.000 |
brand | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -5.48e-04 |
Pos logit contributions | |
ingu | +0.128 |
tto | +0.124 |
brand | +0.124 |
pron | +0.124 |
ravings | +0.121 |
Neg logit contributions | |
� | -0.050 |
nine | -0.050 |
Danger | -0.049 |
Ab | -0.044 |
thirteen | -0.042 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
ingu | +0.001 |
pistol | +0.001 |
tto | +0.001 |
ascal | +0.001 |
ravings | +0.001 |
Neg logit contributions | |
Danger | -0.001 |
nine | -0.001 |
� | -0.001 |
thirteen | -0.001 |
arc | -0.001 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.023 |
ingu | +0.023 |
pron | +0.022 |
pistol | +0.021 |
tto | +0.020 |
Neg logit contributions | |
nine | -0.056 |
� | -0.056 |
Danger | -0.055 |
Ab | -0.053 |
Jen | -0.053 |
Token | ers |
Token ID | 364 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
ingu | +0.327 |
tto | +0.311 |
ascal | +0.290 |
pistol | +0.286 |
ravings | +0.285 |
Neg logit contributions | |
Danger | -0.512 |
nine | -0.505 |
� | -0.496 |
Ab | -0.473 |
thirteen | -0.472 |
Token | went |
Token ID | 1816 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
ingu | +0.045 |
tto | +0.044 |
pistol | +0.042 |
ravings | +0.041 |
ascal | +0.041 |
Neg logit contributions | |
Danger | -0.042 |
nine | -0.040 |
� | -0.039 |
thirteen | -0.037 |
Ab | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +9.55e-04 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.010 |
pistol | +0.010 |
brand | +0.010 |
ravings | +0.009 |
Neg logit contributions | |
Danger | -0.009 |
nine | -0.008 |
� | -0.008 |
thirteen | -0.008 |
arc | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
Danger | +0.001 |
nine | +0.001 |
thirteen | +0.001 |
� | +0.001 |
arc | +0.001 |
Neg logit contributions | |
ingu | -0.002 |
pistol | -0.002 |
tto | -0.002 |
brand | -0.002 |
ravings | -0.002 |
Token | store |
Token ID | 3650 |
Feature activation | +2.79e-05 |
Pos logit contributions | |
ingu | +0.013 |
pistol | +0.013 |
brand | +0.013 |
ravings | +0.012 |
tto | +0.012 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.012 |
thirteen | -0.012 |
Ab | -0.012 |
� | -0.012 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Danger | +0.031 |
nine | +0.031 |
� | +0.030 |
thirteen | +0.029 |
Ab | +0.028 |
Neg logit contributions | |
ingu | -0.032 |
tto | -0.031 |
pistol | -0.029 |
ravings | -0.029 |
ascal | -0.029 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
brand | +0.028 |
pistol | +0.025 |
ingu | +0.024 |
tto | +0.024 |
pron | +0.023 |
Neg logit contributions | |
nine | -0.063 |
Danger | -0.061 |
� | -0.059 |
Jen | -0.058 |
are | -0.057 |
Token | ers |
Token ID | 364 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ingu | +0.320 |
tto | +0.305 |
ascal | +0.282 |
ravings | +0.274 |
pistol | +0.273 |
Neg logit contributions | |
Danger | -0.523 |
nine | -0.513 |
� | -0.510 |
Ab | -0.485 |
thirteen | -0.483 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
ingu | +0.074 |
tto | +0.072 |
brand | +0.070 |
affle | +0.070 |
ravings | +0.070 |
Neg logit contributions | |
nine | -0.030 |
Danger | -0.029 |
� | -0.029 |
Ab | -0.025 |
Jen | -0.023 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.009 |
ascal | +0.009 |
ravings | +0.009 |
pistol | +0.009 |
Neg logit contributions | |
Danger | -0.007 |
nine | -0.007 |
� | -0.007 |
Ab | -0.007 |
thirteen | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.030 |
pron | +0.029 |
pistol | +0.028 |
zed | +0.026 |
handsome | +0.025 |
Neg logit contributions | |
nine | -0.050 |
are | -0.048 |
Danger | -0.048 |
� | -0.047 |
Jen | -0.046 |
Token | ers |
Token ID | 364 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ingu | +0.359 |
tto | +0.337 |
pistol | +0.326 |
brand | +0.325 |
ravings | +0.324 |
Neg logit contributions | |
Danger | -0.475 |
nine | -0.474 |
� | -0.460 |
thirteen | -0.439 |
Ab | -0.438 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
ingu | +0.057 |
brand | +0.055 |
ravings | +0.054 |
ascal | +0.053 |
pistol | +0.052 |
Neg logit contributions | |
� | -0.045 |
are | -0.042 |
nine | -0.042 |
Danger | -0.041 |
paint | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
ingu | +0.176 |
tto | +0.173 |
ascal | +0.165 |
scar | +0.162 |
ouse | +0.160 |
Neg logit contributions | |
paint | -0.060 |
nine | -0.059 |
Jen | -0.055 |
Danger | -0.054 |
Ab | -0.052 |
Token | play |
Token ID | 711 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
ingu | +0.006 |
tto | +0.006 |
pistol | +0.006 |
ravings | +0.006 |
ascal | +0.006 |
Neg logit contributions | |
Danger | -0.004 |
nine | -0.004 |
� | -0.004 |
thirteen | -0.004 |
Ab | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ingu | +0.149 |
tto | +0.142 |
scar | +0.141 |
ascal | +0.141 |
ongo | +0.140 |
Neg logit contributions | |
paint | -0.049 |
nine | -0.046 |
Danger | -0.043 |
� | -0.041 |
are | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
ingu | +0.056 |
tto | +0.054 |
ascal | +0.051 |
pistol | +0.051 |
brand | +0.051 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.030 |
� | -0.029 |
thirteen | -0.028 |
Ab | -0.027 |
Token | smart |
Token ID | 4451 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ingu | +0.009 |
tto | +0.009 |
ravings | +0.009 |
zed | +0.009 |
scar | +0.008 |
Neg logit contributions | |
nine | -0.007 |
� | -0.006 |
Danger | -0.006 |
Ab | -0.006 |
paint | -0.006 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ingu | +0.114 |
tto | +0.110 |
ravings | +0.104 |
ascal | +0.104 |
brand | +0.104 |
Neg logit contributions | |
nine | -0.096 |
Danger | -0.096 |
� | -0.092 |
Ab | -0.088 |
thirteen | -0.086 |
Token | named |
Token ID | 3706 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ingu | +0.020 |
tto | +0.020 |
ascal | +0.019 |
pistol | +0.019 |
ravings | +0.019 |
Neg logit contributions | |
Danger | -0.015 |
nine | -0.014 |
� | -0.014 |
thirteen | -0.013 |
Ab | -0.013 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Danger | +0.029 |
nine | +0.029 |
� | +0.028 |
thirteen | +0.027 |
arc | +0.026 |
Neg logit contributions | |
ingu | -0.035 |
tto | -0.034 |
pistol | -0.032 |
ravings | -0.032 |
ascal | -0.032 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ingu | +0.025 |
brand | +0.024 |
pistol | +0.023 |
tto | +0.022 |
ravings | +0.021 |
Neg logit contributions | |
nine | -0.066 |
Danger | -0.065 |
� | -0.064 |
Ab | -0.061 |
Jen | -0.061 |
Token | ers |
Token ID | 364 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ingu | +0.306 |
tto | +0.294 |
ascal | +0.268 |
affle | +0.258 |
ravings | +0.257 |
Neg logit contributions | |
Danger | -0.533 |
nine | -0.522 |
� | -0.520 |
Ab | -0.493 |
thirteen | -0.493 |
Token | . |
Token ID | 13 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
ingu | +0.069 |
tto | +0.067 |
ravings | +0.064 |
ascal | +0.064 |
brand | +0.064 |
Neg logit contributions | |
nine | -0.029 |
Danger | -0.029 |
� | -0.029 |
Ab | -0.025 |
thirteen | -0.024 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
ingu | +0.011 |
tto | +0.010 |
ascal | +0.010 |
ravings | +0.010 |
pistol | +0.010 |
Neg logit contributions | |
Danger | -0.008 |
nine | -0.008 |
� | -0.008 |
Ab | -0.007 |
thirteen | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
brand | +0.029 |
pistol | +0.028 |
pron | +0.028 |
ingu | +0.026 |
zed | +0.024 |
Neg logit contributions | |
nine | -0.054 |
Danger | -0.053 |
are | -0.052 |
� | -0.052 |
Jen | -0.050 |
Token | ers |
Token ID | 364 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ingu | +0.350 |
tto | +0.329 |
pistol | +0.316 |
ravings | +0.315 |
ascal | +0.315 |
Neg logit contributions | |
Danger | -0.482 |
nine | -0.479 |
� | -0.467 |
thirteen | -0.445 |
Ab | -0.445 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
Danger | +0.034 |
nine | +0.034 |
� | +0.033 |
Ab | +0.031 |
thirteen | +0.031 |
Neg logit contributions | |
ingu | -0.041 |
tto | -0.039 |
ascal | -0.038 |
ravings | -0.037 |
pistol | -0.037 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.026 |
pistol | +0.024 |
ingu | +0.023 |
tto | +0.022 |
pron | +0.021 |
Neg logit contributions | |
nine | -0.058 |
Danger | -0.056 |
� | -0.055 |
Jen | -0.053 |
thirteen | -0.052 |
Token | ers |
Token ID | 364 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ingu | +0.310 |
tto | +0.297 |
ascal | +0.271 |
ravings | +0.261 |
affle | +0.261 |
Neg logit contributions | |
Danger | -0.532 |
nine | -0.521 |
� | -0.519 |
Ab | -0.492 |
thirteen | -0.491 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
ingu | +0.069 |
tto | +0.067 |
ravings | +0.065 |
ascal | +0.065 |
affle | +0.065 |
Neg logit contributions | |
nine | -0.030 |
Danger | -0.030 |
� | -0.030 |
Ab | -0.026 |
thirteen | -0.025 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ingu | +0.008 |
tto | +0.008 |
ascal | +0.007 |
ravings | +0.007 |
pistol | +0.007 |
Neg logit contributions | |
Danger | -0.006 |
nine | -0.006 |
� | -0.006 |
Ab | -0.005 |
thirteen | -0.005 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.030 |
pistol | +0.029 |
pron | +0.028 |
handsome | +0.026 |
zed | +0.025 |
Neg logit contributions | |
nine | -0.049 |
Danger | -0.047 |
� | -0.046 |
are | -0.046 |
Jen | -0.044 |
Token | ers |
Token ID | 364 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ingu | +0.348 |
tto | +0.327 |
pistol | +0.312 |
ascal | +0.312 |
ravings | +0.311 |
Neg logit contributions | |
Danger | -0.488 |
nine | -0.485 |
� | -0.473 |
thirteen | -0.451 |
Ab | -0.451 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
ingu | +0.051 |
ravings | +0.050 |
brand | +0.049 |
ascal | +0.048 |
pistol | +0.048 |
Neg logit contributions | |
� | -0.048 |
are | -0.044 |
nine | -0.043 |
Danger | -0.042 |
paint | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
ingu | +0.175 |
tto | +0.172 |
ascal | +0.163 |
scar | +0.160 |
affle | +0.159 |
Neg logit contributions | |
paint | -0.063 |
nine | -0.060 |
Danger | -0.058 |
Jen | -0.058 |
Ab | -0.056 |
Token | eat |
Token ID | 4483 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
ingu | +0.004 |
tto | +0.004 |
pistol | +0.004 |
ascal | +0.004 |
ravings | +0.004 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
� | -0.003 |
thirteen | -0.003 |
Ab | -0.003 |
Token | tuna |
Token ID | 38883 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ingu | +0.014 |
tto | +0.013 |
ascal | +0.013 |
ravings | +0.012 |
scar | +0.012 |
Neg logit contributions | |
nine | -0.013 |
Danger | -0.013 |
� | -0.012 |
Ab | -0.012 |
paint | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
Danger | +0.016 |
nine | +0.016 |
� | +0.016 |
Ab | +0.015 |
Jen | +0.014 |
Neg logit contributions | |
ingu | -0.021 |
tto | -0.020 |
pron | -0.019 |
ravings | -0.019 |
brand | -0.019 |
Token | paw |
Token ID | 41827 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
ingu | +0.113 |
tto | +0.112 |
scar | +0.105 |
ascal | +0.101 |
Matthew | +0.101 |
Neg logit contributions | |
nine | -0.078 |
paint | -0.075 |
Danger | -0.073 |
Jen | -0.070 |
� | -0.070 |
Token | again |
Token ID | 757 |
Feature activation | +3.60e-04 |
Pos logit contributions | |
ingu | +0.109 |
tto | +0.106 |
ascal | +0.102 |
ravings | +0.100 |
affle | +0.099 |
Neg logit contributions | |
� | -0.061 |
Danger | -0.061 |
nine | -0.061 |
Ab | -0.054 |
thirteen | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -6.66e-04 |
Pos logit contributions | |
� | +0.000 |
nine | +0.000 |
Danger | +0.000 |
Ab | +0.000 |
paint | +0.000 |
Neg logit contributions | |
ingu | -0.001 |
tto | -0.001 |
ascal | -0.001 |
affle | -0.001 |
ravings | -0.001 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
tto | +0.001 |
ingu | +0.001 |
ascal | +0.001 |
pron | +0.001 |
affle | +0.001 |
Neg logit contributions | |
� | -0.001 |
Danger | -0.001 |
nine | -0.001 |
Jen | -0.001 |
Ab | -0.001 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
brand | +0.022 |
pron | +0.022 |
tto | +0.022 |
ingu | +0.022 |
pistol | +0.021 |
Neg logit contributions | |
nine | -0.059 |
Danger | -0.059 |
� | -0.057 |
Ab | -0.054 |
thirteen | -0.054 |
Token | ers |
Token ID | 364 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ingu | +0.360 |
tto | +0.337 |
ravings | +0.326 |
pistol | +0.326 |
ascal | +0.324 |
Neg logit contributions | |
Danger | -0.475 |
nine | -0.474 |
� | -0.464 |
thirteen | -0.441 |
Ab | -0.438 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
ingu | +0.054 |
tto | +0.052 |
ascal | +0.051 |
ravings | +0.050 |
pistol | +0.050 |
Neg logit contributions | |
nine | -0.043 |
Danger | -0.042 |
� | -0.042 |
Ab | -0.039 |
thirteen | -0.038 |
Token | playing |
Token ID | 2712 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
ingu | +0.171 |
tto | +0.167 |
ouse | +0.164 |
uddle | +0.162 |
affle | +0.156 |
Neg logit contributions | |
Jen | -0.076 |
Ab | -0.067 |
nine | -0.066 |
paint | -0.066 |
K | -0.063 |
Token | in |
Token ID | 287 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
ingu | +0.202 |
tto | +0.188 |
ascal | +0.187 |
ravings | +0.179 |
ongo | +0.177 |
Neg logit contributions | |
� | -0.084 |
nine | -0.083 |
paint | -0.079 |
Danger | -0.079 |
are | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
nine | +0.001 |
Danger | +0.001 |
� | +0.001 |
Ab | +0.001 |
Jen | +0.001 |
Neg logit contributions | |
ingu | -0.003 |
tto | -0.002 |
ascal | -0.002 |
ravings | -0.002 |
affle | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
tto | +0.233 |
Matthew | +0.230 |
scar | +0.229 |
ascal | +0.228 |
brand | +0.226 |
Neg logit contributions | |
� | -0.133 |
nine | -0.130 |
are | -0.129 |
Danger | -0.125 |
paint | -0.120 |
Token | One |
Token ID | 1881 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.010 |
ascal | +0.010 |
ravings | +0.009 |
brand | +0.009 |
Neg logit contributions | |
Danger | -0.004 |
nine | -0.004 |
� | -0.003 |
Ab | -0.003 |
thirteen | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
� | +0.093 |
Danger | +0.093 |
nine | +0.092 |
Ab | +0.084 |
Jen | +0.082 |
Neg logit contributions | |
ingu | -0.146 |
tto | -0.137 |
ascal | -0.136 |
brand | -0.135 |
ravings | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
ingu | +0.059 |
tto | +0.057 |
pistol | +0.056 |
ascal | +0.054 |
brand | +0.054 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.031 |
� | -0.030 |
thirteen | -0.029 |
Ab | -0.028 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
nine | +0.006 |
Danger | +0.006 |
� | +0.006 |
Ab | +0.006 |
Jen | +0.005 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.009 |
ascal | -0.009 |
ravings | -0.009 |
affle | -0.008 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
brand | +0.027 |
pistol | +0.025 |
pron | +0.025 |
tto | +0.023 |
ingu | +0.023 |
Neg logit contributions | |
nine | -0.051 |
Danger | -0.050 |
� | -0.048 |
are | -0.046 |
Jen | -0.046 |
Token | ers |
Token ID | 364 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ingu | +0.334 |
tto | +0.316 |
ascal | +0.297 |
pistol | +0.294 |
ravings | +0.293 |
Neg logit contributions | |
Danger | -0.503 |
nine | -0.498 |
� | -0.489 |
Ab | -0.466 |
thirteen | -0.465 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ingu | +0.053 |
tto | +0.051 |
pistol | +0.049 |
ascal | +0.048 |
ravings | +0.048 |
Neg logit contributions | |
Danger | -0.044 |
nine | -0.043 |
� | -0.041 |
thirteen | -0.040 |
Ab | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
ingu | +0.039 |
tto | +0.038 |
ascal | +0.038 |
ravings | +0.038 |
pron | +0.038 |
Neg logit contributions | |
nine | -0.011 |
Jen | -0.009 |
Danger | -0.009 |
Ab | -0.008 |
� | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
ingu | +0.008 |
tto | +0.008 |
zed | +0.008 |
ascal | +0.008 |
ravings | +0.007 |
Neg logit contributions | |
� | -0.006 |
Danger | -0.006 |
nine | -0.006 |
paint | -0.006 |
arc | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
Danger | +0.050 |
� | +0.048 |
nine | +0.044 |
Ab | +0.037 |
Jen | +0.037 |
Neg logit contributions | |
ingu | -0.118 |
tto | -0.113 |
ascal | -0.112 |
ravings | -0.112 |
brand | -0.109 |
Token | A |
Token ID | 317 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Danger | +0.004 |
� | +0.004 |
nine | +0.004 |
Ab | +0.004 |
thirteen | +0.004 |
Neg logit contributions | |
ingu | -0.005 |
tto | -0.005 |
ascal | -0.005 |
ravings | -0.005 |
affle | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
nine | +0.032 |
Danger | +0.032 |
� | +0.031 |
Ab | +0.029 |
thirteen | +0.028 |
Neg logit contributions | |
ingu | -0.034 |
tto | -0.032 |
ascal | -0.031 |
ravings | -0.030 |
affle | -0.029 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
Danger | +0.018 |
nine | +0.017 |
thirteen | +0.016 |
� | +0.016 |
Ab | +0.016 |
Neg logit contributions | |
pistol | -0.020 |
brand | -0.018 |
ingu | -0.018 |
hockey | -0.018 |
tto | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
tto | +0.014 |
ingu | +0.014 |
pistol | +0.014 |
affle | +0.013 |
scar | +0.013 |
Neg logit contributions | |
Danger | -0.014 |
nine | -0.013 |
thirteen | -0.013 |
arc | -0.012 |
Ab | -0.012 |
Token | Wh |
Token ID | 854 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
nine | +0.034 |
arc | +0.033 |
Danger | +0.032 |
thirteen | +0.032 |
ago | +0.030 |
Neg logit contributions | |
ingu | -0.028 |
pistol | -0.026 |
tto | -0.026 |
ascal | -0.024 |
scar | -0.024 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ingu | +0.022 |
tto | +0.019 |
brand | +0.019 |
pistol | +0.018 |
pron | +0.018 |
Neg logit contributions | |
Danger | -0.068 |
nine | -0.067 |
� | -0.067 |
Ab | -0.063 |
thirteen | -0.063 |
Token | ers |
Token ID | 364 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
tto | +0.265 |
ingu | +0.265 |
affle | +0.228 |
ascal | +0.226 |
pistol | +0.222 |
Neg logit contributions | |
Danger | -0.560 |
nine | -0.548 |
� | -0.545 |
arc | -0.526 |
Ab | -0.522 |
Token | also |
Token ID | 635 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
ingu | +0.047 |
tto | +0.045 |
pistol | +0.045 |
ravings | +0.043 |
ascal | +0.043 |
Neg logit contributions | |
Danger | -0.038 |
nine | -0.036 |
thirteen | -0.035 |
arc | -0.034 |
� | -0.034 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Danger | +0.097 |
nine | +0.095 |
� | +0.092 |
thirteen | +0.087 |
Ab | +0.087 |
Neg logit contributions | |
ingu | -0.121 |
tto | -0.117 |
ascal | -0.111 |
pistol | -0.111 |
ravings | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
Danger | +0.019 |
nine | +0.019 |
� | +0.018 |
Ab | +0.017 |
Jen | +0.016 |
Neg logit contributions | |
ingu | -0.031 |
tto | -0.030 |
ascal | -0.029 |
ravings | -0.029 |
affle | -0.028 |
Token | ball |
Token ID | 2613 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
ingu | +0.013 |
tto | +0.012 |
pistol | +0.012 |
ravings | +0.012 |
brand | +0.011 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.012 |
� | -0.012 |
thirteen | -0.011 |
Ab | -0.011 |
Token | song |
Token ID | 3496 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Danger | +0.039 |
nine | +0.038 |
� | +0.037 |
thirteen | +0.036 |
Ab | +0.035 |
Neg logit contributions | |
ingu | -0.028 |
tto | -0.026 |
pistol | -0.025 |
brand | -0.025 |
ascal | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-03 |
Pos logit contributions | |
ingu | +0.070 |
pistol | +0.068 |
brand | +0.067 |
tto | +0.067 |
pron | +0.065 |
Neg logit contributions | |
Danger | -0.068 |
nine | -0.063 |
thirteen | -0.061 |
� | -0.061 |
Ab | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ingu | +0.004 |
tto | +0.004 |
pistol | +0.004 |
ascal | +0.004 |
ravings | +0.004 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
� | -0.003 |
thirteen | -0.003 |
Ab | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ingu | +0.074 |
ravings | +0.072 |
ascal | +0.070 |
pistol | +0.069 |
brand | +0.069 |
Neg logit contributions | |
� | -0.031 |
Danger | -0.027 |
nine | -0.027 |
Jen | -0.024 |
Ab | -0.023 |
Token | Wh |
Token ID | 1199 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ingu | +0.059 |
tto | +0.056 |
ascal | +0.055 |
ravings | +0.054 |
pistol | +0.054 |
Neg logit contributions | |
Danger | -0.041 |
� | -0.041 |
nine | -0.041 |
thirteen | -0.036 |
Ab | -0.036 |
Token | isk |
Token ID | 1984 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
pistol | +0.026 |
ingu | +0.026 |
brand | +0.026 |
pron | +0.025 |
tto | +0.025 |
Neg logit contributions | |
Danger | -0.066 |
nine | -0.066 |
� | -0.064 |
thirteen | -0.061 |
Jen | -0.060 |
Token | ers |
Token ID | 364 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ingu | +0.282 |
tto | +0.275 |
ascal | +0.243 |
affle | +0.236 |
pistol | +0.231 |
Neg logit contributions | |
Danger | -0.553 |
� | -0.537 |
nine | -0.537 |
Ab | -0.513 |
arc | -0.508 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ingu | +0.048 |
tto | +0.045 |
ascal | +0.043 |
pistol | +0.043 |
ravings | +0.041 |
Neg logit contributions | |
Danger | -0.047 |
nine | -0.044 |
thirteen | -0.043 |
� | -0.041 |
Ab | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -9.49e-05 |
Pos logit contributions | |
Danger | +0.022 |
nine | +0.021 |
� | +0.020 |
thirteen | +0.020 |
arc | +0.020 |
Neg logit contributions | |
ingu | -0.023 |
tto | -0.022 |
pistol | -0.022 |
ravings | -0.021 |
brand | -0.021 |
Token | get |
Token ID | 651 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ingu | +0.000 |
pistol | +0.000 |
pron | +0.000 |
brand | +0.000 |
tto | +0.000 |
Neg logit contributions | |
thirteen | -0.000 |
nine | -0.000 |
ago | -0.000 |
Danger | -0.000 |
Ab | -0.000 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
pistol | +0.032 |
brand | +0.031 |
handsome | +0.031 |
tto | +0.031 |
ingu | +0.031 |
Neg logit contributions | |
Danger | -0.033 |
arc | -0.031 |
thirteen | -0.031 |
ago | -0.030 |
nine | -0.029 |
Token | scared |
Token ID | 12008 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
ingu | +0.013 |
tto | +0.012 |
pistol | +0.012 |
ascal | +0.012 |
ravings | +0.012 |
Neg logit contributions | |
Danger | -0.012 |
nine | -0.012 |
� | -0.012 |
thirteen | -0.011 |
Ab | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
Danger | +0.072 |
nine | +0.070 |
� | +0.067 |
thirteen | +0.066 |
arc | +0.064 |
Neg logit contributions | |
ingu | -0.086 |
pistol | -0.082 |
ascal | -0.082 |
tto | -0.081 |
ravings | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Danger | +0.009 |
nine | +0.009 |
� | +0.009 |
thirteen | +0.008 |
Ab | +0.008 |
Neg logit contributions | |
ingu | -0.014 |
tto | -0.014 |
ascal | -0.013 |
pistol | -0.013 |
ravings | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
ingu | +0.021 |
tto | +0.020 |
ravings | +0.020 |
pistol | +0.020 |
ascal | +0.020 |
Neg logit contributions | |
Danger | -0.012 |
� | -0.012 |
nine | -0.012 |
Ab | -0.011 |
Jen | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
tto | +0.018 |
ingu | +0.017 |
ascal | +0.016 |
scar | +0.016 |
ravings | +0.015 |
Neg logit contributions | |
Danger | -0.014 |
nine | -0.014 |
arc | -0.013 |
thirteen | -0.013 |
Ab | -0.013 |
Token | fireworks |
Token ID | 26056 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
� | +0.061 |
Danger | +0.061 |
Ab | +0.058 |
nine | +0.058 |
thirteen | +0.056 |
Neg logit contributions | |
pistol | -0.060 |
ingu | -0.060 |
tto | -0.057 |
ascal | -0.056 |
affle | -0.056 |
Token | were |
Token ID | 547 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
Danger | +0.210 |
nine | +0.205 |
� | +0.197 |
Ab | +0.191 |
thirteen | +0.190 |
Neg logit contributions | |
ingu | -0.237 |
tto | -0.230 |
pistol | -0.228 |
ascal | -0.218 |
brand | -0.217 |
Token | not |
Token ID | 407 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
nine | +0.089 |
Danger | +0.088 |
� | +0.086 |
thirteen | +0.081 |
Ab | +0.081 |
Neg logit contributions | |
ingu | -0.100 |
tto | -0.096 |
ascal | -0.091 |
ravings | -0.091 |
pistol | -0.090 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ingu | +0.029 |
tto | +0.028 |
ascal | +0.027 |
ravings | +0.027 |
affle | +0.026 |
Neg logit contributions | |
nine | -0.024 |
Danger | -0.024 |
� | -0.023 |
Ab | -0.022 |
thirteen | -0.021 |
Token | anymore |
Token ID | 7471 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
Danger | +0.053 |
� | +0.051 |
nine | +0.049 |
thirteen | +0.046 |
Ab | +0.046 |
Neg logit contributions | |
pistol | -0.037 |
ravings | -0.037 |
ingu | -0.037 |
ascal | -0.035 |
ishing | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
ingu | +0.011 |
tto | +0.011 |
ascal | +0.011 |
pistol | +0.011 |
ravings | +0.011 |
Neg logit contributions | |
Danger | -0.006 |
nine | -0.006 |
� | -0.006 |
thirteen | -0.006 |
Ab | -0.006 |
Token | blue |
Token ID | 4171 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.010 |
ascal | +0.009 |
ravings | +0.009 |
affle | +0.009 |
Neg logit contributions | |
nine | -0.008 |
Danger | -0.008 |
� | -0.008 |
thirteen | -0.007 |
arc | -0.007 |
Token | shirt |
Token ID | 10147 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
Danger | +0.097 |
nine | +0.095 |
� | +0.094 |
Ab | +0.090 |
thirteen | +0.089 |
Neg logit contributions | |
ingu | -0.075 |
tto | -0.071 |
pistol | -0.067 |
ascal | -0.067 |
ravings | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
ingu | +0.180 |
tto | +0.171 |
pistol | +0.169 |
ravings | +0.167 |
brand | +0.166 |
Neg logit contributions | |
Danger | -0.122 |
nine | -0.114 |
� | -0.113 |
Ab | -0.108 |
thirteen | -0.106 |
Token | They |
Token ID | 1119 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ingu | +0.014 |
tto | +0.013 |
pistol | +0.013 |
ravings | +0.013 |
ascal | +0.012 |
Neg logit contributions | |
Danger | -0.009 |
nine | -0.009 |
� | -0.009 |
thirteen | -0.009 |
Ab | -0.008 |
Token | make |
Token ID | 787 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
ingu | +0.032 |
pistol | +0.030 |
tto | +0.029 |
affle | +0.028 |
brand | +0.028 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.020 |
Ab | -0.019 |
Jen | -0.018 |
thirteen | -0.018 |
Token | two |
Token ID | 734 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
tto | +0.124 |
ascal | +0.122 |
ingu | +0.121 |
ravings | +0.118 |
scar | +0.115 |
Neg logit contributions | |
nine | -0.056 |
� | -0.055 |
Danger | -0.054 |
thirteen | -0.048 |
arc | -0.046 |
Token | teams |
Token ID | 3466 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
nine | +0.202 |
Danger | +0.201 |
� | +0.200 |
thirteen | +0.184 |
Ab | +0.181 |
Neg logit contributions | |
ingu | -0.242 |
tto | -0.238 |
ascal | -0.227 |
ravings | -0.224 |
pistol | -0.220 |
Token | with |
Token ID | 351 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
Danger | +0.019 |
Ab | +0.018 |
nine | +0.017 |
thirteen | +0.017 |
� | +0.017 |
Neg logit contributions | |
ingu | -0.022 |
pistol | -0.022 |
tto | -0.021 |
brand | -0.020 |
ravings | -0.020 |
Token | other |
Token ID | 584 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ingu | +0.041 |
tto | +0.039 |
pistol | +0.038 |
ascal | +0.038 |
brand | +0.038 |
Neg logit contributions | |
Danger | -0.030 |
nine | -0.029 |
� | -0.029 |
Ab | -0.027 |
thirteen | -0.027 |
Token | kids |
Token ID | 3988 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
� | +0.148 |
nine | +0.148 |
Danger | +0.144 |
thirteen | +0.132 |
arc | +0.129 |
Neg logit contributions | |
tto | -0.204 |
ingu | -0.200 |
ascal | -0.191 |
ravings | -0.188 |
scar | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
Danger | +0.058 |
nine | +0.054 |
thirteen | +0.052 |
Ab | +0.052 |
� | +0.051 |
Neg logit contributions | |
ingu | -0.074 |
pistol | -0.070 |
tto | -0.069 |
ascal | -0.067 |
ravings | -0.067 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
Danger | +0.059 |
nine | +0.057 |
� | +0.054 |
thirteen | +0.053 |
Ab | +0.052 |
Neg logit contributions | |
ingu | -0.064 |
tto | -0.062 |
pistol | -0.058 |
ascal | -0.058 |
brand | -0.058 |
Token | back |
Token ID | 736 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
� | +0.044 |
nine | +0.041 |
Ab | +0.037 |
Danger | +0.037 |
thirteen | +0.034 |
Neg logit contributions | |
ingu | -0.095 |
tto | -0.095 |
affle | -0.093 |
scar | -0.090 |
ascal | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ingu | +0.028 |
tto | +0.027 |
pistol | +0.027 |
brand | +0.027 |
ravings | +0.026 |
Neg logit contributions | |
Danger | -0.027 |
nine | -0.024 |
thirteen | -0.024 |
� | -0.023 |
arc | -0.022 |
Token | immediately |
Token ID | 3393 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ingu | +0.023 |
tto | +0.022 |
ascal | +0.021 |
pistol | +0.021 |
ravings | +0.021 |
Neg logit contributions | |
Danger | -0.018 |
nine | -0.018 |
� | -0.017 |
Ab | -0.016 |
thirteen | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
ingu | +0.019 |
tto | +0.018 |
ascal | +0.017 |
pistol | +0.017 |
ravings | +0.017 |
Neg logit contributions | |
Danger | -0.016 |
nine | -0.015 |
� | -0.015 |
Ab | -0.014 |
thirteen | -0.014 |
Token | two |
Token ID | 734 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
pistol | +0.009 |
ingu | +0.009 |
brand | +0.009 |
pron | +0.009 |
tto | +0.008 |
Neg logit contributions | |
Danger | -0.009 |
nine | -0.008 |
� | -0.008 |
thirteen | -0.008 |
Ab | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
Danger | +0.203 |
nine | +0.197 |
� | +0.190 |
thirteen | +0.181 |
Ab | +0.179 |
Neg logit contributions | |
ingu | -0.257 |
tto | -0.244 |
pistol | -0.235 |
ascal | -0.235 |
brand | -0.233 |
Token | them |
Token ID | 606 |
Feature activation | -3.93e-04 |
Pos logit contributions | |
Danger | +0.124 |
nine | +0.120 |
� | +0.119 |
thirteen | +0.110 |
Ab | +0.109 |
Neg logit contributions | |
ingu | -0.165 |
tto | -0.158 |
ascal | -0.152 |
pistol | -0.150 |
ravings | -0.150 |
Token | were |
Token ID | 547 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
ingu | +0.001 |
tto | +0.001 |
pistol | +0.001 |
brand | +0.001 |
ravings | +0.001 |
Neg logit contributions | |
Danger | -0.001 |
nine | -0.001 |
� | -0.001 |
thirteen | -0.001 |
Ab | -0.001 |
Token | having |
Token ID | 1719 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
Danger | +0.081 |
nine | +0.081 |
� | +0.079 |
Ab | +0.074 |
thirteen | +0.074 |
Neg logit contributions | |
ingu | -0.086 |
tto | -0.083 |
ascal | -0.079 |
pistol | -0.079 |
ravings | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
ingu | +0.002 |
tto | +0.002 |
ascal | +0.002 |
ravings | +0.002 |
pistol | +0.002 |
Neg logit contributions | |
� | -0.002 |
nine | -0.002 |
Danger | -0.002 |
Ab | -0.002 |
thirteen | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ingu | +0.071 |
tto | +0.069 |
pistol | +0.065 |
ascal | +0.064 |
brand | +0.064 |
Neg logit contributions | |
Danger | -0.069 |
nine | -0.066 |
thirteen | -0.062 |
� | -0.061 |
arc | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
ingu | +0.030 |
tto | +0.029 |
ascal | +0.027 |
brand | +0.027 |
pistol | +0.027 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.031 |
� | -0.030 |
thirteen | -0.029 |
Ab | -0.028 |
Token | fat |
Token ID | 3735 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ingu | +0.093 |
tto | +0.093 |
brand | +0.088 |
ravings | +0.084 |
ascal | +0.083 |
Neg logit contributions | |
Danger | -0.134 |
nine | -0.129 |
thirteen | -0.123 |
� | -0.121 |
arc | -0.121 |
Token | that |
Token ID | 326 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
Danger | +0.021 |
nine | +0.020 |
� | +0.020 |
thirteen | +0.018 |
Ab | +0.018 |
Neg logit contributions | |
ingu | -0.025 |
tto | -0.024 |
pistol | -0.023 |
ascal | -0.023 |
ravings | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
ingu | +0.119 |
tto | +0.113 |
pistol | +0.110 |
brand | +0.107 |
ravings | +0.106 |
Neg logit contributions | |
Danger | -0.145 |
nine | -0.140 |
� | -0.131 |
thirteen | -0.131 |
arc | -0.129 |
Token | rain |
Token ID | 6290 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
pistol | +0.008 |
ingu | +0.008 |
brand | +0.007 |
tto | +0.007 |
pron | +0.007 |
Neg logit contributions | |
Danger | -0.007 |
nine | -0.006 |
� | -0.006 |
thirteen | -0.006 |
arc | -0.005 |
Token | couldn |
Token ID | 3521 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Danger | +0.202 |
nine | +0.199 |
� | +0.195 |
Ab | +0.182 |
thirteen | +0.182 |
Neg logit contributions | |
ingu | -0.233 |
tto | -0.223 |
ascal | -0.214 |
pistol | -0.212 |
ravings | -0.211 |
Token | 't |
Token ID | 470 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
tto | +0.068 |
zed | +0.065 |
ingu | +0.065 |
pistol | +0.064 |
scar | +0.063 |
Neg logit contributions | |
nine | -0.045 |
Danger | -0.041 |
thirteen | -0.040 |
arc | -0.040 |
Ab | -0.039 |
Token | reach |
Token ID | 3151 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
nine | +0.100 |
Danger | +0.097 |
thirteen | +0.097 |
ago | +0.088 |
Flowers | +0.086 |
Neg logit contributions | |
Years | -0.125 |
ingu | -0.124 |
tto | -0.124 |
zed | -0.123 |
pistol | -0.121 |
Token | him |
Token ID | 683 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
Danger | +0.003 |
nine | +0.003 |
� | +0.003 |
thirteen | +0.003 |
arc | +0.003 |
Neg logit contributions | |
ingu | -0.004 |
tto | -0.004 |
pistol | -0.004 |
brand | -0.004 |
ravings | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.42e-04 |
Pos logit contributions | |
ingu | +0.159 |
tto | +0.152 |
pistol | +0.150 |
brand | +0.148 |
ravings | +0.146 |
Neg logit contributions | |
Danger | -0.106 |
nine | -0.105 |
thirteen | -0.095 |
� | -0.095 |
Ab | -0.091 |
Token | ever |
Token ID | 1683 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ingu | +0.285 |
tto | +0.275 |
brand | +0.272 |
pistol | +0.269 |
ravings | +0.262 |
Neg logit contributions | |
Danger | -0.199 |
nine | -0.187 |
thirteen | -0.172 |
arc | -0.170 |
Ab | -0.168 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
Danger | +0.096 |
nine | +0.085 |
thirteen | +0.077 |
Ab | +0.077 |
� | +0.077 |
Neg logit contributions | |
ingu | -0.099 |
brand | -0.096 |
tto | -0.092 |
pistol | -0.091 |
ravings | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
Danger | +0.038 |
nine | +0.038 |
thirteen | +0.036 |
� | +0.035 |
arc | +0.034 |
Neg logit contributions | |
ingu | -0.043 |
tto | -0.040 |
pistol | -0.039 |
ascal | -0.038 |
ravings | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ingu | +0.043 |
ravings | +0.041 |
tto | +0.041 |
pistol | +0.041 |
ascal | +0.040 |
Neg logit contributions | |
� | -0.024 |
Danger | -0.024 |
nine | -0.023 |
Ab | -0.021 |
Jen | -0.020 |
Token | The |
Token ID | 464 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ingu | +0.033 |
tto | +0.032 |
ascal | +0.030 |
Years | +0.030 |
scar | +0.030 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.032 |
Ab | -0.030 |
thirteen | -0.030 |
arc | -0.030 |
Token | two |
Token ID | 734 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Danger | +0.038 |
nine | +0.037 |
� | +0.037 |
thirteen | +0.034 |
Ab | +0.034 |
Neg logit contributions | |
ingu | -0.041 |
tto | -0.040 |
ascal | -0.038 |
ravings | -0.037 |
pistol | -0.037 |
Token | children |
Token ID | 1751 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
nine | +0.242 |
Danger | +0.242 |
� | +0.238 |
Ab | +0.223 |
thirteen | +0.223 |
Neg logit contributions | |
ingu | -0.213 |
tto | -0.208 |
ascal | -0.196 |
ravings | -0.195 |
pistol | -0.193 |
Token | spent |
Token ID | 3377 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
Danger | +0.086 |
nine | +0.079 |
thirteen | +0.078 |
arc | +0.076 |
Jen | +0.072 |
Neg logit contributions | |
ingu | -0.078 |
tto | -0.070 |
pistol | -0.066 |
affle | -0.064 |
scar | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ingu | +0.212 |
ascal | +0.211 |
ravings | +0.203 |
tto | +0.200 |
pron | +0.200 |
Neg logit contributions | |
nine | -0.050 |
� | -0.047 |
Jen | -0.038 |
Ab | -0.038 |
are | -0.037 |
Token | rest |
Token ID | 1334 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ingu | +0.020 |
ascal | +0.019 |
ravings | +0.019 |
tto | +0.019 |
pistol | +0.019 |
Neg logit contributions | |
� | -0.014 |
nine | -0.013 |
Danger | -0.013 |
Ab | -0.012 |
thirteen | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ingu | +0.085 |
tto | +0.083 |
ascal | +0.080 |
pistol | +0.080 |
ravings | +0.080 |
Neg logit contributions | |
Danger | -0.032 |
nine | -0.032 |
� | -0.031 |
Ab | -0.027 |
thirteen | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
Danger | +0.077 |
nine | +0.072 |
� | +0.070 |
thirteen | +0.068 |
Ab | +0.067 |
Neg logit contributions | |
ingu | -0.087 |
ravings | -0.084 |
brand | -0.083 |
pistol | -0.083 |
tto | -0.082 |
Token | but |
Token ID | 475 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Danger | +0.025 |
nine | +0.023 |
� | +0.023 |
arc | +0.022 |
thirteen | +0.022 |
Neg logit contributions | |
ingu | -0.026 |
pistol | -0.025 |
brand | -0.025 |
tto | -0.025 |
pron | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ingu | +0.043 |
tto | +0.042 |
ascal | +0.041 |
ravings | +0.040 |
pistol | +0.040 |
Neg logit contributions | |
Danger | -0.031 |
nine | -0.030 |
� | -0.030 |
Ab | -0.027 |
thirteen | -0.027 |
Token | stumbled |
Token ID | 24241 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
� | +0.035 |
nine | +0.034 |
Danger | +0.033 |
Ab | +0.031 |
Jen | +0.031 |
Neg logit contributions | |
ingu | -0.053 |
brand | -0.051 |
ravings | -0.050 |
ascal | -0.049 |
pistol | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Danger | +0.047 |
nine | +0.041 |
thirteen | +0.040 |
arc | +0.040 |
� | +0.039 |
Neg logit contributions | |
ingu | -0.060 |
tto | -0.059 |
pistol | -0.055 |
ascal | -0.055 |
brand | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
nine | +0.012 |
Danger | +0.012 |
� | +0.011 |
Ab | +0.010 |
thirteen | +0.010 |
Neg logit contributions | |
ingu | -0.029 |
tto | -0.028 |
ascal | -0.027 |
affle | -0.027 |
ravings | -0.027 |
Token | rock |
Token ID | 3881 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Danger | +0.002 |
nine | +0.002 |
� | +0.002 |
Ab | +0.002 |
thirteen | +0.002 |
Neg logit contributions | |
ingu | -0.004 |
tto | -0.004 |
ascal | -0.003 |
ravings | -0.003 |
pistol | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
pistol | +0.021 |
tto | +0.020 |
ingu | +0.020 |
ravings | +0.020 |
pron | +0.019 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.020 |
Ab | -0.019 |
thirteen | -0.019 |
Flowers | -0.019 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ingu | +0.019 |
tto | +0.018 |
pistol | +0.017 |
ravings | +0.017 |
brand | +0.017 |
Neg logit contributions | |
Danger | -0.018 |
nine | -0.017 |
� | -0.017 |
arc | -0.016 |
thirteen | -0.016 |
Token | down |
Token ID | 866 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
Danger | +0.033 |
� | +0.030 |
nine | +0.030 |
thirteen | +0.028 |
arc | +0.028 |
Neg logit contributions | |
ingu | -0.037 |
tto | -0.036 |
pistol | -0.036 |
ascal | -0.034 |
brand | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
pistol | +0.023 |
tto | +0.022 |
zed | +0.021 |
brand | +0.021 |
hockey | +0.021 |
Neg logit contributions | |
Danger | -0.027 |
arc | -0.025 |
thirteen | -0.025 |
nine | -0.024 |
� | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Danger | +0.004 |
nine | +0.004 |
� | +0.004 |
thirteen | +0.004 |
Ab | +0.004 |
Neg logit contributions | |
ingu | -0.006 |
tto | -0.005 |
pistol | -0.005 |
ascal | -0.005 |
ravings | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ingu | +0.045 |
ravings | +0.044 |
tto | +0.044 |
ascal | +0.043 |
pistol | +0.043 |
Neg logit contributions | |
� | -0.020 |
Danger | -0.020 |
nine | -0.019 |
Jen | -0.017 |
Ab | -0.017 |
Token | They |
Token ID | 2990 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
tto | +0.027 |
ingu | +0.026 |
ascal | +0.025 |
Years | +0.025 |
scar | +0.025 |
Neg logit contributions | |
Danger | -0.036 |
Ab | -0.035 |
nine | -0.034 |
thirteen | -0.034 |
Am | -0.032 |
Token | started |
Token ID | 2067 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ingu | +0.017 |
tto | +0.016 |
pistol | +0.015 |
ascal | +0.015 |
ravings | +0.015 |
Neg logit contributions | |
Danger | -0.014 |
nine | -0.013 |
� | -0.013 |
Ab | -0.012 |
thirteen | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
nine | +0.059 |
Danger | +0.058 |
� | +0.057 |
thirteen | +0.051 |
Ab | +0.051 |
Neg logit contributions | |
ingu | -0.101 |
tto | -0.099 |
ascal | -0.095 |
affle | -0.094 |
ravings | -0.092 |
Token | scoop |
Token ID | 23529 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Danger | +0.006 |
nine | +0.006 |
� | +0.006 |
thirteen | +0.005 |
Ab | +0.005 |
Neg logit contributions | |
ingu | -0.010 |
tto | -0.009 |
pistol | -0.009 |
ascal | -0.009 |
ravings | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Danger | +0.015 |
nine | +0.015 |
� | +0.015 |
Ab | +0.013 |
thirteen | +0.013 |
Neg logit contributions | |
ingu | -0.024 |
tto | -0.023 |
ascal | -0.022 |
ravings | -0.022 |
pistol | -0.022 |
Token | sauce |
Token ID | 10746 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
Danger | +0.069 |
nine | +0.068 |
� | +0.067 |
thirteen | +0.064 |
Ab | +0.063 |
Neg logit contributions | |
ingu | -0.055 |
tto | -0.053 |
ascal | -0.050 |
ravings | -0.049 |
pistol | -0.049 |
Token | from |
Token ID | 422 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
ingu | +0.167 |
tto | +0.160 |
pistol | +0.156 |
ravings | +0.153 |
ascal | +0.153 |
Neg logit contributions | |
Danger | -0.109 |
nine | -0.104 |
� | -0.098 |
Ab | -0.096 |
thirteen | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
Danger | +0.070 |
nine | +0.069 |
� | +0.067 |
Ab | +0.062 |
thirteen | +0.062 |
Neg logit contributions | |
ingu | -0.102 |
tto | -0.098 |
ascal | -0.094 |
pistol | -0.094 |
ravings | -0.094 |
Token | bowl |
Token ID | 9396 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
ingu | +0.010 |
tto | +0.010 |
pistol | +0.009 |
ascal | +0.009 |
ravings | +0.009 |
Neg logit contributions | |
Danger | -0.010 |
nine | -0.010 |
� | -0.010 |
Ab | -0.010 |
thirteen | -0.009 |
Token | check |
Token ID | 2198 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
Danger | +0.022 |
nine | +0.022 |
thirteen | +0.021 |
Ab | +0.019 |
arc | +0.019 |
Neg logit contributions | |
ingu | -0.035 |
pistol | -0.034 |
tto | -0.034 |
brand | -0.032 |
affle | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
ingu | +0.093 |
pistol | +0.092 |
tto | +0.085 |
affle | +0.084 |
brand | +0.083 |
Neg logit contributions | |
Danger | -0.080 |
arc | -0.075 |
� | -0.074 |
thirteen | -0.074 |
nine | -0.071 |
Token | out |
Token ID | 503 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Danger | +0.003 |
nine | +0.002 |
thirteen | +0.002 |
Ab | +0.002 |
� | +0.002 |
Neg logit contributions | |
ingu | -0.003 |
tto | -0.003 |
pistol | -0.003 |
brand | -0.003 |
affle | -0.003 |
Token | ," |
Token ID | 553 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
Danger | +0.016 |
arc | +0.014 |
nine | +0.014 |
thirteen | +0.014 |
Sylv | +0.013 |
Neg logit contributions | |
ingu | -0.022 |
brand | -0.021 |
pistol | -0.020 |
tto | -0.020 |
udd | -0.019 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
Danger | +0.102 |
nine | +0.100 |
thirteen | +0.097 |
arc | +0.090 |
� | +0.089 |
Neg logit contributions | |
ingu | -0.111 |
pistol | -0.106 |
tto | -0.103 |
scar | -0.099 |
hockey | -0.099 |
Token | said |
Token ID | 531 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ingu | +0.149 |
tto | +0.142 |
pistol | +0.137 |
ascal | +0.135 |
ravings | +0.133 |
Neg logit contributions | |
Danger | -0.125 |
nine | -0.122 |
thirteen | -0.114 |
� | -0.113 |
arc | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Danger | +0.025 |
nine | +0.024 |
thirteen | +0.023 |
� | +0.022 |
arc | +0.021 |
Neg logit contributions | |
ingu | -0.035 |
tto | -0.034 |
pistol | -0.034 |
ascal | -0.033 |
brand | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Danger | +0.014 |
nine | +0.014 |
� | +0.013 |
Ab | +0.012 |
thirteen | +0.012 |
Neg logit contributions | |
ingu | -0.020 |
tto | -0.020 |
ascal | -0.019 |
ravings | -0.019 |
brand | -0.019 |
Token | But |
Token ID | 1537 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
ingu | +0.033 |
tto | +0.032 |
ascal | +0.032 |
pistol | +0.031 |
Years | +0.031 |
Neg logit contributions | |
nine | -0.024 |
Danger | -0.023 |
Ab | -0.022 |
� | -0.022 |
thirteen | -0.021 |
Token | be |
Token ID | 307 |
Feature activation | +3.08e-04 |
Pos logit contributions | |
Danger | +0.115 |
nine | +0.111 |
thirteen | +0.104 |
� | +0.100 |
adies | +0.095 |
Neg logit contributions | |
pistol | -0.143 |
ingu | -0.143 |
brand | -0.140 |
tto | -0.129 |
hockey | -0.129 |
Token | quiet |
Token ID | 5897 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
nine | +0.001 |
� | +0.000 |
Danger | +0.000 |
thirteen | +0.000 |
Jen | +0.000 |
Neg logit contributions | |
ingu | -0.001 |
tto | -0.000 |
ascal | -0.000 |
ravings | -0.000 |
pistol | -0.000 |
Token | together |
Token ID | 1978 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
ingu | +0.171 |
tto | +0.162 |
ravings | +0.159 |
brand | +0.157 |
pistol | +0.157 |
Neg logit contributions | |
Danger | -0.082 |
nine | -0.077 |
� | -0.074 |
thirteen | -0.071 |
Ab | -0.070 |
Token | ." |
Token ID | 526 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Danger | +0.004 |
nine | +0.004 |
� | +0.004 |
thirteen | +0.004 |
Ab | +0.004 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.009 |
ravings | -0.009 |
pistol | -0.008 |
ascal | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
Danger | +0.035 |
nine | +0.035 |
� | +0.033 |
thirteen | +0.032 |
Ab | +0.031 |
Neg logit contributions | |
ingu | -0.052 |
tto | -0.050 |
pistol | -0.048 |
ravings | -0.048 |
ascal | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ingu | +0.042 |
ascal | +0.042 |
ravings | +0.041 |
pistol | +0.041 |
affle | +0.040 |
Neg logit contributions | |
� | -0.013 |
Jen | -0.010 |
Danger | -0.009 |
Ab | -0.009 |
nine | -0.009 |
Token | After |
Token ID | 3260 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
ingu | +0.029 |
tto | +0.027 |
ascal | +0.027 |
pistol | +0.026 |
ravings | +0.026 |
Neg logit contributions | |
Danger | -0.023 |
nine | -0.023 |
� | -0.023 |
Ab | -0.021 |
thirteen | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Danger | +0.104 |
nine | +0.103 |
� | +0.100 |
Ab | +0.093 |
thirteen | +0.091 |
Neg logit contributions | |
ingu | -0.163 |
tto | -0.157 |
ascal | -0.152 |
ravings | -0.151 |
pistol | -0.150 |
Token | drank |
Token ID | 24070 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Danger | +0.022 |
nine | +0.022 |
thirteen | +0.021 |
� | +0.020 |
arc | +0.020 |
Neg logit contributions | |
ingu | -0.023 |
tto | -0.022 |
brand | -0.021 |
ravings | -0.020 |
ascal | -0.020 |
Token | juice |
Token ID | 13135 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ingu | +0.072 |
tto | +0.070 |
pistol | +0.067 |
ascal | +0.067 |
ravings | +0.067 |
Neg logit contributions | |
Danger | -0.041 |
nine | -0.040 |
� | -0.039 |
thirteen | -0.036 |
Ab | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
� | +0.008 |
nine | +0.008 |
Danger | +0.007 |
Ab | +0.007 |
are | +0.006 |
Neg logit contributions | |
ingu | -0.024 |
ascal | -0.024 |
tto | -0.024 |
affle | -0.023 |
ravings | -0.023 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Danger | +0.022 |
� | +0.021 |
thirteen | +0.021 |
nine | +0.020 |
arc | +0.018 |
Neg logit contributions | |
ingu | -0.029 |
pistol | -0.028 |
brand | -0.027 |
tto | -0.027 |
pron | -0.026 |
Token | my |
Token ID | 1820 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
� | +0.015 |
nine | +0.013 |
paint | +0.007 |
Jen | +0.007 |
ill | +0.006 |
Neg logit contributions | |
brand | -0.086 |
tto | -0.086 |
zed | -0.086 |
ravings | -0.084 |
affle | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ingu | +0.039 |
tto | +0.037 |
ascal | +0.037 |
ravings | +0.037 |
pistol | +0.037 |
Neg logit contributions | |
� | -0.021 |
nine | -0.020 |
Danger | -0.020 |
Ab | -0.018 |
Jen | -0.018 |
Token | " |
Token ID | 1 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
ingu | +0.028 |
tto | +0.028 |
Years | +0.026 |
scar | +0.026 |
ascal | +0.025 |
Neg logit contributions | |
Danger | -0.029 |
Ab | -0.027 |
nine | -0.026 |
arc | -0.026 |
paint | -0.026 |
Token | Really |
Token ID | 26392 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
Danger | +0.078 |
nine | +0.076 |
� | +0.074 |
Ab | +0.069 |
thirteen | +0.069 |
Neg logit contributions | |
ingu | -0.117 |
tto | -0.113 |
ascal | -0.109 |
pistol | -0.108 |
ravings | -0.107 |
Token | ? |
Token ID | 30 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Danger | +0.007 |
nine | +0.006 |
� | +0.006 |
thirteen | +0.006 |
Ab | +0.006 |
Neg logit contributions | |
ingu | -0.009 |
tto | -0.008 |
ascal | -0.008 |
pistol | -0.008 |
brand | -0.008 |
Token | Did |
Token ID | 7731 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ingu | +0.032 |
pistol | +0.030 |
hockey | +0.030 |
brand | +0.030 |
tto | +0.029 |
Neg logit contributions | |
nine | -0.021 |
arc | -0.020 |
Danger | -0.020 |
thirteen | -0.020 |
paint | -0.019 |
Token | you |
Token ID | 345 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
nine | +0.079 |
Danger | +0.079 |
arc | +0.074 |
thirteen | +0.072 |
� | +0.070 |
Neg logit contributions | |
ingu | -0.133 |
tto | -0.122 |
pistol | -0.119 |
brand | -0.118 |
hockey | -0.115 |
Token | ever |
Token ID | 1683 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
Danger | +0.079 |
nine | +0.078 |
Ab | +0.071 |
� | +0.071 |
thirteen | +0.070 |
Neg logit contributions | |
ingu | -0.147 |
tto | -0.141 |
pistol | -0.138 |
ascal | -0.136 |
brand | -0.136 |
Token | lose |
Token ID | 4425 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
Danger | +0.081 |
nine | +0.080 |
� | +0.072 |
Ab | +0.072 |
thirteen | +0.071 |
Neg logit contributions | |
ingu | -0.138 |
tto | -0.130 |
pistol | -0.127 |
brand | -0.127 |
ascal | -0.126 |
Token | your |
Token ID | 534 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ingu | +0.061 |
pistol | +0.058 |
tto | +0.058 |
brand | +0.057 |
ascal | +0.056 |
Neg logit contributions | |
Danger | -0.047 |
� | -0.044 |
nine | -0.044 |
thirteen | -0.042 |
Ab | -0.041 |
Token | boats |
Token ID | 16659 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
nine | +0.032 |
Danger | +0.031 |
� | +0.031 |
paint | +0.029 |
arc | +0.028 |
Neg logit contributions | |
ingu | -0.036 |
tto | -0.035 |
ascal | -0.033 |
ravings | -0.032 |
scar | -0.032 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
� | +0.082 |
nine | +0.081 |
Danger | +0.077 |
paint | +0.070 |
thirteen | +0.069 |
Neg logit contributions | |
ingu | -0.153 |
tto | -0.151 |
ascal | -0.146 |
affle | -0.142 |
ravings | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
ingu | +0.014 |
pistol | +0.013 |
tto | +0.013 |
brand | +0.013 |
ascal | +0.013 |
Neg logit contributions | |
Danger | -0.010 |
nine | -0.009 |
� | -0.009 |
Ab | -0.009 |
thirteen | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Danger | +0.002 |
� | +0.002 |
nine | +0.002 |
thirteen | +0.001 |
arc | +0.001 |
Neg logit contributions | |
ingu | -0.004 |
ravings | -0.004 |
tto | -0.004 |
affle | -0.003 |
brand | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
nine | +0.033 |
� | +0.032 |
Danger | +0.031 |
Ab | +0.028 |
paint | +0.028 |
Neg logit contributions | |
ingu | -0.051 |
tto | -0.050 |
ascal | -0.049 |
ravings | -0.049 |
pistol | -0.048 |
Token | many |
Token ID | 867 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
Danger | +0.029 |
� | +0.026 |
nine | +0.026 |
thirteen | +0.025 |
Ab | +0.025 |
Neg logit contributions | |
ingu | -0.035 |
tto | -0.032 |
brand | -0.032 |
ravings | -0.031 |
pron | -0.031 |
Token | colors |
Token ID | 7577 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
Danger | +0.012 |
nine | +0.012 |
� | +0.011 |
Ab | +0.011 |
thirteen | +0.011 |
Neg logit contributions | |
ingu | -0.020 |
tto | -0.019 |
ascal | -0.018 |
pistol | -0.018 |
ravings | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Danger | +0.103 |
nine | +0.097 |
� | +0.095 |
Ab | +0.089 |
thirteen | +0.088 |
Neg logit contributions | |
ingu | -0.149 |
tto | -0.141 |
brand | -0.138 |
pistol | -0.137 |
ascal | -0.136 |
Token | made |
Token ID | 925 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
ingu | +0.025 |
tto | +0.023 |
brand | +0.023 |
pistol | +0.022 |
ascal | +0.022 |
Neg logit contributions | |
Danger | -0.017 |
nine | -0.016 |
� | -0.016 |
thirteen | -0.015 |
Ab | -0.015 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ingu | +0.121 |
brand | +0.113 |
tto | +0.111 |
ascal | +0.109 |
ravings | +0.108 |
Neg logit contributions | |
Danger | -0.094 |
� | -0.090 |
nine | -0.090 |
thirteen | -0.084 |
Ab | -0.083 |
Token | pictures |
Token ID | 5986 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
Danger | +0.037 |
nine | +0.034 |
� | +0.034 |
thirteen | +0.032 |
Ab | +0.031 |
Neg logit contributions | |
ingu | -0.036 |
brand | -0.034 |
ascal | -0.031 |
pistol | -0.031 |
udd | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Danger | +0.110 |
nine | +0.099 |
Ab | +0.097 |
thirteen | +0.094 |
� | +0.092 |
Neg logit contributions | |
brand | -0.106 |
ingu | -0.106 |
pistol | -0.095 |
pron | -0.094 |
ravings | -0.093 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Danger | +0.126 |
� | +0.120 |
nine | +0.120 |
thirteen | +0.111 |
Ab | +0.106 |
Neg logit contributions | |
ingu | -0.177 |
brand | -0.165 |
pistol | -0.163 |
ascal | -0.162 |
tto | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ingu | +0.045 |
tto | +0.043 |
ravings | +0.043 |
pistol | +0.042 |
ascal | +0.042 |
Neg logit contributions | |
Danger | -0.025 |
� | -0.025 |
nine | -0.025 |
Ab | -0.023 |
Jen | -0.022 |
Token | Ben |
Token ID | 11696 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
tto | +0.026 |
Matthew | +0.025 |
Mic | +0.025 |
Years | +0.025 |
Jeremy | +0.024 |
Neg logit contributions | |
Danger | -0.039 |
thirteen | -0.038 |
Ab | -0.038 |
arc | -0.037 |
nine | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ingu | +0.095 |
tto | +0.091 |
ascal | +0.088 |
ravings | +0.088 |
brand | +0.087 |
Neg logit contributions | |
� | -0.072 |
nine | -0.071 |
Danger | -0.071 |
thirteen | -0.065 |
Ab | -0.064 |
Token | Mia |
Token ID | 32189 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ingu | +0.023 |
pistol | +0.021 |
tto | +0.021 |
ascal | +0.020 |
ravings | +0.020 |
Neg logit contributions | |
Danger | -0.017 |
� | -0.016 |
nine | -0.015 |
thirteen | -0.015 |
arc | -0.015 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
Danger | +0.053 |
nine | +0.050 |
thirteen | +0.048 |
Ab | +0.048 |
Jen | +0.048 |
Neg logit contributions | |
ingu | -0.036 |
pistol | -0.031 |
tto | -0.031 |
ascal | -0.029 |
brand | -0.028 |
Token | about |
Token ID | 546 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
Danger | +0.004 |
nine | +0.004 |
� | +0.004 |
Ab | +0.003 |
thirteen | +0.003 |
Neg logit contributions | |
ingu | -0.006 |
tto | -0.005 |
ascal | -0.005 |
ravings | -0.005 |
pistol | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
ingu | +0.125 |
tto | +0.121 |
pistol | +0.118 |
brand | +0.116 |
ascal | +0.116 |
Neg logit contributions | |
Danger | -0.076 |
nine | -0.075 |
� | -0.072 |
thirteen | -0.068 |
Ab | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
ingu | +0.002 |
pistol | +0.002 |
tto | +0.002 |
brand | +0.002 |
ravings | +0.002 |
Neg logit contributions | |
Danger | -0.002 |
nine | -0.002 |
thirteen | -0.002 |
Ab | -0.002 |
� | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
Danger | +0.002 |
nine | +0.002 |
� | +0.002 |
thirteen | +0.002 |
Ab | +0.002 |
Neg logit contributions | |
ingu | -0.004 |
pistol | -0.003 |
tto | -0.003 |
ascal | -0.003 |
ravings | -0.003 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ingu | +0.024 |
tto | +0.023 |
pistol | +0.022 |
ascal | +0.022 |
ravings | +0.022 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.021 |
� | -0.020 |
Ab | -0.019 |
thirteen | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -8.15e-04 |
Pos logit contributions | |
tto | +0.091 |
ingu | +0.090 |
ascal | +0.086 |
affle | +0.084 |
scar | +0.084 |
Neg logit contributions | |
nine | -0.044 |
Danger | -0.043 |
� | -0.041 |
Jen | -0.040 |
Ab | -0.039 |
Token | told |
Token ID | 1297 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
� | +0.029 |
nine | +0.026 |
Danger | +0.024 |
Ab | +0.023 |
paint | +0.021 |
Neg logit contributions | |
ravings | -0.053 |
ingu | -0.053 |
ascal | -0.052 |
affle | -0.051 |
tto | -0.050 |
Token | him |
Token ID | 683 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
Danger | +0.041 |
nine | +0.040 |
� | +0.039 |
Ab | +0.036 |
thirteen | +0.035 |
Neg logit contributions | |
ingu | -0.082 |
tto | -0.081 |
ascal | -0.078 |
ravings | -0.077 |
pistol | -0.077 |
Token | about |
Token ID | 546 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ingu | +0.118 |
tto | +0.111 |
pistol | +0.107 |
ascal | +0.104 |
ravings | +0.104 |
Neg logit contributions | |
Danger | -0.130 |
nine | -0.128 |
� | -0.122 |
arc | -0.120 |
thirteen | -0.119 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
ingu | +0.133 |
tto | +0.129 |
ascal | +0.124 |
ravings | +0.123 |
affle | +0.122 |
Neg logit contributions | |
Danger | -0.067 |
nine | -0.066 |
� | -0.064 |
Ab | -0.060 |
thirteen | -0.057 |
Token | loud |
Token ID | 7812 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ingu | +0.004 |
tto | +0.004 |
ascal | +0.004 |
pistol | +0.004 |
ravings | +0.004 |
Neg logit contributions | |
Danger | -0.004 |
nine | -0.004 |
� | -0.004 |
Ab | -0.004 |
thirteen | -0.004 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Danger | +0.064 |
nine | +0.063 |
� | +0.062 |
Ab | +0.058 |
thirteen | +0.058 |
Neg logit contributions | |
ingu | -0.070 |
tto | -0.067 |
ascal | -0.064 |
pistol | -0.064 |
ravings | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
pistol | +0.043 |
ingu | +0.043 |
brand | +0.042 |
tto | +0.041 |
ravings | +0.041 |
Neg logit contributions | |
Danger | -0.036 |
nine | -0.035 |
Ab | -0.033 |
thirteen | -0.032 |
arc | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
ingu | +0.019 |
tto | +0.018 |
ascal | +0.018 |
ravings | +0.018 |
affle | +0.017 |
Neg logit contributions | |
nine | -0.015 |
Danger | -0.015 |
� | -0.014 |
Ab | -0.013 |
thirteen | -0.013 |
Token | barking |
Token ID | 48961 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
ingu | +0.004 |
tto | +0.004 |
ascal | +0.004 |
ravings | +0.004 |
affle | +0.004 |
Neg logit contributions | |
Danger | -0.003 |
nine | -0.003 |
� | -0.003 |
paint | -0.003 |
thirteen | -0.003 |
Token | dog |
Token ID | 3290 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
ingu | +0.095 |
tto | +0.091 |
ascal | +0.086 |
ravings | +0.085 |
brand | +0.085 |
Neg logit contributions | |
Danger | -0.078 |
nine | -0.076 |
� | -0.076 |
Ab | -0.070 |
thirteen | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
ingu | +0.093 |
tto | +0.090 |
ascal | +0.087 |
ravings | +0.086 |
pistol | +0.085 |
Neg logit contributions | |
Danger | -0.058 |
nine | -0.057 |
� | -0.056 |
Ab | -0.051 |
thirteen | -0.051 |
Token | Do |
Token ID | 2141 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
ingu | +0.068 |
pistol | +0.067 |
tto | +0.066 |
brand | +0.063 |
hockey | +0.063 |
Neg logit contributions | |
nine | -0.039 |
thirteen | -0.034 |
Danger | -0.032 |
arc | -0.032 |
paint | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
Danger | +0.050 |
� | +0.049 |
nine | +0.047 |
thirteen | +0.038 |
Ab | +0.038 |
Neg logit contributions | |
ingu | -0.166 |
tto | -0.163 |
ravings | -0.159 |
ascal | -0.159 |
pistol | -0.157 |
Token | want |
Token ID | 765 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
Danger | +0.068 |
nine | +0.067 |
thirteen | +0.064 |
Ab | +0.061 |
arc | +0.060 |
Neg logit contributions | |
ingu | -0.129 |
affle | -0.124 |
tto | -0.121 |
ascal | -0.118 |
pistol | -0.115 |
Token | to |
Token ID | 284 |
Feature activation | +6.60e-04 |
Pos logit contributions | |
Danger | +0.105 |
nine | +0.103 |
� | +0.100 |
thirteen | +0.095 |
Ab | +0.095 |
Neg logit contributions | |
ingu | -0.133 |
tto | -0.127 |
pistol | -0.123 |
ascal | -0.121 |
ravings | -0.121 |
Token | play |
Token ID | 711 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
Danger | +0.001 |
nine | +0.001 |
thirteen | +0.001 |
� | +0.001 |
Ab | +0.001 |
Neg logit contributions | |
ingu | -0.001 |
pistol | -0.001 |
tto | -0.001 |
brand | -0.001 |
affle | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ingu | +0.129 |
tto | +0.126 |
ascal | +0.123 |
ravings | +0.122 |
scar | +0.119 |
Neg logit contributions | |
Danger | -0.059 |
nine | -0.059 |
� | -0.058 |
arc | -0.051 |
paint | -0.050 |
Token | me |
Token ID | 502 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
ingu | +0.040 |
tto | +0.039 |
ascal | +0.038 |
ravings | +0.037 |
pron | +0.037 |
Neg logit contributions | |
Danger | -0.031 |
nine | -0.031 |
� | -0.030 |
Ab | -0.028 |
thirteen | -0.027 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ingu | +0.011 |
tto | +0.011 |
ascal | +0.010 |
ravings | +0.010 |
brand | +0.010 |
Neg logit contributions | |
nine | -0.005 |
Danger | -0.005 |
� | -0.005 |
Ab | -0.004 |
thirteen | -0.004 |
Token | Carl |
Token ID | 8124 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
� | +0.017 |
Danger | +0.017 |
nine | +0.017 |
Ab | +0.016 |
Jen | +0.016 |
Neg logit contributions | |
ingu | -0.027 |
tto | -0.026 |
ravings | -0.025 |
ascal | -0.025 |
brand | -0.024 |
Token | looked |
Token ID | 3114 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
ingu | +0.134 |
tto | +0.129 |
ravings | +0.125 |
ascal | +0.125 |
pistol | +0.123 |
Neg logit contributions | |
Danger | -0.100 |
� | -0.099 |
nine | -0.099 |
Ab | -0.092 |
thirteen | -0.090 |
Token | at |
Token ID | 379 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
ingu | +0.115 |
tto | +0.112 |
ascal | +0.109 |
ravings | +0.108 |
affle | +0.105 |
Neg logit contributions | |
nine | -0.070 |
� | -0.069 |
Danger | -0.068 |
Ab | -0.063 |
thirteen | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e-04 |
Pos logit contributions | |
Danger | +0.070 |
nine | +0.069 |
thirteen | +0.067 |
arc | +0.064 |
� | +0.062 |
Neg logit contributions | |
ingu | -0.074 |
pistol | -0.074 |
ascal | -0.068 |
tto | -0.068 |
brand | -0.067 |
Token | " |
Token ID | 366 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Danger | +0.001 |
nine | +0.001 |
� | +0.001 |
thirteen | +0.001 |
Ab | +0.001 |
Neg logit contributions | |
ingu | -0.001 |
tto | -0.001 |
ascal | -0.001 |
pistol | -0.001 |
ravings | -0.001 |
Token | There |
Token ID | 1858 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
ingu | +0.048 |
tto | +0.047 |
ascal | +0.046 |
pistol | +0.045 |
scar | +0.043 |
Neg logit contributions | |
nine | -0.042 |
Danger | -0.041 |
Ab | -0.040 |
thirteen | -0.038 |
� | -0.038 |
Token | 's |
Token ID | 338 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Danger | +0.053 |
nine | +0.052 |
� | +0.046 |
thirteen | +0.046 |
Ab | +0.045 |
Neg logit contributions | |
ingu | -0.101 |
tto | -0.098 |
pistol | -0.094 |
ravings | -0.093 |
brand | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
Danger | +0.015 |
arc | +0.014 |
nine | +0.014 |
thirteen | +0.013 |
Ab | +0.013 |
Neg logit contributions | |
pistol | -0.017 |
brand | -0.017 |
ingu | -0.017 |
tto | -0.016 |
hockey | -0.015 |
Token | dog |
Token ID | 3290 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
ingu | +0.005 |
tto | +0.005 |
ascal | +0.005 |
ravings | +0.005 |
affle | +0.005 |
Neg logit contributions | |
nine | -0.005 |
Danger | -0.005 |
� | -0.005 |
Ab | -0.004 |
thirteen | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ingu | +0.084 |
tto | +0.083 |
pistol | +0.083 |
ravings | +0.079 |
affle | +0.078 |
Neg logit contributions | |
Danger | -0.068 |
nine | -0.067 |
thirteen | -0.067 |
Ab | -0.066 |
arc | -0.062 |
Token | It |
Token ID | 632 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
pistol | +0.052 |
ingu | +0.051 |
tto | +0.049 |
ascal | +0.048 |
hockey | +0.047 |
Neg logit contributions | |
nine | -0.045 |
thirteen | -0.042 |
arc | -0.042 |
paint | -0.039 |
ind | -0.037 |
Token | might |
Token ID | 1244 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
nine | +0.014 |
Danger | +0.013 |
Ab | +0.012 |
arc | +0.012 |
thirteen | +0.012 |
Neg logit contributions | |
tto | -0.019 |
ingu | -0.019 |
pistol | -0.019 |
affle | -0.018 |
ascal | -0.018 |
Token | bite |
Token ID | 13197 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
pistol | +0.050 |
tto | +0.050 |
ingu | +0.048 |
brand | +0.047 |
affle | +0.046 |
Neg logit contributions | |
nine | -0.040 |
Danger | -0.038 |
thirteen | -0.037 |
Ab | -0.037 |
arc | -0.036 |
Token | us |
Token ID | 514 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Danger | +0.012 |
nine | +0.011 |
� | +0.011 |
Ab | +0.010 |
thirteen | +0.010 |
Neg logit contributions | |
ingu | -0.015 |
tto | -0.015 |
pistol | -0.014 |
ravings | -0.014 |
ascal | -0.014 |
Token | But |
Token ID | 1537 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
tto | +0.038 |
Years | +0.036 |
ingu | +0.035 |
Days | +0.034 |
scar | +0.034 |
Neg logit contributions | |
nine | -0.047 |
Danger | -0.046 |
thirteen | -0.046 |
arc | -0.045 |
Ab | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Danger | +0.130 |
thirteen | +0.122 |
� | +0.112 |
arc | +0.112 |
nine | +0.103 |
Neg logit contributions | |
zed | -0.094 |
brand | -0.092 |
ingu | -0.088 |
pistol | -0.086 |
Years | -0.086 |
Token | didn |
Token ID | 1422 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
� | +0.028 |
nine | +0.026 |
Danger | +0.026 |
Ab | +0.025 |
Jen | +0.023 |
Neg logit contributions | |
ingu | -0.037 |
brand | -0.035 |
pistol | -0.035 |
ascal | -0.034 |
ravings | -0.034 |
Token | 't |
Token ID | 470 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
tto | +0.069 |
ingu | +0.066 |
zed | +0.063 |
pistol | +0.063 |
brand | +0.063 |
Neg logit contributions | |
nine | -0.045 |
arc | -0.042 |
thirteen | -0.042 |
Ab | -0.042 |
Danger | -0.039 |
Token | know |
Token ID | 760 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
Danger | +0.086 |
nine | +0.085 |
thirteen | +0.081 |
� | +0.078 |
arc | +0.074 |
Neg logit contributions | |
ingu | -0.171 |
tto | -0.165 |
ascal | -0.162 |
ravings | -0.161 |
pistol | -0.159 |
Token | how |
Token ID | 703 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Danger | +0.076 |
nine | +0.072 |
� | +0.072 |
thirteen | +0.070 |
arc | +0.068 |
Neg logit contributions | |
ingu | -0.054 |
brand | -0.052 |
pistol | -0.049 |
tto | -0.049 |
ascal | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +2.54e-04 |
Pos logit contributions | |
ingu | +0.239 |
brand | +0.238 |
tto | +0.233 |
pistol | +0.232 |
ravings | +0.227 |
Neg logit contributions | |
nine | -0.277 |
Danger | -0.273 |
thirteen | -0.267 |
arc | -0.256 |
� | -0.246 |
Token | mind |
Token ID | 2000 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
thirteen | +0.000 |
nine | +0.000 |
Danger | +0.000 |
ago | +0.000 |
Ab | +0.000 |
Neg logit contributions | |
ingu | -0.000 |
tto | -0.000 |
pistol | -0.000 |
ascal | -0.000 |
ravings | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ingu | +0.045 |
pistol | +0.043 |
ravings | +0.042 |
ascal | +0.042 |
brand | +0.042 |
Neg logit contributions | |
Danger | -0.038 |
nine | -0.037 |
thirteen | -0.035 |
� | -0.034 |
arc | -0.033 |
Token | own |
Token ID | 898 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ingu | +0.018 |
tto | +0.017 |
ascal | +0.016 |
pistol | +0.016 |
ravings | +0.016 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.020 |
� | -0.020 |
Ab | -0.019 |
thirteen | -0.019 |
Token | business |
Token ID | 1597 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
nine | +0.031 |
Danger | +0.031 |
� | +0.030 |
thirteen | +0.030 |
Ab | +0.028 |
Neg logit contributions | |
ingu | -0.026 |
pistol | -0.026 |
ravings | -0.025 |
brand | -0.025 |
tto | -0.025 |
Token | did |
Token ID | 750 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ingu | +0.165 |
tto | +0.157 |
ascal | +0.154 |
ravings | +0.152 |
pistol | +0.149 |
Neg logit contributions | |
Danger | -0.127 |
nine | -0.125 |
� | -0.125 |
Ab | -0.114 |
thirteen | -0.112 |
Token | not |
Token ID | 407 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ingu | +0.040 |
tto | +0.039 |
pistol | +0.037 |
ravings | +0.037 |
ascal | +0.037 |
Neg logit contributions | |
Danger | -0.040 |
nine | -0.039 |
� | -0.038 |
Ab | -0.037 |
thirteen | -0.036 |
Token | like |
Token ID | 588 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
ingu | +0.061 |
tto | +0.058 |
pistol | +0.058 |
ravings | +0.057 |
affle | +0.057 |
Neg logit contributions | |
Danger | -0.029 |
nine | -0.028 |
thirteen | -0.027 |
Ab | -0.026 |
� | -0.026 |
Token | math |
Token ID | 10688 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
nine | +0.034 |
Danger | +0.033 |
� | +0.033 |
paint | +0.029 |
Jen | +0.029 |
Neg logit contributions | |
tto | -0.055 |
ingu | -0.054 |
ascal | -0.052 |
affle | -0.051 |
scar | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-05 |
Pos logit contributions | |
ingu | +0.034 |
tto | +0.034 |
ascal | +0.033 |
affle | +0.031 |
ravings | +0.031 |
Neg logit contributions | |
� | -0.015 |
nine | -0.014 |
Danger | -0.013 |
thirteen | -0.011 |
are | -0.011 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ingu | +0.000 |
tto | +0.000 |
ascal | +0.000 |
ravings | +0.000 |
pistol | +0.000 |
Neg logit contributions | |
Danger | -0.000 |
nine | -0.000 |
� | -0.000 |
Ab | -0.000 |
thirteen | -0.000 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ingu | +0.283 |
tto | +0.270 |
ascal | +0.265 |
brand | +0.261 |
ravings | +0.260 |
Neg logit contributions | |
� | -0.208 |
nine | -0.201 |
Danger | -0.201 |
thirteen | -0.180 |
Ab | -0.180 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-04 |
Pos logit contributions | |
nine | +0.020 |
Danger | +0.019 |
� | +0.019 |
thirteen | +0.017 |
Ab | +0.017 |
Neg logit contributions | |
ingu | -0.033 |
tto | -0.033 |
ascal | -0.032 |
affle | -0.031 |
ravings | -0.031 |
Token | play |
Token ID | 711 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
Danger | +0.000 |
nine | +0.000 |
thirteen | +0.000 |
Ab | +0.000 |
arc | +0.000 |
Neg logit contributions | |
ingu | -0.000 |
ravings | -0.000 |
tto | -0.000 |
pistol | -0.000 |
affle | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
tto | +0.128 |
ingu | +0.127 |
ascal | +0.124 |
scar | +0.119 |
ravings | +0.116 |
Neg logit contributions | |
nine | -0.066 |
� | -0.064 |
Danger | -0.063 |
paint | -0.057 |
are | -0.053 |
Token | not |
Token ID | 407 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ingu | +0.030 |
brand | +0.029 |
pistol | +0.029 |
ravings | +0.028 |
zed | +0.028 |
Neg logit contributions | |
Danger | -0.021 |
nine | -0.020 |
thirteen | -0.019 |
Ab | -0.019 |
arc | -0.019 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ingu | +0.088 |
tto | +0.085 |
pistol | +0.081 |
ascal | +0.081 |
ravings | +0.080 |
Neg logit contributions | |
Danger | -0.070 |
nine | -0.068 |
� | -0.065 |
thirteen | -0.062 |
Ab | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
Danger | +0.018 |
nine | +0.017 |
� | +0.017 |
arc | +0.017 |
thirteen | +0.016 |
Neg logit contributions | |
ingu | -0.020 |
tto | -0.019 |
pistol | -0.019 |
brand | -0.018 |
ravings | -0.018 |
Token | go |
Token ID | 467 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
ingu | +0.003 |
tto | +0.003 |
pistol | +0.003 |
ravings | +0.003 |
brand | +0.003 |
Neg logit contributions | |
nine | -0.002 |
Danger | -0.002 |
thirteen | -0.002 |
ago | -0.002 |
arc | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
Danger | +0.012 |
thirteen | +0.011 |
nine | +0.011 |
arc | +0.010 |
� | +0.010 |
Neg logit contributions | |
pistol | -0.012 |
ingu | -0.012 |
brand | -0.011 |
tto | -0.011 |
affle | -0.011 |
Token | an |
Token ID | 281 |
Feature activation | -4.65e-04 |
Pos logit contributions | |
Danger | +0.006 |
nine | +0.006 |
� | +0.005 |
Ab | +0.005 |
thirteen | +0.005 |
Neg logit contributions | |
ingu | -0.011 |
tto | -0.010 |
ascal | -0.010 |
ravings | -0.010 |
pistol | -0.010 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ingu | +0.001 |
tto | +0.001 |
ascal | +0.001 |
pistol | +0.001 |
ravings | +0.001 |
Neg logit contributions | |
nine | -0.001 |
� | -0.001 |
Danger | -0.001 |
Ab | -0.001 |
thirteen | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ingu | +0.245 |
tto | +0.237 |
pistol | +0.232 |
brand | +0.228 |
ravings | +0.226 |
Neg logit contributions | |
Danger | -0.183 |
nine | -0.176 |
� | -0.166 |
thirteen | -0.162 |
Ab | -0.156 |
Token | he |
Token ID | 339 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ingu | +0.104 |
tto | +0.099 |
pistol | +0.094 |
ascal | +0.094 |
ravings | +0.093 |
Neg logit contributions | |
Danger | -0.122 |
nine | -0.120 |
� | -0.117 |
thirteen | -0.112 |
Ab | -0.110 |
Token | decided |
Token ID | 3066 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
ingu | +0.064 |
tto | +0.061 |
ascal | +0.060 |
ravings | +0.059 |
pistol | +0.059 |
Neg logit contributions | |
Danger | -0.042 |
� | -0.041 |
nine | -0.041 |
Ab | -0.038 |
thirteen | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
Danger | +0.117 |
nine | +0.114 |
� | +0.109 |
thirteen | +0.106 |
arc | +0.104 |
Neg logit contributions | |
ingu | -0.135 |
tto | -0.131 |
pistol | -0.126 |
brand | -0.125 |
ravings | -0.123 |
Token | climb |
Token ID | 12080 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
ingu | +0.002 |
tto | +0.002 |
pistol | +0.002 |
zed | +0.002 |
ravings | +0.002 |
Neg logit contributions | |
nine | -0.001 |
thirteen | -0.001 |
Danger | -0.001 |
arc | -0.001 |
ago | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-03 |
Pos logit contributions | |
Danger | +0.073 |
nine | +0.070 |
� | +0.069 |
thirteen | +0.064 |
Ab | +0.062 |
Neg logit contributions | |
ingu | -0.131 |
tto | -0.126 |
pistol | -0.122 |
ascal | -0.122 |
ravings | -0.121 |
Token | book |
Token ID | 1492 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ingu | +0.008 |
pistol | +0.007 |
brand | +0.007 |
ravings | +0.007 |
affle | +0.007 |
Neg logit contributions | |
Danger | -0.007 |
� | -0.007 |
Ab | -0.007 |
nine | -0.007 |
Jen | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
ingu | +0.019 |
tto | +0.018 |
pistol | +0.018 |
brand | +0.018 |
ravings | +0.018 |
Neg logit contributions | |
Danger | -0.013 |
nine | -0.012 |
� | -0.012 |
thirteen | -0.012 |
Ab | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
nine | +0.011 |
Danger | +0.011 |
� | +0.010 |
thirteen | +0.010 |
Ab | +0.009 |
Neg logit contributions | |
ingu | -0.018 |
ravings | -0.017 |
tto | -0.017 |
brand | -0.017 |
ascal | -0.016 |
Token | hugged |
Token ID | 41130 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
ingu | +0.013 |
tto | +0.012 |
pistol | +0.011 |
ascal | +0.011 |
brand | +0.011 |
Neg logit contributions | |
Danger | -0.012 |
nine | -0.012 |
thirteen | -0.011 |
� | -0.011 |
Ab | -0.011 |
Token | each |
Token ID | 1123 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ingu | +0.046 |
pistol | +0.042 |
ascal | +0.042 |
tto | +0.042 |
ravings | +0.041 |
Neg logit contributions | |
Danger | -0.040 |
� | -0.038 |
nine | -0.038 |
thirteen | -0.036 |
Ab | -0.034 |
Token | other |
Token ID | 584 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ingu | +0.320 |
pistol | +0.291 |
tto | +0.279 |
affle | +0.276 |
ascal | +0.273 |
Neg logit contributions | |
Danger | -0.258 |
thirteen | -0.247 |
Ab | -0.245 |
arc | -0.242 |
� | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
Danger | +0.152 |
nine | +0.144 |
� | +0.134 |
Ab | +0.132 |
thirteen | +0.131 |
Neg logit contributions | |
ingu | -0.222 |
tto | -0.208 |
pistol | -0.205 |
brand | -0.202 |
ascal | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Danger | +0.011 |
nine | +0.011 |
thirteen | +0.011 |
� | +0.011 |
Ab | +0.010 |
Neg logit contributions | |
ingu | -0.018 |
ravings | -0.017 |
tto | -0.017 |
brand | -0.017 |
ascal | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ingu | +0.028 |
ravings | +0.027 |
pistol | +0.027 |
ascal | +0.027 |
tto | +0.027 |
Neg logit contributions | |
� | -0.016 |
Danger | -0.016 |
nine | -0.015 |
Jen | -0.014 |
Ab | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
tto | +0.020 |
ingu | +0.020 |
Years | +0.019 |
pron | +0.018 |
ascal | +0.018 |
Neg logit contributions | |
Danger | -0.022 |
Ab | -0.022 |
nine | -0.021 |
thirteen | -0.021 |
Jen | -0.020 |
Token | there |
Token ID | 612 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Danger | +0.011 |
nine | +0.011 |
� | +0.010 |
thirteen | +0.010 |
Ab | +0.010 |
Neg logit contributions | |
ingu | -0.015 |
tto | -0.015 |
pistol | -0.014 |
ascal | -0.014 |
brand | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
� | +0.011 |
Ab | +0.010 |
are | +0.010 |
Danger | +0.009 |
nine | +0.009 |
Neg logit contributions | |
ingu | -0.025 |
ascal | -0.025 |
ravings | -0.025 |
pistol | -0.024 |
pron | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -9.64e-04 |
Pos logit contributions | |
ingu | +0.041 |
tto | +0.040 |
brand | +0.038 |
pistol | +0.038 |
ascal | +0.038 |
Neg logit contributions | |
Danger | -0.025 |
nine | -0.024 |
� | -0.023 |
thirteen | -0.023 |
Ab | -0.022 |
Token | dog |
Token ID | 3290 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
ingu | +0.002 |
tto | +0.002 |
ravings | +0.002 |
zed | +0.002 |
scar | +0.002 |
Neg logit contributions | |
nine | -0.001 |
� | -0.001 |
Danger | -0.001 |
paint | -0.001 |
arc | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
ingu | +0.106 |
tto | +0.102 |
ascal | +0.098 |
ravings | +0.098 |
brand | +0.097 |
Neg logit contributions | |
Danger | -0.057 |
nine | -0.057 |
� | -0.055 |
Ab | -0.050 |
Jen | -0.048 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Danger | +0.044 |
� | +0.043 |
nine | +0.042 |
Jen | +0.040 |
Ab | +0.040 |
Neg logit contributions | |
ingu | -0.046 |
ascal | -0.044 |
tto | -0.043 |
ravings | -0.043 |
affle | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-04 |
Pos logit contributions | |
ingu | +0.370 |
tto | +0.363 |
ravings | +0.359 |
affle | +0.353 |
brand | +0.352 |
Neg logit contributions | |
� | -0.111 |
nine | -0.109 |
Danger | -0.101 |
Jen | -0.086 |
Ab | -0.084 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.000 |
Danger | +0.000 |
nine | +0.000 |
Jen | +0.000 |
are | +0.000 |
Neg logit contributions | |
ingu | -0.000 |
ascal | -0.000 |
tto | -0.000 |
ravings | -0.000 |
affle | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
ingu | +0.314 |
ravings | +0.311 |
ascal | +0.304 |
brand | +0.294 |
ishing | +0.289 |
Neg logit contributions | |
� | -0.204 |
are | -0.166 |
have | -0.164 |
paint | -0.144 |
Jen | -0.140 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
ingu | +0.186 |
tto | +0.182 |
ascal | +0.176 |
ouse | +0.175 |
imm | +0.173 |
Neg logit contributions | |
paint | -0.052 |
Jen | -0.048 |
nine | -0.045 |
Danger | -0.043 |
touch | -0.040 |
Token | chew |
Token ID | 34722 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Danger | +0.002 |
� | +0.002 |
nine | +0.002 |
paint | +0.002 |
Ab | +0.002 |
Neg logit contributions | |
ingu | -0.003 |
tto | -0.003 |
ascal | -0.003 |
ravings | -0.003 |
brand | -0.003 |