Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
� | +0.021 |
ages | +0.018 |
's | +0.018 |
aul | +0.018 |
ience | +0.017 |
Neg logit contributions | |
them | -0.013 |
mate | -0.013 |
polar | -0.011 |
wreck | -0.011 |
tow | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
� | +0.029 |
ages | +0.027 |
decisions | +0.026 |
aul | +0.026 |
adow | +0.025 |
Neg logit contributions | |
them | -0.028 |
mate | -0.024 |
inn | -0.022 |
tow | -0.022 |
ramp | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
� | +0.031 |
's | +0.027 |
ages | +0.025 |
aul | +0.024 |
cious | +0.023 |
Neg logit contributions | |
mate | -0.030 |
them | -0.029 |
wreck | -0.028 |
polar | -0.027 |
tow | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +0.032 |
ages | +0.031 |
aul | +0.030 |
decisions | +0.030 |
's | +0.029 |
Neg logit contributions | |
them | -0.027 |
mate | -0.026 |
inn | -0.022 |
tow | -0.022 |
ramp | -0.021 |
Token | Check |
Token ID | 9787 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
mate | +0.011 |
them | +0.011 |
tow | +0.009 |
polar | +0.009 |
wreck | +0.009 |
Neg logit contributions | |
� | -0.017 |
's | -0.015 |
ages | -0.015 |
aul | -0.015 |
decisions | -0.014 |
Token | mate |
Token ID | 9830 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
them | +0.042 |
tow | +0.041 |
polar | +0.040 |
wreck | +0.040 |
snowball | +0.038 |
Neg logit contributions | |
� | -0.065 |
's | -0.058 |
ages | -0.057 |
decisions | -0.053 |
cious | -0.052 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
mate | +0.548 |
them | +0.536 |
wreck | +0.428 |
polar | +0.411 |
ramp | +0.410 |
Neg logit contributions | |
� | -1.037 |
aul | -0.914 |
ages | -0.912 |
's | -0.905 |
List | -0.903 |
Token | declared |
Token ID | 6875 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
them | +0.244 |
mate | +0.201 |
stuffed | +0.190 |
his | +0.190 |
tant | +0.184 |
Neg logit contributions | |
� | -0.219 |
aul | -0.214 |
decisions | -0.212 |
adow | -0.211 |
ages | -0.210 |
Token | Elsa |
Token ID | 19226 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
them | +0.127 |
mate | +0.115 |
his | +0.100 |
polar | +0.099 |
stuffed | +0.097 |
Neg logit contributions | |
� | -0.163 |
ages | -0.148 |
aul | -0.144 |
bey | -0.141 |
aut | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
� | +0.174 |
aul | +0.167 |
List | +0.163 |
bey | +0.162 |
pays | +0.161 |
Neg logit contributions | |
them | -0.085 |
mate | -0.077 |
captain | -0.067 |
polar | -0.065 |
control | -0.063 |
Token | Her |
Token ID | 2332 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
� | +0.032 |
ages | +0.028 |
decisions | +0.028 |
ience | +0.027 |
aul | +0.027 |
Neg logit contributions | |
them | -0.029 |
mate | -0.027 |
tow | -0.024 |
inn | -0.024 |
polar | -0.022 |
Token | pieces |
Token ID | 5207 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
� | +0.020 |
's | +0.017 |
ages | +0.016 |
aul | +0.015 |
pays | +0.015 |
Neg logit contributions | |
mate | -0.015 |
them | -0.015 |
polar | -0.014 |
tow | -0.014 |
wreck | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
� | +0.014 |
's | +0.012 |
ages | +0.012 |
aul | +0.012 |
cious | +0.012 |
Neg logit contributions | |
them | -0.010 |
mate | -0.010 |
wreck | -0.008 |
tow | -0.008 |
polar | -0.008 |
Token | try |
Token ID | 1949 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
� | +0.021 |
's | +0.018 |
aul | +0.014 |
ages | +0.014 |
pays | +0.014 |
Neg logit contributions | |
mate | -0.018 |
snowball | -0.017 |
polar | -0.017 |
inn | -0.016 |
tant | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
mate | +0.140 |
them | +0.128 |
polar | +0.125 |
tow | +0.122 |
wreck | +0.122 |
Neg logit contributions | |
� | -0.222 |
's | -0.200 |
ages | -0.187 |
aul | -0.181 |
cious | -0.175 |
Token | check |
Token ID | 2198 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
� | +0.046 |
's | +0.041 |
ages | +0.040 |
aul | +0.039 |
cious | +0.038 |
Neg logit contributions | |
mate | -0.026 |
them | -0.026 |
wreck | -0.022 |
polar | -0.022 |
tow | -0.022 |
Token | mate |
Token ID | 9830 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
mate | +0.032 |
them | +0.029 |
polar | +0.029 |
wreck | +0.029 |
tow | +0.028 |
Neg logit contributions | |
� | -0.063 |
's | -0.056 |
ages | -0.054 |
aul | -0.052 |
pays | -0.051 |
Token | your |
Token ID | 534 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
them | +0.648 |
mate | +0.643 |
wreck | +0.549 |
tow | +0.545 |
polar | +0.543 |
Neg logit contributions | |
� | -0.962 |
's | -0.837 |
ages | -0.829 |
aul | -0.794 |
cious | -0.773 |
Token | opponent |
Token ID | 6125 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
mate | +0.056 |
them | +0.055 |
wreck | +0.050 |
polar | +0.049 |
tow | +0.049 |
Neg logit contributions | |
� | -0.064 |
's | -0.055 |
ages | -0.054 |
aul | -0.052 |
cious | -0.050 |
Token | ." |
Token ID | 526 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
� | +0.218 |
ages | +0.189 |
aul | +0.188 |
List | +0.186 |
's | +0.184 |
Neg logit contributions | |
them | -0.152 |
mate | -0.145 |
wreck | -0.125 |
ramp | -0.124 |
captain | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
them | +0.112 |
mate | +0.109 |
tow | +0.098 |
wreck | +0.096 |
ramp | +0.095 |
Neg logit contributions | |
� | -0.149 |
's | -0.130 |
ages | -0.130 |
aul | -0.123 |
cious | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
� | +0.029 |
's | +0.025 |
ages | +0.023 |
aul | +0.022 |
bey | +0.021 |
Neg logit contributions | |
mate | -0.032 |
them | -0.030 |
polar | -0.029 |
wreck | -0.029 |
captain | -0.028 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
� | +0.129 |
aul | +0.121 |
Michelle | +0.110 |
List | +0.109 |
decisions | +0.106 |
Neg logit contributions | |
mate | -0.232 |
them | -0.230 |
ramp | -0.223 |
racer | -0.217 |
puck | -0.217 |
Token | s |
Token ID | 82 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
� | +0.365 |
ages | +0.336 |
aul | +0.330 |
cious | +0.322 |
's | +0.322 |
Neg logit contributions | |
them | -0.294 |
mate | -0.294 |
inn | -0.253 |
tow | -0.249 |
wreck | -0.247 |
Token | King |
Token ID | 2677 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
� | +0.036 |
's | +0.031 |
ages | +0.031 |
aul | +0.030 |
cious | +0.029 |
Neg logit contributions | |
mate | -0.028 |
them | -0.028 |
wreck | -0.025 |
tow | -0.024 |
ramp | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
� | +0.105 |
List | +0.092 |
aul | +0.090 |
ages | +0.087 |
bey | +0.085 |
Neg logit contributions | |
mate | -0.196 |
them | -0.193 |
wreck | -0.176 |
captain | -0.172 |
racer | -0.172 |
Token | check |
Token ID | 2198 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
� | +0.024 |
's | +0.020 |
pays | +0.017 |
decisions | +0.017 |
ages | +0.017 |
Neg logit contributions | |
mate | -0.018 |
polar | -0.018 |
them | -0.018 |
ramp | -0.017 |
inn | -0.017 |
Token | mate |
Token ID | 9830 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
mate | +0.035 |
them | +0.035 |
wreck | +0.031 |
polar | +0.031 |
tow | +0.030 |
Neg logit contributions | |
� | -0.051 |
's | -0.044 |
ages | -0.043 |
aul | -0.041 |
cious | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
mate | +0.687 |
them | +0.680 |
wreck | +0.605 |
polar | +0.604 |
tow | +0.599 |
Neg logit contributions | |
� | -0.917 |
's | -0.800 |
ages | -0.780 |
aul | -0.742 |
cious | -0.722 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
� | +0.016 |
's | +0.014 |
ages | +0.014 |
aul | +0.013 |
cious | +0.013 |
Neg logit contributions | |
mate | -0.010 |
them | -0.010 |
wreck | -0.008 |
polar | -0.008 |
tow | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
� | +0.021 |
's | +0.016 |
ages | +0.013 |
aul | +0.012 |
List | +0.012 |
Neg logit contributions | |
mate | -0.033 |
captain | -0.031 |
polar | -0.031 |
wreck | -0.031 |
spoiler | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
� | +0.033 |
's | +0.026 |
ages | +0.024 |
List | +0.022 |
aut | +0.022 |
Neg logit contributions | |
mate | -0.022 |
them | -0.022 |
polar | -0.021 |
ware | -0.020 |
captain | -0.019 |
Token | little |
Token ID | 1310 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
� | +0.074 |
ages | +0.067 |
's | +0.065 |
aul | +0.065 |
cious | +0.062 |
Neg logit contributions | |
mate | -0.050 |
them | -0.049 |
wreck | -0.045 |
polar | -0.044 |
tow | -0.044 |
Token | enough |
Token ID | 1576 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
� | +0.300 |
ages | +0.279 |
cious | +0.267 |
aul | +0.265 |
's | +0.259 |
Neg logit contributions | |
them | -0.191 |
mate | -0.178 |
wreck | -0.148 |
polar | -0.143 |
tow | -0.143 |
Token | to |
Token ID | 284 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
them | +0.027 |
mate | +0.025 |
wreck | +0.022 |
tow | +0.022 |
polar | +0.021 |
Neg logit contributions | |
� | -0.041 |
ages | -0.037 |
's | -0.036 |
aul | -0.035 |
cious | -0.034 |
Token | find |
Token ID | 1064 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
� | +0.033 |
's | +0.029 |
ages | +0.029 |
aul | +0.027 |
cious | +0.027 |
Neg logit contributions | |
mate | -0.021 |
them | -0.021 |
wreck | -0.018 |
polar | -0.018 |
tow | -0.018 |
Token | your |
Token ID | 534 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
them | +0.041 |
mate | +0.036 |
tow | +0.032 |
wreck | +0.031 |
polar | +0.031 |
Neg logit contributions | |
� | -0.046 |
ages | -0.041 |
aul | -0.039 |
cious | -0.038 |
's | -0.038 |
Token | soul |
Token ID | 5848 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
them | +0.044 |
mate | +0.042 |
wreck | +0.040 |
polar | +0.038 |
tow | +0.038 |
Neg logit contributions | |
� | -0.056 |
ages | -0.048 |
's | -0.047 |
aul | -0.047 |
cious | -0.045 |
Token | mate |
Token ID | 9830 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
� | +0.429 |
ages | +0.386 |
aul | +0.378 |
List | +0.367 |
cious | +0.366 |
Neg logit contributions | |
them | -0.289 |
mate | -0.274 |
wreck | -0.229 |
captain | -0.226 |
polar | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
them | +0.677 |
mate | +0.659 |
tow | +0.518 |
wreck | +0.508 |
control | +0.506 |
Neg logit contributions | |
� | -0.870 |
ages | -0.791 |
aul | -0.788 |
List | -0.759 |
cious | -0.737 |
Token | don |
Token ID | 836 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ages | +0.016 |
� | +0.016 |
cious | +0.015 |
aul | +0.015 |
aut | +0.014 |
Neg logit contributions | |
them | -0.018 |
mate | -0.016 |
captain | -0.014 |
tow | -0.014 |
wreck | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
� | +0.319 |
ages | +0.303 |
's | +0.292 |
cious | +0.291 |
aul | +0.291 |
Neg logit contributions | |
them | -0.148 |
mate | -0.138 |
wreck | -0.113 |
tow | -0.113 |
ramp | -0.106 |
Token | be |
Token ID | 307 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
them | +0.244 |
mate | +0.242 |
wreck | +0.217 |
polar | +0.212 |
tow | +0.209 |
Neg logit contributions | |
� | -0.348 |
ages | -0.306 |
's | -0.305 |
aul | -0.290 |
cious | -0.283 |
Token | afraid |
Token ID | 7787 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
them | +0.123 |
mate | +0.119 |
wreck | +0.110 |
polar | +0.109 |
tow | +0.106 |
Neg logit contributions | |
� | -0.122 |
ages | -0.102 |
's | -0.102 |
aul | -0.097 |
cious | -0.094 |
Token | popular |
Token ID | 2968 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
� | +0.132 |
ages | +0.115 |
's | +0.114 |
aul | +0.109 |
cious | +0.107 |
Neg logit contributions | |
them | -0.071 |
mate | -0.069 |
wreck | -0.063 |
polar | -0.061 |
tow | -0.061 |
Token | that |
Token ID | 326 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
mate | +0.090 |
them | +0.089 |
tow | +0.080 |
inn | +0.079 |
polar | +0.079 |
Neg logit contributions | |
� | -0.129 |
's | -0.115 |
ages | -0.110 |
aul | -0.104 |
decisions | -0.102 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
them | +0.065 |
mate | +0.063 |
wreck | +0.056 |
polar | +0.055 |
tow | +0.055 |
Neg logit contributions | |
� | -0.072 |
ages | -0.065 |
's | -0.062 |
aul | -0.062 |
cious | -0.061 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
� | +0.141 |
ages | +0.127 |
aul | +0.120 |
's | +0.119 |
cious | +0.118 |
Neg logit contributions | |
them | -0.130 |
mate | -0.125 |
wreck | -0.115 |
polar | -0.110 |
tow | -0.108 |
Token | a |
Token ID | 257 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
them | +0.022 |
mate | +0.020 |
wreck | +0.016 |
tow | +0.016 |
polar | +0.016 |
Neg logit contributions | |
� | -0.032 |
ages | -0.029 |
aul | -0.028 |
's | -0.028 |
cious | -0.028 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
� | +0.056 |
's | +0.049 |
ages | +0.045 |
aul | +0.044 |
cious | +0.043 |
Neg logit contributions | |
mate | -0.041 |
them | -0.041 |
polar | -0.036 |
inn | -0.035 |
tow | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ramp | +0.542 |
polar | +0.541 |
snowball | +0.535 |
them | +0.531 |
mate | +0.518 |
Neg logit contributions | |
� | -0.775 |
's | -0.661 |
ages | -0.590 |
aul | -0.539 |
cious | -0.535 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
mate | +0.191 |
them | +0.174 |
ramp | +0.170 |
inn | +0.170 |
wreck | +0.170 |
Neg logit contributions | |
� | -0.221 |
's | -0.190 |
ages | -0.176 |
decisions | -0.167 |
aul | -0.165 |
Token | same |
Token ID | 976 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
� | +0.002 |
ages | +0.001 |
's | +0.001 |
aul | +0.001 |
cious | +0.001 |
Neg logit contributions | |
mate | -0.001 |
them | -0.001 |
wreck | -0.001 |
polar | -0.001 |
tow | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
mate | +0.111 |
them | +0.109 |
polar | +0.100 |
inn | +0.099 |
tow | +0.099 |
Neg logit contributions | |
� | -0.161 |
's | -0.143 |
ages | -0.131 |
decisions | -0.126 |
aul | -0.124 |
Token | |
Token ID | 220 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
� | +0.004 |
ages | +0.004 |
's | +0.004 |
aul | +0.004 |
cious | +0.003 |
Neg logit contributions | |
them | -0.004 |
mate | -0.004 |
tow | -0.004 |
polar | -0.004 |
wreck | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
� | +0.036 |
ages | +0.032 |
's | +0.032 |
aul | +0.030 |
cious | +0.030 |
Neg logit contributions | |
them | -0.032 |
mate | -0.032 |
tow | -0.028 |
polar | -0.028 |
wreck | -0.028 |
Token | could |
Token ID | 714 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
� | +0.198 |
's | +0.166 |
ages | +0.149 |
aul | +0.141 |
bey | +0.139 |
Neg logit contributions | |
mate | -0.183 |
them | -0.176 |
ramp | -0.164 |
polar | -0.162 |
tow | -0.161 |
Token | use |
Token ID | 779 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
mate | +0.064 |
them | +0.059 |
inn | +0.055 |
polar | +0.055 |
tow | +0.053 |
Neg logit contributions | |
� | -0.093 |
's | -0.080 |
ages | -0.073 |
aul | -0.068 |
cious | -0.066 |
Token | an |
Token ID | 281 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
mate | +0.159 |
polar | +0.143 |
them | +0.142 |
wreck | +0.138 |
tow | +0.137 |
Neg logit contributions | |
� | -0.197 |
's | -0.170 |
ages | -0.155 |
aul | -0.148 |
pays | -0.147 |
Token | extra |
Token ID | 3131 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
� | +0.159 |
's | +0.135 |
ages | +0.125 |
aul | +0.121 |
decisions | +0.120 |
Neg logit contributions | |
mate | -0.136 |
them | -0.134 |
polar | -0.121 |
tow | -0.117 |
wreck | -0.117 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
mate | +0.152 |
them | +0.150 |
wreck | +0.133 |
polar | +0.132 |
tow | +0.131 |
Neg logit contributions | |
� | -0.217 |
's | -0.190 |
ages | -0.186 |
aul | -0.177 |
cious | -0.172 |
Token | of |
Token ID | 286 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
polar | +0.496 |
mate | +0.488 |
them | +0.487 |
snowball | +0.475 |
ramp | +0.469 |
Neg logit contributions | |
� | -0.799 |
's | -0.688 |
ages | -0.629 |
aul | -0.578 |
cious | -0.569 |
Token | hands |
Token ID | 2832 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
mate | +0.168 |
wreck | +0.151 |
ramp | +0.146 |
inn | +0.144 |
them | +0.143 |
Neg logit contributions | |
� | -0.218 |
's | -0.189 |
ages | -0.172 |
cious | -0.160 |
aul | -0.160 |
Token | ." |
Token ID | 526 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
� | +0.228 |
's | +0.199 |
ages | +0.197 |
aul | +0.189 |
cious | +0.185 |
Neg logit contributions | |
them | -0.163 |
mate | -0.161 |
wreck | -0.140 |
polar | -0.139 |
tow | -0.137 |
Token | The |
Token ID | 383 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
them | +0.099 |
mate | +0.093 |
tow | +0.083 |
polar | +0.082 |
inn | +0.080 |
Neg logit contributions | |
� | -0.126 |
ages | -0.118 |
's | -0.112 |
cious | -0.111 |
decisions | -0.110 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
� | +0.120 |
's | +0.105 |
ages | +0.102 |
aul | +0.098 |
cious | +0.095 |
Neg logit contributions | |
mate | -0.085 |
them | -0.084 |
wreck | -0.074 |
polar | -0.074 |
tow | -0.074 |
Token | naughty |
Token ID | 45128 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
them | +0.180 |
his | +0.167 |
polar | +0.161 |
wreck | +0.155 |
mate | +0.154 |
Neg logit contributions | |
� | -0.223 |
ages | -0.197 |
grand | -0.194 |
ama | -0.193 |
aul | -0.192 |
Token | so |
Token ID | 523 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
� | +0.066 |
ages | +0.059 |
's | +0.057 |
aul | +0.057 |
cious | +0.055 |
Neg logit contributions | |
them | -0.043 |
mate | -0.042 |
polar | -0.038 |
wreck | -0.037 |
ramp | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
them | +0.171 |
mate | +0.161 |
wreck | +0.146 |
polar | +0.145 |
tow | +0.142 |
Neg logit contributions | |
� | -0.308 |
's | -0.279 |
ages | -0.277 |
aul | -0.269 |
cious | -0.264 |
Token | took |
Token ID | 1718 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
� | +0.027 |
ages | +0.023 |
's | +0.023 |
aul | +0.022 |
decisions | +0.022 |
Neg logit contributions | |
them | -0.027 |
mate | -0.026 |
polar | -0.024 |
wreck | -0.024 |
tow | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
� | +0.180 |
's | +0.159 |
ages | +0.156 |
aul | +0.152 |
cious | +0.147 |
Neg logit contributions | |
them | -0.127 |
mate | -0.125 |
polar | -0.108 |
wreck | -0.108 |
tow | -0.107 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.52e+00 |
Pos logit contributions | |
� | +0.100 |
's | +0.088 |
ages | +0.078 |
aul | +0.075 |
cious | +0.074 |
Neg logit contributions | |
mate | -0.066 |
them | -0.064 |
captain | -0.055 |
polar | -0.055 |
tow | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
mate | +0.479 |
them | +0.476 |
ramp | +0.476 |
polar | +0.467 |
snowball | +0.461 |
Neg logit contributions | |
� | -0.812 |
's | -0.695 |
ages | -0.630 |
aul | -0.570 |
cious | -0.569 |
Token | his |
Token ID | 465 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
mate | +0.178 |
ramp | +0.156 |
wreck | +0.156 |
tow | +0.150 |
inn | +0.149 |
Neg logit contributions | |
� | -0.212 |
's | -0.183 |
ages | -0.171 |
decisions | -0.156 |
ience | -0.154 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
mate | +0.253 |
them | +0.251 |
wreck | +0.224 |
polar | +0.223 |
tow | +0.222 |
Neg logit contributions | |
� | -0.313 |
's | -0.272 |
ages | -0.265 |
aul | -0.252 |
cious | -0.245 |
Token | 's |
Token ID | 338 |
Feature activation | -9.14e+00 |
Pos logit contributions | |
List | +0.104 |
� | +0.102 |
decisions | +0.096 |
aul | +0.095 |
ages | +0.094 |
Neg logit contributions | |
them | -0.229 |
mate | -0.210 |
polar | -0.207 |
tow | -0.200 |
load | -0.196 |
Token | clothes |
Token ID | 8242 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
� | +0.692 |
's | +0.608 |
ages | +0.586 |
aul | +0.551 |
cious | +0.538 |
Neg logit contributions | |
mate | -0.525 |
them | -0.514 |
wreck | -0.460 |
polar | -0.457 |
tow | -0.454 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
� | +0.009 |
ages | +0.008 |
cious | +0.008 |
aul | +0.007 |
's | +0.007 |
Neg logit contributions | |
them | -0.010 |
mate | -0.010 |
tow | -0.009 |
wreck | -0.009 |
polar | -0.009 |
Token | v |
Token ID | 410 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
� | +0.187 |
ages | +0.164 |
's | +0.163 |
aul | +0.159 |
cious | +0.156 |
Neg logit contributions | |
them | -0.124 |
mate | -0.117 |
wreck | -0.103 |
polar | -0.101 |
tow | -0.098 |
Token | room |
Token ID | 3823 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
mate | +0.227 |
them | +0.226 |
polar | +0.209 |
tow | +0.201 |
wreck | +0.194 |
Neg logit contributions | |
� | -0.479 |
ages | -0.444 |
's | -0.440 |
aul | -0.407 |
ups | -0.393 |
Token | - |
Token ID | 12 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
mate | +0.518 |
them | +0.505 |
polar | +0.449 |
tow | +0.447 |
wreck | +0.447 |
Neg logit contributions | |
� | -0.804 |
's | -0.714 |
ages | -0.694 |
aul | -0.653 |
cious | -0.639 |
Token | v |
Token ID | 85 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
mate | +0.019 |
them | +0.018 |
polar | +0.017 |
tow | +0.017 |
wreck | +0.016 |
Neg logit contributions | |
� | -0.024 |
's | -0.021 |
ages | -0.021 |
aul | -0.019 |
cious | -0.018 |
Token | room |
Token ID | 3823 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
polar | +0.157 |
mate | +0.155 |
tow | +0.149 |
them | +0.145 |
firefighter | +0.144 |
Neg logit contributions | |
's | -0.410 |
� | -0.408 |
ages | -0.397 |
ups | -0.360 |
decisions | -0.351 |
Token | sounds |
Token ID | 5238 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
mate | +0.491 |
them | +0.473 |
tow | +0.425 |
polar | +0.425 |
wreck | +0.420 |
Neg logit contributions | |
� | -0.778 |
's | -0.696 |
ages | -0.675 |
aul | -0.625 |
cious | -0.617 |
Token | . |
Token ID | 13 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
� | +0.338 |
's | +0.296 |
ages | +0.279 |
aul | +0.253 |
cious | +0.252 |
Neg logit contributions | |
mate | -0.278 |
them | -0.260 |
tow | -0.248 |
polar | -0.248 |
wreck | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
mate | +0.031 |
them | +0.031 |
wreck | +0.028 |
polar | +0.028 |
tow | +0.027 |
Neg logit contributions | |
� | -0.036 |
's | -0.031 |
ages | -0.030 |
aul | -0.029 |
cious | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
mate | +0.032 |
wreck | +0.030 |
captain | +0.029 |
polar | +0.029 |
them | +0.029 |
Neg logit contributions | |
� | -0.024 |
's | -0.019 |
List | -0.017 |
ages | -0.016 |
aul | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
mate | +0.020 |
them | +0.020 |
wreck | +0.018 |
polar | +0.018 |
tow | +0.018 |
Neg logit contributions | |
� | -0.029 |
's | -0.025 |
ages | -0.024 |
aul | -0.023 |
cious | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
� | +0.262 |
's | +0.229 |
ages | +0.226 |
aul | +0.216 |
cious | +0.211 |
Neg logit contributions | |
mate | -0.174 |
them | -0.173 |
wreck | -0.153 |
polar | -0.152 |
tow | -0.150 |
Token | He |
Token ID | 679 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
� | +0.016 |
's | +0.014 |
ages | +0.013 |
aul | +0.013 |
List | +0.013 |
Neg logit contributions | |
mate | -0.008 |
them | -0.008 |
wreck | -0.006 |
polar | -0.006 |
tow | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
them | +0.128 |
mate | +0.125 |
wreck | +0.116 |
polar | +0.116 |
tow | +0.112 |
Neg logit contributions | |
� | -0.141 |
ages | -0.125 |
's | -0.120 |
decisions | -0.119 |
aul | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +0.086 |
's | +0.074 |
ages | +0.074 |
aul | +0.071 |
ience | +0.068 |
Neg logit contributions | |
them | -0.072 |
mate | -0.069 |
polar | -0.063 |
wreck | -0.063 |
tow | -0.063 |
Token | big |
Token ID | 1263 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
� | +0.082 |
's | +0.073 |
ages | +0.064 |
aul | +0.063 |
cious | +0.062 |
Neg logit contributions | |
them | -0.065 |
mate | -0.063 |
inn | -0.056 |
room | -0.051 |
tow | -0.050 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.43e+00 |
Pos logit contributions | |
mate | +0.076 |
them | +0.075 |
inn | +0.065 |
tow | +0.063 |
polar | +0.062 |
Neg logit contributions | |
� | -0.097 |
's | -0.088 |
ages | -0.079 |
aul | -0.078 |
decisions | -0.075 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
them | +0.591 |
mate | +0.566 |
ramp | +0.563 |
snowball | +0.561 |
polar | +0.556 |
Neg logit contributions | |
� | -0.723 |
's | -0.629 |
ages | -0.555 |
adow | -0.499 |
grand | -0.497 |
Token | scissors |
Token ID | 41786 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
mate | +0.194 |
ramp | +0.173 |
wreck | +0.170 |
inn | +0.168 |
tow | +0.166 |
Neg logit contributions | |
� | -0.191 |
's | -0.170 |
ages | -0.157 |
aul | -0.148 |
cious | -0.143 |
Token | that |
Token ID | 326 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
mate | +0.176 |
them | +0.166 |
polar | +0.158 |
tow | +0.158 |
snowball | +0.156 |
Neg logit contributions | |
� | -0.180 |
's | -0.161 |
ages | -0.150 |
aul | -0.133 |
cious | -0.131 |
Token | he |
Token ID | 339 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
them | +0.033 |
mate | +0.032 |
wreck | +0.028 |
polar | +0.028 |
tow | +0.027 |
Neg logit contributions | |
� | -0.053 |
's | -0.046 |
ages | -0.046 |
aul | -0.044 |
cious | -0.044 |
Token | loved |
Token ID | 6151 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
� | +0.020 |
's | +0.017 |
ages | +0.016 |
aul | +0.015 |
cious | +0.014 |
Neg logit contributions | |
mate | -0.024 |
them | -0.024 |
tow | -0.022 |
polar | -0.022 |
wreck | -0.021 |
Token | |
Token ID | 220 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
them | +0.106 |
lot | +0.083 |
his | +0.074 |
mate | +0.073 |
room | +0.071 |
Neg logit contributions | |
� | -0.143 |
ience | -0.135 |
rewarding | -0.130 |
decisions | -0.130 |
cious | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
� | +0.078 |
ience | +0.071 |
cious | +0.069 |
ages | +0.068 |
's | +0.067 |
Neg logit contributions | |
them | -0.050 |
mate | -0.045 |
tow | -0.040 |
inn | -0.039 |
ramp | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
� | +0.032 |
's | +0.028 |
ages | +0.027 |
aul | +0.025 |
cious | +0.024 |
Neg logit contributions | |
mate | -0.031 |
them | -0.030 |
wreck | -0.028 |
polar | -0.028 |
tow | -0.028 |
Token | When |
Token ID | 2215 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
� | +0.033 |
ages | +0.029 |
's | +0.029 |
aul | +0.027 |
decisions | +0.027 |
Neg logit contributions | |
mate | -0.028 |
them | -0.028 |
tow | -0.024 |
wreck | -0.024 |
ramp | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
them | +0.082 |
mate | +0.077 |
tow | +0.068 |
wreck | +0.067 |
polar | +0.066 |
Neg logit contributions | |
� | -0.112 |
ages | -0.101 |
's | -0.097 |
aul | -0.096 |
cious | -0.094 |
Token | timer |
Token ID | 19781 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
� | +0.027 |
's | +0.024 |
ages | +0.023 |
aul | +0.021 |
bey | +0.020 |
Neg logit contributions | |
mate | -0.023 |
them | -0.023 |
wreck | -0.020 |
polar | -0.020 |
ramp | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
them | +0.531 |
mate | +0.501 |
tow | +0.478 |
polar | +0.451 |
wreck | +0.447 |
Neg logit contributions | |
� | -0.706 |
ages | -0.609 |
aul | -0.603 |
cious | -0.600 |
List | -0.598 |
Token | off |
Token ID | 572 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
� | +0.225 |
's | +0.197 |
ages | +0.178 |
aul | +0.168 |
Michelle | +0.167 |
Neg logit contributions | |
mate | -0.215 |
them | -0.205 |
polar | -0.203 |
ramp | -0.202 |
snowball | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
� | +0.047 |
's | +0.042 |
ages | +0.036 |
pays | +0.033 |
aul | +0.033 |
Neg logit contributions | |
mate | -0.054 |
captain | -0.048 |
puck | -0.048 |
wreck | -0.048 |
them | -0.048 |
Token | they |
Token ID | 484 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
� | +0.035 |
's | +0.031 |
ages | +0.030 |
aul | +0.029 |
cious | +0.028 |
Neg logit contributions | |
mate | -0.019 |
them | -0.018 |
wreck | -0.016 |
polar | -0.016 |
tow | -0.016 |
Token | took |
Token ID | 1718 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
� | +0.126 |
's | +0.110 |
ages | +0.100 |
aul | +0.096 |
cious | +0.091 |
Neg logit contributions | |
mate | -0.130 |
them | -0.122 |
ramp | -0.114 |
wreck | -0.113 |
tow | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
� | +0.225 |
's | +0.196 |
ages | +0.196 |
aul | +0.187 |
cious | +0.185 |
Neg logit contributions | |
them | -0.135 |
mate | -0.133 |
wreck | -0.116 |
polar | -0.114 |
tow | -0.112 |
Token | She |
Token ID | 1375 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
� | +0.022 |
's | +0.019 |
ages | +0.018 |
aul | +0.018 |
cious | +0.017 |
Neg logit contributions | |
mate | -0.016 |
them | -0.016 |
wreck | -0.014 |
polar | -0.014 |
tow | -0.014 |
Token | bought |
Token ID | 5839 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
� | +0.055 |
decisions | +0.053 |
ages | +0.051 |
cious | +0.048 |
aul | +0.048 |
Neg logit contributions | |
them | -0.042 |
mate | -0.038 |
polar | -0.037 |
stuffed | -0.035 |
wreck | -0.035 |
Token | him |
Token ID | 683 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
them | +0.055 |
mate | +0.047 |
polar | +0.044 |
tow | +0.041 |
wreck | +0.041 |
Neg logit contributions | |
� | -0.091 |
ages | -0.080 |
's | -0.079 |
cious | -0.076 |
bey | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
them | +0.217 |
mate | +0.196 |
polar | +0.182 |
his | +0.173 |
wreck | +0.172 |
Neg logit contributions | |
� | -0.313 |
ages | -0.267 |
's | -0.261 |
cious | -0.260 |
bey | -0.257 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
� | +0.076 |
's | +0.067 |
aul | +0.058 |
ages | +0.057 |
List | +0.053 |
Neg logit contributions | |
them | -0.071 |
mate | -0.071 |
inn | -0.064 |
ramp | -0.058 |
wreck | -0.057 |
Token | of |
Token ID | 286 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
mate | +0.505 |
ramp | +0.493 |
snowball | +0.490 |
them | +0.489 |
polar | +0.480 |
Neg logit contributions | |
� | -0.776 |
's | -0.679 |
ages | -0.605 |
aul | -0.562 |
cious | -0.544 |
Token | new |
Token ID | 649 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mate | +0.202 |
wreck | +0.185 |
ramp | +0.178 |
tow | +0.172 |
inn | +0.166 |
Neg logit contributions | |
� | -0.202 |
's | -0.179 |
ages | -0.150 |
aul | -0.140 |
persever | -0.138 |
Token | shoes |
Token ID | 10012 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
mate | +0.092 |
wreck | +0.084 |
them | +0.084 |
tow | +0.082 |
polar | +0.079 |
Neg logit contributions | |
� | -0.118 |
's | -0.112 |
ages | -0.093 |
cious | -0.086 |
decisions | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
mate | +0.083 |
them | +0.080 |
polar | +0.074 |
wreck | +0.073 |
tow | +0.073 |
Neg logit contributions | |
� | -0.099 |
's | -0.088 |
ages | -0.083 |
aul | -0.078 |
cious | -0.075 |
Token | They |
Token ID | 1119 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
� | +0.019 |
's | +0.016 |
ages | +0.015 |
aul | +0.015 |
cious | +0.014 |
Neg logit contributions | |
mate | -0.018 |
them | -0.017 |
wreck | -0.016 |
polar | -0.016 |
tow | -0.015 |
Token | fairy |
Token ID | 25607 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
� | +0.076 |
ages | +0.070 |
's | +0.068 |
aul | +0.065 |
cious | +0.064 |
Neg logit contributions | |
mate | -0.048 |
them | -0.047 |
polar | -0.043 |
wreck | -0.043 |
captain | -0.042 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
them | +0.005 |
mate | +0.005 |
polar | +0.004 |
wreck | +0.004 |
tow | +0.004 |
Neg logit contributions | |
� | -0.005 |
ages | -0.005 |
aul | -0.005 |
decisions | -0.005 |
List | -0.004 |
Token | Benny |
Token ID | 44275 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
� | +0.248 |
's | +0.219 |
ages | +0.218 |
aul | +0.208 |
cious | +0.204 |
Neg logit contributions | |
them | -0.131 |
mate | -0.128 |
polar | -0.108 |
wreck | -0.106 |
tow | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
� | +0.006 |
bey | +0.005 |
ages | +0.005 |
cious | +0.005 |
List | +0.005 |
Neg logit contributions | |
them | -0.004 |
mate | -0.003 |
his | -0.003 |
polar | -0.003 |
snowball | -0.003 |
Token | special |
Token ID | 2041 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
� | +0.089 |
's | +0.078 |
ages | +0.076 |
aul | +0.073 |
cious | +0.070 |
Neg logit contributions | |
mate | -0.055 |
them | -0.055 |
wreck | -0.047 |
polar | -0.047 |
tow | -0.046 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
� | +0.183 |
's | +0.160 |
ages | +0.154 |
aul | +0.148 |
decisions | +0.143 |
Neg logit contributions | |
them | -0.115 |
mate | -0.114 |
polar | -0.099 |
wreck | -0.099 |
ramp | -0.097 |
Token | of |
Token ID | 286 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
mate | +0.479 |
them | +0.474 |
ramp | +0.473 |
polar | +0.465 |
snowball | +0.456 |
Neg logit contributions | |
� | -0.797 |
's | -0.686 |
ages | -0.621 |
aul | -0.576 |
cious | -0.570 |
Token | shoes |
Token ID | 10012 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
mate | +0.172 |
them | +0.156 |
wreck | +0.156 |
ramp | +0.154 |
inn | +0.151 |
Neg logit contributions | |
� | -0.222 |
's | -0.192 |
ages | -0.179 |
aul | -0.169 |
decisions | -0.166 |
Token | that |
Token ID | 326 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
mate | +0.073 |
them | +0.071 |
polar | +0.065 |
wreck | +0.064 |
tow | +0.064 |
Neg logit contributions | |
� | -0.095 |
's | -0.083 |
ages | -0.079 |
aul | -0.075 |
cious | -0.073 |
Token | made |
Token ID | 925 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
them | +0.034 |
mate | +0.032 |
polar | +0.029 |
tow | +0.029 |
wreck | +0.028 |
Neg logit contributions | |
� | -0.036 |
ages | -0.032 |
aul | -0.031 |
decisions | -0.031 |
's | -0.031 |
Token | him |
Token ID | 683 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
mate | +0.022 |
them | +0.022 |
wreck | +0.018 |
polar | +0.018 |
tow | +0.018 |
Neg logit contributions | |
� | -0.053 |
's | -0.048 |
ages | -0.047 |
aul | -0.045 |
cious | -0.044 |
Token | |
Token ID | 220 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ience | +0.042 |
ages | +0.041 |
uch | +0.040 |
� | +0.039 |
decisions | +0.039 |
Neg logit contributions | |
them | -0.022 |
tow | -0.018 |
mate | -0.016 |
his | -0.015 |
lot | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
� | +0.089 |
ience | +0.087 |
cious | +0.082 |
decisions | +0.080 |
ages | +0.080 |
Neg logit contributions | |
them | -0.050 |
mate | -0.041 |
tow | -0.036 |
inn | -0.034 |
ramp | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
� | +0.039 |
's | +0.035 |
ages | +0.034 |
aul | +0.033 |
decisions | +0.032 |
Neg logit contributions | |
them | -0.031 |
mate | -0.030 |
tow | -0.027 |
polar | -0.026 |
wreck | -0.025 |
Token | When |
Token ID | 2215 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
� | +0.034 |
ages | +0.033 |
aul | +0.032 |
decisions | +0.032 |
's | +0.031 |
Neg logit contributions | |
them | -0.033 |
mate | -0.032 |
tow | -0.029 |
inn | -0.025 |
snowball | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
them | +0.088 |
mate | +0.078 |
tow | +0.071 |
his | +0.067 |
lot | +0.065 |
Neg logit contributions | |
ages | -0.104 |
� | -0.102 |
aul | -0.097 |
aut | -0.096 |
cious | -0.094 |
Token | timer |
Token ID | 19781 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
� | +0.040 |
ages | +0.035 |
's | +0.035 |
aul | +0.033 |
cious | +0.033 |
Neg logit contributions | |
them | -0.026 |
mate | -0.025 |
tow | -0.023 |
wreck | -0.023 |
polar | -0.022 |
Token | finally |
Token ID | 3443 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
them | +0.514 |
mate | +0.471 |
tow | +0.464 |
polar | +0.432 |
wreck | +0.428 |
Neg logit contributions | |
� | -0.703 |
ages | -0.616 |
List | -0.615 |
aul | -0.611 |
cious | -0.603 |
Token | be |
Token ID | 307 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
them | +0.334 |
mate | +0.322 |
tow | +0.290 |
wreck | +0.284 |
inn | +0.281 |
Neg logit contributions | |
� | -0.436 |
ages | -0.393 |
's | -0.378 |
aul | -0.371 |
decisions | -0.365 |
Token | ep |
Token ID | 538 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
them | +0.121 |
mate | +0.113 |
polar | +0.105 |
tow | +0.104 |
inn | +0.103 |
Neg logit contributions | |
� | -0.127 |
ages | -0.106 |
's | -0.105 |
aul | -0.103 |
List | -0.103 |
Token | ed |
Token ID | 276 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
them | +0.343 |
mate | +0.334 |
polar | +0.301 |
tow | +0.298 |
wreck | +0.297 |
Neg logit contributions | |
� | -0.377 |
ages | -0.317 |
aul | -0.314 |
List | -0.313 |
's | -0.308 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
� | +0.235 |
ages | +0.205 |
's | +0.204 |
aul | +0.194 |
cious | +0.191 |
Neg logit contributions | |
them | -0.172 |
mate | -0.166 |
polar | -0.147 |
wreck | -0.146 |
tow | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
mate | +0.023 |
them | +0.023 |
wreck | +0.020 |
polar | +0.020 |
tow | +0.020 |
Neg logit contributions | |
� | -0.032 |
's | -0.028 |
ages | -0.027 |
aul | -0.026 |
cious | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
� | +0.004 |
ages | +0.003 |
's | +0.003 |
aul | +0.003 |
cious | +0.003 |
Neg logit contributions | |
them | -0.003 |
mate | -0.003 |
polar | -0.003 |
tow | -0.003 |
wreck | -0.003 |
Token | picked |
Token ID | 6497 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
them | +0.155 |
polar | +0.134 |
snowball | +0.131 |
stuffed | +0.131 |
hon | +0.129 |
Neg logit contributions | |
� | -0.174 |
ages | -0.173 |
decisions | -0.171 |
cious | -0.165 |
aul | -0.161 |
Token | out |
Token ID | 503 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
them | +0.057 |
mate | +0.053 |
polar | +0.047 |
snowball | +0.047 |
wreck | +0.046 |
Neg logit contributions | |
� | -0.053 |
ages | -0.046 |
's | -0.044 |
aul | -0.043 |
cious | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
� | +0.101 |
's | +0.088 |
ages | +0.083 |
aul | +0.079 |
cious | +0.076 |
Neg logit contributions | |
mate | -0.090 |
them | -0.087 |
wreck | -0.081 |
polar | -0.080 |
ramp | -0.080 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
� | +0.078 |
's | +0.069 |
aul | +0.056 |
ages | +0.056 |
cious | +0.054 |
Neg logit contributions | |
mate | -0.062 |
them | -0.058 |
inn | -0.053 |
captain | -0.050 |
control | -0.050 |
Token | with |
Token ID | 351 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
polar | +0.516 |
mate | +0.504 |
ramp | +0.498 |
snowball | +0.491 |
wreck | +0.488 |
Neg logit contributions | |
� | -0.800 |
's | -0.687 |
ages | -0.569 |
aul | -0.537 |
pays | -0.536 |
Token | her |
Token ID | 607 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
� | +0.073 |
's | +0.062 |
ages | +0.057 |
aul | +0.053 |
cious | +0.052 |
Neg logit contributions | |
mate | -0.073 |
wreck | -0.065 |
ramp | -0.065 |
them | -0.064 |
polar | -0.062 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
mate | +0.077 |
them | +0.072 |
wreck | +0.067 |
inn | +0.066 |
tow | +0.066 |
Neg logit contributions | |
� | -0.095 |
's | -0.085 |
ages | -0.077 |
aul | -0.073 |
cious | -0.071 |
Token | cartoon |
Token ID | 16251 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
mate | +0.109 |
inn | +0.099 |
wreck | +0.094 |
ramp | +0.094 |
firefighter | +0.092 |
Neg logit contributions | |
� | -0.131 |
's | -0.124 |
ages | -0.099 |
cious | -0.094 |
decisions | -0.092 |
Token | character |
Token ID | 2095 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
mate | +0.241 |
them | +0.239 |
polar | +0.211 |
wreck | +0.210 |
tow | +0.210 |
Neg logit contributions | |
� | -0.323 |
's | -0.281 |
ages | -0.276 |
aul | -0.265 |
cious | -0.257 |
Token | " |
Token ID | 366 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
mate | +0.064 |
wreck | +0.061 |
them | +0.059 |
polar | +0.059 |
ramp | +0.056 |
Neg logit contributions | |
� | -0.058 |
's | -0.047 |
ages | -0.041 |
List | -0.039 |
Michelle | -0.039 |
Token | They |
Token ID | 2990 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
mate | +0.155 |
them | +0.153 |
polar | +0.140 |
wreck | +0.140 |
tow | +0.138 |
Neg logit contributions | |
� | -0.163 |
's | -0.139 |
ages | -0.135 |
aul | -0.127 |
cious | -0.123 |
Token | make |
Token ID | 787 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
mate | +0.091 |
them | +0.089 |
polar | +0.079 |
wreck | +0.078 |
tow | +0.078 |
Neg logit contributions | |
� | -0.124 |
's | -0.108 |
ages | -0.105 |
aul | -0.100 |
cious | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
mate | +0.169 |
them | +0.163 |
polar | +0.147 |
tow | +0.147 |
wreck | +0.147 |
Neg logit contributions | |
� | -0.204 |
's | -0.178 |
ages | -0.170 |
aul | -0.162 |
cious | -0.156 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
� | +0.062 |
's | +0.055 |
decisions | +0.046 |
aul | +0.043 |
pays | +0.042 |
Neg logit contributions | |
mate | -0.054 |
them | -0.051 |
inn | -0.047 |
detector | -0.041 |
uit | -0.041 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
mate | +0.088 |
them | +0.082 |
inn | +0.075 |
cowboy | +0.067 |
tant | +0.066 |
Neg logit contributions | |
� | -0.109 |
's | -0.104 |
decisions | -0.087 |
ages | -0.082 |
aul | -0.081 |
Token | ." |
Token ID | 526 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
snowball | +0.582 |
polar | +0.582 |
ramp | +0.565 |
mate | +0.560 |
puck | +0.541 |
Neg logit contributions | |
� | -0.715 |
's | -0.614 |
ages | -0.509 |
grand | -0.438 |
adow | -0.438 |
Token |
|
Token ID | 198 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
mate | +0.192 |
them | +0.182 |
wreck | +0.176 |
polar | +0.172 |
ramp | +0.167 |
Neg logit contributions | |
� | -0.176 |
's | -0.150 |
ages | -0.140 |
aul | -0.131 |
List | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
mate | +0.035 |
wreck | +0.033 |
polar | +0.032 |
captain | +0.032 |
stuffed | +0.031 |
Neg logit contributions | |
� | -0.022 |
's | -0.017 |
List | -0.014 |
ages | -0.014 |
aul | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
mate | +0.025 |
them | +0.024 |
wreck | +0.023 |
polar | +0.023 |
ramp | +0.022 |
Neg logit contributions | |
� | -0.029 |
's | -0.024 |
ages | -0.023 |
aul | -0.021 |
cious | -0.021 |
Token | I |
Token ID | 40 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
mate | +0.062 |
them | +0.061 |
polar | +0.059 |
wreck | +0.059 |
ramp | +0.055 |
Neg logit contributions | |
� | -0.058 |
's | -0.047 |
ages | -0.046 |
cious | -0.043 |
aul | -0.043 |
Token | c |
Token ID | 66 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
� | +0.282 |
's | +0.242 |
ages | +0.235 |
aul | +0.222 |
cious | +0.216 |
Neg logit contributions | |
mate | -0.260 |
them | -0.258 |
polar | -0.232 |
wreck | -0.232 |
tow | -0.230 |
Token | ival |
Token ID | 2473 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
� | +0.220 |
's | +0.181 |
ages | +0.181 |
aul | +0.175 |
cious | +0.173 |
Neg logit contributions | |
them | -0.206 |
mate | -0.202 |
wreck | -0.184 |
polar | -0.179 |
tow | -0.177 |
Token | took |
Token ID | 1718 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
mate | +0.045 |
them | +0.044 |
polar | +0.040 |
wreck | +0.040 |
tow | +0.039 |
Neg logit contributions | |
� | -0.056 |
's | -0.049 |
ages | -0.047 |
aul | -0.044 |
cious | -0.043 |
Token | out |
Token ID | 503 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
� | +0.190 |
's | +0.172 |
ages | +0.162 |
pays | +0.152 |
decisions | +0.150 |
Neg logit contributions | |
mate | -0.109 |
them | -0.098 |
wreck | -0.095 |
ramp | -0.095 |
polar | -0.095 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
� | +0.114 |
's | +0.103 |
ages | +0.097 |
aul | +0.089 |
decisions | +0.089 |
Neg logit contributions | |
mate | -0.083 |
them | -0.074 |
ramp | -0.071 |
wreck | -0.071 |
inn | -0.069 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
� | +0.087 |
's | +0.076 |
ages | +0.064 |
aul | +0.062 |
pays | +0.062 |
Neg logit contributions | |
them | -0.068 |
mate | -0.064 |
inn | -0.059 |
polar | -0.055 |
room | -0.053 |
Token | of |
Token ID | 286 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
them | +0.475 |
mate | +0.466 |
polar | +0.456 |
snowball | +0.439 |
ramp | +0.434 |
Neg logit contributions | |
� | -0.803 |
's | -0.700 |
ages | -0.619 |
aul | -0.574 |
pays | -0.560 |
Token | scissors |
Token ID | 41786 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
mate | +0.171 |
them | +0.152 |
inn | +0.150 |
tow | +0.142 |
polar | +0.141 |
Neg logit contributions | |
� | -0.211 |
's | -0.189 |
ages | -0.174 |
decisions | -0.167 |
aul | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
mate | +0.170 |
them | +0.165 |
polar | +0.152 |
tow | +0.151 |
wreck | +0.150 |
Neg logit contributions | |
� | -0.200 |
's | -0.177 |
ages | -0.166 |
aul | -0.152 |
cious | -0.149 |
Token | said |
Token ID | 531 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
� | +0.045 |
aul | +0.040 |
ages | +0.039 |
's | +0.039 |
cious | +0.038 |
Neg logit contributions | |
them | -0.033 |
mate | -0.031 |
tow | -0.029 |
wreck | -0.028 |
polar | -0.028 |
Token | : |
Token ID | 25 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
mate | +0.003 |
them | +0.003 |
wreck | +0.003 |
polar | +0.003 |
tow | +0.003 |
Neg logit contributions | |
� | -0.004 |
's | -0.003 |
ages | -0.003 |
aul | -0.003 |
cious | -0.003 |
Token | moments |
Token ID | 7188 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
them | +0.165 |
mate | +0.155 |
wreck | +0.147 |
tant | +0.145 |
snowball | +0.144 |
Neg logit contributions | |
� | -0.187 |
's | -0.164 |
cious | -0.159 |
Michelle | -0.158 |
aul | -0.154 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
� | +0.218 |
ages | +0.200 |
's | +0.193 |
cious | +0.190 |
aul | +0.189 |
Neg logit contributions | |
them | -0.162 |
mate | -0.153 |
wreck | -0.128 |
tow | -0.127 |
inn | -0.123 |
Token | check |
Token ID | 2198 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
� | +0.021 |
's | +0.018 |
ages | +0.018 |
aul | +0.017 |
cious | +0.016 |
Neg logit contributions | |
mate | -0.014 |
them | -0.013 |
wreck | -0.012 |
polar | -0.012 |
tow | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
them | +0.043 |
mate | +0.040 |
wreck | +0.031 |
tow | +0.031 |
polar | +0.031 |
Neg logit contributions | |
� | -0.060 |
ages | -0.054 |
's | -0.052 |
aul | -0.052 |
cious | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
them | +0.168 |
mate | +0.155 |
tow | +0.137 |
wreck | +0.137 |
polar | +0.135 |
Neg logit contributions | |
� | -0.190 |
ages | -0.163 |
's | -0.163 |
aul | -0.154 |
cious | -0.154 |
Token | date |
Token ID | 3128 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
� | +0.019 |
's | +0.017 |
ages | +0.017 |
aul | +0.016 |
cious | +0.015 |
Neg logit contributions | |
mate | -0.016 |
them | -0.016 |
wreck | -0.014 |
polar | -0.014 |
tow | -0.014 |
Token | can |
Token ID | 460 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
mate | +0.524 |
them | +0.515 |
tow | +0.434 |
wreck | +0.428 |
polar | +0.414 |
Neg logit contributions | |
� | -0.699 |
ages | -0.627 |
's | -0.614 |
aul | -0.605 |
cious | -0.585 |
Token | save |
Token ID | 3613 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
mate | +0.053 |
them | +0.051 |
polar | +0.049 |
snowball | +0.049 |
ramp | +0.047 |
Neg logit contributions | |
� | -0.078 |
's | -0.067 |
ages | -0.060 |
aul | -0.057 |
decisions | -0.055 |
Token | you |
Token ID | 345 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
them | +0.037 |
mate | +0.030 |
his | +0.027 |
wreck | +0.026 |
control | +0.025 |
Neg logit contributions | |
� | -0.042 |
cious | -0.039 |
ages | -0.038 |
List | -0.037 |
aul | -0.036 |
Token | from |
Token ID | 422 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
� | +0.354 |
List | +0.348 |
ages | +0.347 |
aul | +0.335 |
bey | +0.335 |
Neg logit contributions | |
them | -0.201 |
mate | -0.167 |
wreck | -0.148 |
his | -0.145 |
control | -0.140 |
Token | a |
Token ID | 257 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
� | +0.311 |
's | +0.271 |
ages | +0.270 |
aul | +0.255 |
cious | +0.252 |
Neg logit contributions | |
them | -0.234 |
mate | -0.226 |
wreck | -0.201 |
polar | -0.197 |
tow | -0.194 |
Token | because |
Token ID | 780 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
� | +0.124 |
ages | +0.106 |
ience | +0.106 |
aul | +0.104 |
bey | +0.103 |
Neg logit contributions | |
them | -0.084 |
mate | -0.074 |
wreck | -0.070 |
polar | -0.066 |
his | -0.066 |
Token | he |
Token ID | 339 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
� | +0.177 |
's | +0.155 |
ages | +0.147 |
aul | +0.141 |
List | +0.137 |
Neg logit contributions | |
mate | -0.112 |
them | -0.108 |
wreck | -0.096 |
polar | -0.095 |
ramp | -0.095 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
� | +0.033 |
's | +0.028 |
ages | +0.027 |
aul | +0.025 |
cious | +0.025 |
Neg logit contributions | |
mate | -0.034 |
them | -0.034 |
wreck | -0.031 |
polar | -0.031 |
tow | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
� | +0.103 |
's | +0.088 |
ages | +0.087 |
aul | +0.084 |
cious | +0.080 |
Neg logit contributions | |
them | -0.091 |
mate | -0.089 |
polar | -0.080 |
wreck | -0.080 |
tow | -0.080 |
Token | new |
Token ID | 649 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
� | +0.090 |
's | +0.079 |
ages | +0.069 |
aul | +0.067 |
cious | +0.066 |
Neg logit contributions | |
mate | -0.076 |
them | -0.075 |
inn | -0.068 |
control | -0.060 |
ramp | -0.059 |
Token | pair |
Token ID | 5166 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
them | +0.081 |
mate | +0.079 |
inn | +0.072 |
tow | +0.064 |
polar | +0.063 |
Neg logit contributions | |
� | -0.118 |
's | -0.109 |
ages | -0.096 |
decisions | -0.092 |
aul | -0.091 |
Token | of |
Token ID | 286 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
them | +0.556 |
snowball | +0.542 |
mate | +0.538 |
ramp | +0.533 |
polar | +0.523 |
Neg logit contributions | |
� | -0.721 |
's | -0.635 |
ages | -0.556 |
adow | -0.503 |
cious | -0.502 |
Token | shoes |
Token ID | 10012 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
mate | +0.203 |
ramp | +0.189 |
wreck | +0.189 |
tow | +0.183 |
inn | +0.174 |
Neg logit contributions | |
� | -0.173 |
's | -0.155 |
ages | -0.131 |
aul | -0.125 |
cious | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
mate | +0.094 |
them | +0.087 |
snowball | +0.085 |
polar | +0.084 |
tow | +0.083 |
Neg logit contributions | |
� | -0.094 |
's | -0.084 |
ages | -0.076 |
aul | -0.067 |
bey | -0.066 |
Token | The |
Token ID | 383 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
� | +0.026 |
ages | +0.022 |
's | +0.022 |
aul | +0.021 |
cious | +0.021 |
Neg logit contributions | |
them | -0.018 |
mate | -0.017 |
tow | -0.015 |
wreck | -0.015 |
polar | -0.015 |
Token | shoes |
Token ID | 10012 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
� | +0.120 |
's | +0.110 |
pays | +0.090 |
bey | +0.089 |
ages | +0.089 |
Neg logit contributions | |
mate | -0.107 |
wreck | -0.096 |
polar | -0.094 |
them | -0.091 |
tow | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
� | +0.017 |
's | +0.014 |
ages | +0.011 |
aul | +0.011 |
List | +0.011 |
Neg logit contributions | |
mate | -0.022 |
captain | -0.021 |
wreck | -0.021 |
polar | -0.021 |
puck | -0.020 |
Token | When |
Token ID | 2215 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
� | +0.022 |
's | +0.018 |
ages | +0.018 |
aul | +0.017 |
cious | +0.016 |
Neg logit contributions | |
mate | -0.019 |
them | -0.019 |
polar | -0.017 |
wreck | -0.017 |
ramp | -0.017 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
them | +0.081 |
mate | +0.073 |
tow | +0.064 |
wreck | +0.060 |
polar | +0.059 |
Neg logit contributions | |
� | -0.120 |
ages | -0.114 |
aul | -0.108 |
's | -0.107 |
cious | -0.106 |
Token | marked |
Token ID | 7498 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
them | +0.016 |
mate | +0.015 |
wreck | +0.015 |
tow | +0.015 |
polar | +0.014 |
Neg logit contributions | |
ages | -0.018 |
decisions | -0.018 |
� | -0.018 |
List | -0.018 |
aul | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
mate | +0.130 |
them | +0.129 |
wreck | +0.112 |
polar | +0.112 |
tow | +0.111 |
Neg logit contributions | |
� | -0.194 |
's | -0.170 |
ages | -0.167 |
aul | -0.160 |
cious | -0.156 |
Token | date |
Token ID | 3128 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
� | +0.023 |
ages | +0.021 |
apa | +0.020 |
aul | +0.019 |
bey | +0.019 |
Neg logit contributions | |
them | -0.015 |
mate | -0.014 |
match | -0.013 |
lot | -0.013 |
stuffed | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
mate | +0.504 |
them | +0.497 |
tow | +0.416 |
ramp | +0.401 |
wreck | +0.399 |
Neg logit contributions | |
� | -0.708 |
ages | -0.658 |
aul | -0.631 |
's | -0.611 |
decisions | -0.607 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
� | +0.026 |
ages | +0.026 |
aul | +0.024 |
cious | +0.023 |
bey | +0.023 |
Neg logit contributions | |
them | -0.023 |
mate | -0.021 |
his | -0.020 |
stuffed | -0.019 |
tow | -0.019 |
Token | rainbow |
Token ID | 27223 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
� | +0.077 |
's | +0.067 |
ages | +0.061 |
aul | +0.059 |
cious | +0.058 |
Neg logit contributions | |
them | -0.063 |
mate | -0.062 |
inn | -0.057 |
polar | -0.055 |
wreck | -0.054 |
Token | - |
Token ID | 12 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
them | +0.030 |
mate | +0.030 |
wreck | +0.027 |
polar | +0.026 |
tow | +0.026 |
Neg logit contributions | |
� | -0.040 |
's | -0.034 |
ages | -0.034 |
aul | -0.033 |
cious | -0.031 |
Token | col |
Token ID | 4033 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
� | +0.027 |
decisions | +0.024 |
ages | +0.024 |
's | +0.023 |
aul | +0.022 |
Neg logit contributions | |
them | -0.027 |
mate | -0.025 |
tow | -0.022 |
wreck | -0.022 |
inn | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
� | +0.118 |
ages | +0.105 |
's | +0.101 |
cious | +0.100 |
aul | +0.099 |
Neg logit contributions | |
them | -0.090 |
mate | -0.081 |
tow | -0.073 |
polar | -0.073 |
wreck | -0.070 |
Token | calendar |
Token ID | 11845 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
� | +0.092 |
's | +0.082 |
ages | +0.076 |
aul | +0.072 |
cious | +0.071 |
Neg logit contributions | |
mate | -0.063 |
them | -0.062 |
inn | -0.054 |
polar | -0.053 |
tow | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
� | +0.156 |
ages | +0.138 |
's | +0.135 |
aul | +0.132 |
cious | +0.131 |
Neg logit contributions | |
mate | -0.106 |
them | -0.104 |
wreck | -0.090 |
tow | -0.089 |
ramp | -0.088 |
Token | mark |
Token ID | 1317 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ages | +0.049 |
aul | +0.049 |
� | +0.048 |
aut | +0.046 |
ience | +0.046 |
Neg logit contributions | |
them | -0.027 |
mate | -0.021 |
match | -0.021 |
tow | -0.020 |
stuffed | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
them | +0.002 |
mate | +0.002 |
tow | +0.002 |
polar | +0.002 |
wreck | +0.002 |
Neg logit contributions | |
� | -0.003 |
's | -0.002 |
ages | -0.002 |
aul | -0.002 |
cious | -0.002 |
Token | date |
Token ID | 3128 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
� | +0.028 |
ages | +0.025 |
apa | +0.024 |
bey | +0.024 |
aul | +0.023 |
Neg logit contributions | |
them | -0.020 |
lot | -0.018 |
mate | -0.018 |
match | -0.016 |
stuffed | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
mate | +0.527 |
them | +0.522 |
wreck | +0.465 |
polar | +0.464 |
tow | +0.459 |
Neg logit contributions | |
� | -0.709 |
's | -0.619 |
ages | -0.603 |
aul | -0.574 |
cious | -0.559 |
Token | a |
Token ID | 257 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
� | +0.070 |
's | +0.060 |
ages | +0.058 |
aul | +0.055 |
cious | +0.053 |
Neg logit contributions | |
mate | -0.060 |
them | -0.056 |
wreck | -0.054 |
polar | -0.054 |
ramp | -0.054 |
Token | cr |
Token ID | 1067 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
� | +0.091 |
's | +0.080 |
ages | +0.076 |
aul | +0.073 |
cious | +0.071 |
Neg logit contributions | |
mate | -0.061 |
them | -0.061 |
polar | -0.054 |
wreck | -0.053 |
inn | -0.052 |
Token | ay |
Token ID | 323 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
mate | +0.022 |
them | +0.021 |
polar | +0.019 |
wreck | +0.019 |
ramp | +0.019 |
Neg logit contributions | |
� | -0.039 |
's | -0.034 |
ages | -0.034 |
aul | -0.033 |
cious | -0.031 |
Token | on |
Token ID | 261 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
them | +0.283 |
mate | +0.281 |
tow | +0.244 |
wreck | +0.238 |
polar | +0.237 |
Neg logit contributions | |
� | -0.297 |
's | -0.253 |
ages | -0.250 |
aul | -0.241 |
cious | -0.236 |
Token | by |
Token ID | 416 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
� | +0.016 |
's | +0.013 |
List | +0.009 |
aul | +0.009 |
ages | +0.009 |
Neg logit contributions | |
mate | -0.026 |
captain | -0.025 |
wreck | -0.025 |
polar | -0.025 |
puck | -0.025 |
Token | one |
Token ID | 530 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
� | +0.195 |
's | +0.169 |
ages | +0.161 |
aul | +0.153 |
cious | +0.149 |
Neg logit contributions | |
mate | -0.155 |
them | -0.150 |
polar | -0.138 |
tow | -0.137 |
wreck | -0.137 |
Token | � |
Token ID | 6184 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
� | +0.005 |
ages | +0.004 |
's | +0.004 |
aul | +0.004 |
cious | +0.004 |
Neg logit contributions | |
mate | -0.003 |
them | -0.003 |
wreck | -0.003 |
polar | -0.003 |
tow | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
� | +0.000 |
's | +0.000 |
ages | +0.000 |
aul | +0.000 |
cious | +0.000 |
Neg logit contributions | |
mate | -0.000 |
them | -0.000 |
wreck | -0.000 |
tow | -0.000 |
polar | -0.000 |
Token | € |
Token ID | 26391 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
mate | +0.004 |
them | +0.004 |
tow | +0.004 |
ramp | +0.004 |
inn | +0.004 |
Neg logit contributions | |
� | -0.004 |
ages | -0.003 |
's | -0.003 |
aul | -0.003 |
bey | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
� | +0.213 |
decisions | +0.205 |
ages | +0.198 |
aul | +0.197 |
ience | +0.196 |
Neg logit contributions | |
them | -0.137 |
mate | -0.135 |
tow | -0.123 |
ramp | -0.122 |
racer | -0.114 |
Token | � |
Token ID | 250 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
� | +0.975 |
's | +0.870 |
ages | +0.863 |
aul | +0.795 |
decisions | +0.792 |
Neg logit contributions | |
mate | -0.796 |
them | -0.776 |
wreck | -0.706 |
ramp | -0.696 |
tow | -0.696 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
mate | +0.004 |
them | +0.004 |
tow | +0.004 |
inn | +0.004 |
wreck | +0.004 |
Neg logit contributions | |
� | -0.004 |
's | -0.004 |
ages | -0.004 |
aul | -0.004 |
cious | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
mate | +0.061 |
them | +0.061 |
wreck | +0.053 |
tow | +0.053 |
polar | +0.053 |
Neg logit contributions | |
� | -0.084 |
's | -0.074 |
ages | -0.073 |
aul | -0.070 |
cious | -0.068 |
Token | 2 |
Token ID | 362 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
� | +0.046 |
ages | +0.041 |
's | +0.039 |
aul | +0.037 |
cious | +0.035 |
Neg logit contributions | |
them | -0.078 |
mate | -0.076 |
tow | -0.070 |
polar | -0.070 |
wreck | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
them | +0.048 |
mate | +0.047 |
polar | +0.041 |
wreck | +0.040 |
tow | +0.040 |
Neg logit contributions | |
� | -0.069 |
's | -0.060 |
ages | -0.060 |
aul | -0.057 |
cious | -0.056 |
Token | rare |
Token ID | 4071 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
� | +0.122 |
's | +0.106 |
ages | +0.103 |
aul | +0.098 |
cious | +0.095 |
Neg logit contributions | |
mate | -0.095 |
them | -0.094 |
wreck | -0.083 |
polar | -0.083 |
tow | -0.083 |
Token | silence |
Token ID | 9550 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
mate | +0.022 |
them | +0.021 |
wreck | +0.019 |
polar | +0.019 |
tow | +0.019 |
Neg logit contributions | |
� | -0.032 |
's | -0.028 |
ages | -0.027 |
aul | -0.026 |
cious | -0.025 |
Token | � |
Token ID | 6184 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.216 |
ages | +0.194 |
's | +0.189 |
aul | +0.185 |
cious | +0.181 |
Neg logit contributions | |
them | -0.152 |
mate | -0.148 |
wreck | -0.130 |
polar | -0.127 |
tow | -0.126 |
Token | � |
Token ID | 95 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
ages | +0.009 |
� | +0.009 |
's | +0.009 |
aul | +0.008 |
decisions | +0.008 |
Neg logit contributions | |
mate | -0.009 |
them | -0.009 |
tow | -0.008 |
inn | -0.008 |
ramp | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
mate | +0.004 |
them | +0.004 |
inn | +0.004 |
tow | +0.004 |
ramp | +0.004 |
Neg logit contributions | |
ages | -0.003 |
� | -0.003 |
's | -0.003 |
aul | -0.003 |
decisions | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
decisions | +0.182 |
aul | +0.179 |
� | +0.178 |
List | +0.169 |
persever | +0.169 |
Neg logit contributions | |
them | -0.162 |
mate | -0.157 |
tow | -0.151 |
ramp | -0.147 |
racer | -0.144 |
Token | � |
Token ID | 250 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
� | +0.968 |
ages | +0.935 |
's | +0.909 |
decisions | +0.871 |
cious | +0.861 |
Neg logit contributions | |
mate | -0.713 |
them | -0.694 |
ramp | -0.655 |
wreck | -0.650 |
tow | -0.630 |
Token | that |
Token ID | 326 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
mate | +0.009 |
them | +0.009 |
tow | +0.008 |
wreck | +0.008 |
inn | +0.008 |
Neg logit contributions | |
� | -0.009 |
's | -0.008 |
ages | -0.008 |
aul | -0.008 |
cious | -0.007 |
Token | added |
Token ID | 2087 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
them | +0.010 |
mate | +0.009 |
wreck | +0.009 |
splash | +0.009 |
rock | +0.008 |
Neg logit contributions | |
ages | -0.006 |
assy | -0.006 |
aul | -0.006 |
cious | -0.006 |
bey | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
� | +0.138 |
ages | +0.125 |
's | +0.121 |
aul | +0.118 |
cious | +0.117 |
Neg logit contributions | |
them | -0.113 |
mate | -0.104 |
wreck | -0.089 |
polar | -0.089 |
tow | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
� | +0.053 |
ages | +0.047 |
's | +0.046 |
aul | +0.045 |
cious | +0.043 |
Neg logit contributions | |
them | -0.040 |
mate | -0.038 |
wreck | -0.034 |
polar | -0.034 |
tow | -0.033 |
Token | something |
Token ID | 1223 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
them | +0.053 |
mate | +0.050 |
wreck | +0.044 |
polar | +0.043 |
tow | +0.043 |
Neg logit contributions | |
� | -0.065 |
ages | -0.059 |
's | -0.057 |
aul | -0.056 |
bey | -0.054 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.295 |
's | +0.255 |
ages | +0.247 |
aul | +0.234 |
cious | +0.228 |
Neg logit contributions | |
mate | -0.246 |
them | -0.243 |
polar | -0.218 |
wreck | -0.218 |
tow | -0.216 |
Token | � |
Token ID | 6184 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
� | +0.115 |
ages | +0.102 |
's | +0.100 |
aul | +0.098 |
cious | +0.094 |
Neg logit contributions | |
them | -0.076 |
mate | -0.074 |
wreck | -0.063 |
polar | -0.062 |
tow | -0.061 |
Token | � |
Token ID | 95 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
ages | +0.020 |
� | +0.019 |
's | +0.018 |
decisions | +0.017 |
mindful | +0.017 |
Neg logit contributions | |
mate | -0.018 |
ramp | -0.017 |
them | -0.017 |
wreck | -0.016 |
tow | -0.016 |
Token | € |
Token ID | 26391 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ages | +0.004 |
� | +0.004 |
bey | +0.004 |
decisions | +0.004 |
aul | +0.004 |
Neg logit contributions | |
mate | -0.005 |
them | -0.005 |
ramp | -0.005 |
tow | -0.005 |
inn | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
decisions | +0.194 |
aul | +0.182 |
persever | +0.181 |
ience | +0.180 |
� | +0.177 |
Neg logit contributions | |
them | -0.164 |
mate | -0.151 |
room | -0.148 |
ramp | -0.147 |
tow | -0.143 |
Token | � |
Token ID | 250 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ages | +1.117 |
decisions | +1.100 |
� | +1.081 |
's | +1.033 |
cious | +1.016 |
Neg logit contributions | |
them | -0.513 |
mate | -0.499 |
ramp | -0.465 |
wreck | -0.451 |
tow | -0.438 |
Token | the |
Token ID | 262 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
mate | +0.010 |
them | +0.010 |
tow | +0.009 |
wreck | +0.009 |
inn | +0.009 |
Neg logit contributions | |
� | -0.010 |
's | -0.010 |
ages | -0.009 |
aul | -0.009 |
ience | -0.009 |
Token | mirror |
Token ID | 10162 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
� | +0.067 |
ages | +0.062 |
's | +0.060 |
aul | +0.058 |
cious | +0.056 |
Neg logit contributions | |
mate | -0.042 |
them | -0.041 |
wreck | -0.039 |
polar | -0.038 |
tow | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
them | +0.011 |
mate | +0.011 |
wreck | +0.009 |
match | +0.009 |
ramp | +0.009 |
Neg logit contributions | |
� | -0.014 |
List | -0.013 |
ages | -0.013 |
aul | -0.013 |
Michelle | -0.012 |
Token | making |
Token ID | 1642 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
them | +0.006 |
mate | +0.006 |
polar | +0.005 |
wreck | +0.005 |
tow | +0.005 |
Neg logit contributions | |
� | -0.008 |
ages | -0.008 |
aul | -0.007 |
's | -0.007 |
bey | -0.007 |
Token | from |
Token ID | 422 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
� | +0.109 |
's | +0.095 |
ages | +0.089 |
aul | +0.084 |
cious | +0.082 |
Neg logit contributions | |
mate | -0.083 |
them | -0.080 |
tow | -0.073 |
wreck | -0.073 |
ramp | -0.072 |
Token | overhead |
Token ID | 16965 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
� | +0.264 |
's | +0.218 |
praying | +0.206 |
Michelle | +0.199 |
Louise | +0.197 |
Neg logit contributions | |
mate | -0.296 |
inn | -0.270 |
ramp | -0.257 |
tant | -0.254 |
puck | -0.254 |
Token | � |
Token ID | 6184 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
mate | +0.103 |
them | +0.101 |
wreck | +0.090 |
polar | +0.090 |
tow | +0.089 |
Neg logit contributions | |
� | -0.144 |
's | -0.127 |
ages | -0.122 |
aul | -0.116 |
cious | -0.113 |
Token | � |
Token ID | 95 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
� | +0.022 |
ages | +0.021 |
's | +0.020 |
bey | +0.019 |
decisions | +0.019 |
Neg logit contributions | |
mate | -0.019 |
them | -0.018 |
wreck | -0.018 |
ramp | -0.017 |
tow | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
� | +0.010 |
ages | +0.010 |
bey | +0.009 |
ience | +0.009 |
aul | +0.009 |
Neg logit contributions | |
mate | -0.012 |
them | -0.011 |
tow | -0.011 |
wreck | -0.010 |
ramp | -0.010 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
� | +0.216 |
decisions | +0.214 |
ience | +0.205 |
aul | +0.203 |
persever | +0.203 |
Neg logit contributions | |
them | -0.158 |
mate | -0.152 |
ramp | -0.149 |
tow | -0.144 |
wreck | -0.144 |
Token | � |
Token ID | 250 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
� | +0.935 |
ages | +0.851 |
's | +0.830 |
decisions | +0.813 |
aul | +0.766 |
Neg logit contributions | |
mate | -0.779 |
them | -0.770 |
wreck | -0.721 |
ramp | -0.714 |
tow | -0.696 |
Token | it |
Token ID | 340 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
mate | +0.008 |
them | +0.008 |
polar | +0.007 |
wreck | +0.007 |
tow | +0.007 |
Neg logit contributions | |
� | -0.009 |
's | -0.008 |
ages | -0.008 |
aul | -0.007 |
cious | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
them | +0.071 |
wreck | +0.068 |
mate | +0.067 |
polar | +0.067 |
hon | +0.065 |
Neg logit contributions | |
ages | -0.037 |
aul | -0.036 |
cious | -0.032 |
oney | -0.030 |
List | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
them | +0.007 |
mate | +0.006 |
polar | +0.006 |
tow | +0.005 |
wreck | +0.005 |
Neg logit contributions | |
� | -0.009 |
ages | -0.009 |
aul | -0.009 |
bey | -0.008 |
cious | -0.008 |
Token | switch |
Token ID | 5078 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
� | +0.121 |
's | +0.105 |
ages | +0.099 |
aul | +0.095 |
cious | +0.094 |
Neg logit contributions | |
them | -0.091 |
mate | -0.090 |
inn | -0.079 |
tow | -0.078 |
wreck | -0.076 |
Token | of |
Token ID | 286 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ages | +0.176 |
aul | +0.170 |
� | +0.166 |
ience | +0.161 |
bey | +0.161 |
Neg logit contributions | |
them | -0.110 |
mate | -0.091 |
tow | -0.075 |
control | -0.071 |
his | -0.071 |
Token | school |
Token ID | 1524 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
mate | +0.157 |
them | +0.148 |
wreck | +0.140 |
polar | +0.140 |
ramp | +0.139 |
Neg logit contributions | |
� | -0.190 |
's | -0.163 |
ages | -0.154 |
aul | -0.149 |
cious | -0.144 |
Token | � |
Token ID | 6184 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
them | +0.150 |
mate | +0.145 |
wreck | +0.123 |
tow | +0.120 |
ramp | +0.119 |
Neg logit contributions | |
� | -0.241 |
ages | -0.219 |
aul | -0.215 |
's | -0.207 |
cious | -0.205 |
Token | � |
Token ID | 95 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
� | +0.019 |
ages | +0.019 |
's | +0.018 |
decisions | +0.017 |
aul | +0.016 |
Neg logit contributions | |
mate | -0.020 |
them | -0.019 |
wreck | -0.018 |
inn | -0.018 |
ramp | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
ages | +0.002 |
� | +0.002 |
decisions | +0.002 |
aul | +0.002 |
ience | +0.002 |
Neg logit contributions | |
mate | -0.003 |
them | -0.003 |
tow | -0.003 |
inn | -0.003 |
room | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
decisions | +0.194 |
� | +0.185 |
aul | +0.182 |
ience | +0.177 |
persever | +0.177 |
Neg logit contributions | |
them | -0.161 |
mate | -0.149 |
room | -0.142 |
tow | -0.140 |
ramp | -0.138 |
Token | � |
Token ID | 250 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
� | +1.098 |
ages | +0.996 |
's | +0.988 |
decisions | +0.943 |
cious | +0.918 |
Neg logit contributions | |
mate | -0.643 |
them | -0.630 |
wreck | -0.555 |
ramp | -0.550 |
tow | -0.547 |
Token | it |
Token ID | 340 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
mate | +0.018 |
them | +0.018 |
tow | +0.016 |
wreck | +0.016 |
polar | +0.016 |
Neg logit contributions | |
� | -0.019 |
's | -0.016 |
ages | -0.016 |
aul | -0.015 |
cious | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
them | +0.076 |
mate | +0.074 |
match | +0.071 |
wreck | +0.068 |
ramp | +0.067 |
Neg logit contributions | |
ages | -0.038 |
aul | -0.037 |
cious | -0.034 |
oney | -0.031 |
List | -0.031 |
Token | an |
Token ID | 281 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
them | +0.006 |
mate | +0.006 |
tow | +0.005 |
polar | +0.005 |
wreck | +0.005 |
Neg logit contributions | |
� | -0.008 |
ages | -0.007 |
's | -0.007 |
aul | -0.007 |
cious | -0.007 |
Token | important |
Token ID | 1593 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
� | +0.173 |
's | +0.148 |
ages | +0.143 |
aul | +0.135 |
cious | +0.131 |
Neg logit contributions | |
mate | -0.180 |
them | -0.178 |
wreck | -0.161 |
polar | -0.161 |
tow | -0.160 |
Token | something |
Token ID | 1223 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
mate | +0.053 |
them | +0.050 |
tow | +0.047 |
ramp | +0.047 |
inn | +0.046 |
Neg logit contributions | |
� | -0.050 |
's | -0.044 |
ages | -0.040 |
aul | -0.038 |
cious | -0.036 |
Token | special |
Token ID | 2041 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
� | +0.311 |
's | +0.270 |
ages | +0.236 |
cious | +0.223 |
aul | +0.222 |
Neg logit contributions | |
mate | -0.253 |
them | -0.234 |
tow | -0.217 |
polar | -0.214 |
captain | -0.214 |
Token | � |
Token ID | 6184 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
� | +0.197 |
's | +0.171 |
ages | +0.171 |
aul | +0.163 |
cious | +0.159 |
Neg logit contributions | |
mate | -0.136 |
them | -0.136 |
wreck | -0.118 |
polar | -0.117 |
tow | -0.115 |
Token | � |
Token ID | 95 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
� | +0.030 |
ages | +0.027 |
's | +0.026 |
decisions | +0.025 |
bey | +0.025 |
Neg logit contributions | |
mate | -0.025 |
them | -0.023 |
ramp | -0.023 |
wreck | -0.023 |
tow | -0.021 |
Token | € |
Token ID | 26391 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
� | +0.013 |
ages | +0.012 |
bey | +0.011 |
decisions | +0.011 |
ience | +0.011 |
Neg logit contributions | |
mate | -0.015 |
them | -0.014 |
ramp | -0.013 |
tow | -0.013 |
wreck | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
� | +0.189 |
decisions | +0.174 |
aul | +0.161 |
ience | +0.161 |
persever | +0.158 |
Neg logit contributions | |
them | -0.200 |
mate | -0.197 |
ramp | -0.192 |
room | -0.184 |
snowball | -0.182 |
Token | � |
Token ID | 250 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
� | +0.982 |
ages | +0.880 |
's | +0.855 |
decisions | +0.845 |
aul | +0.798 |
Neg logit contributions | |
them | -0.736 |
mate | -0.730 |
wreck | -0.681 |
ramp | -0.677 |
tow | -0.651 |
Token | a |
Token ID | 257 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
mate | +0.010 |
them | +0.010 |
wreck | +0.009 |
polar | +0.009 |
tow | +0.009 |
Neg logit contributions | |
� | -0.012 |
's | -0.010 |
ages | -0.010 |
aul | -0.009 |
cious | -0.009 |
Token | pool |
Token ID | 5933 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
� | +0.117 |
's | +0.102 |
ages | +0.097 |
aul | +0.093 |
cious | +0.093 |
Neg logit contributions | |
them | -0.080 |
mate | -0.078 |
inn | -0.068 |
tow | -0.066 |
wreck | -0.065 |
Token | ! |
Token ID | 0 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
them | +0.186 |
mate | +0.186 |
polar | +0.164 |
tow | +0.163 |
wreck | +0.162 |
Neg logit contributions | |
� | -0.261 |
's | -0.227 |
ages | -0.217 |
aul | -0.207 |
cious | -0.200 |
Token | It |
Token ID | 632 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
mate | +0.049 |
them | +0.048 |
tow | +0.046 |
polar | +0.045 |
wreck | +0.042 |
Neg logit contributions | |
ages | -0.048 |
� | -0.048 |
's | -0.045 |
aul | -0.044 |
bey | -0.043 |
Token | t |
Token ID | 83 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
� | +0.352 |
's | +0.297 |
ages | +0.274 |
aul | +0.256 |
cious | +0.245 |
Neg logit contributions | |
mate | -0.353 |
them | -0.350 |
polar | -0.335 |
wreck | -0.331 |
ramp | -0.329 |
Token | help |
Token ID | 1037 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
mate | +0.011 |
them | +0.011 |
snowball | +0.011 |
ramp | +0.010 |
polar | +0.010 |
Neg logit contributions | |
� | -0.014 |
's | -0.011 |
ages | -0.009 |
mindful | -0.009 |
cious | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
mate | +0.078 |
tow | +0.073 |
ramp | +0.072 |
polar | +0.072 |
wreck | +0.072 |
Neg logit contributions | |
� | -0.090 |
's | -0.079 |
ages | -0.065 |
decisions | -0.064 |
pays | -0.060 |
Token | â |
Token ID | 22940 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
mate | +0.072 |
polar | +0.072 |
tow | +0.070 |
them | +0.070 |
firefighter | +0.068 |
Neg logit contributions | |
� | -0.086 |
's | -0.076 |
ages | -0.060 |
pays | -0.057 |
decisions | -0.056 |
Token | € |
Token ID | 26391 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
� | +0.099 |
ages | +0.087 |
's | +0.084 |
cious | +0.081 |
aul | +0.080 |
Neg logit contributions | |
mate | -0.157 |
them | -0.149 |
inn | -0.144 |
wreck | -0.138 |
ramp | -0.136 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.178 |
decisions | +0.161 |
aul | +0.157 |
ience | +0.154 |
List | +0.152 |
Neg logit contributions | |
them | -0.199 |
mate | -0.197 |
ramp | -0.187 |
wreck | -0.178 |
tow | -0.177 |
Token | � |
Token ID | 251 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
� | +1.103 |
's | +0.985 |
ages | +0.971 |
aul | +0.920 |
cious | +0.917 |
Neg logit contributions | |
mate | -0.651 |
them | -0.637 |
wreck | -0.559 |
ramp | -0.551 |
tow | -0.550 |
Token | he |
Token ID | 258 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
� | +0.027 |
's | +0.023 |
ages | +0.023 |
aul | +0.022 |
cious | +0.021 |
Neg logit contributions | |
them | -0.023 |
mate | -0.023 |
polar | -0.020 |
wreck | -0.020 |
tow | -0.020 |
Token | reached |
Token ID | 4251 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
mate | +0.354 |
them | +0.346 |
tow | +0.331 |
wreck | +0.329 |
polar | +0.326 |
Neg logit contributions | |
� | -0.418 |
's | -0.369 |
ages | -0.348 |
aul | -0.318 |
cious | -0.313 |
Token | out |
Token ID | 503 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
mate | +0.018 |
wreck | +0.016 |
them | +0.016 |
polar | +0.015 |
ramp | +0.015 |
Neg logit contributions | |
� | -0.019 |
's | -0.017 |
ages | -0.015 |
pays | -0.014 |
decisions | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
� | +0.148 |
's | +0.128 |
ages | +0.108 |
pays | +0.107 |
Louise | +0.106 |
Neg logit contributions | |
mate | -0.086 |
wreck | -0.084 |
ramp | -0.083 |
spoiler | -0.074 |
puck | -0.074 |
Token | those |
Token ID | 883 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
� | +0.008 |
ages | +0.007 |
cious | +0.007 |
ience | +0.007 |
bey | +0.007 |
Neg logit contributions | |
them | -0.004 |
mate | -0.004 |
tow | -0.004 |
polar | -0.004 |
wreck | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
them | +0.045 |
mate | +0.043 |
wreck | +0.039 |
polar | +0.038 |
tow | +0.038 |
Neg logit contributions | |
� | -0.054 |
ages | -0.047 |
's | -0.047 |
aul | -0.044 |
cious | -0.043 |
Token | need |
Token ID | 761 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mate | +0.004 |
them | +0.004 |
polar | +0.003 |
wreck | +0.003 |
tow | +0.003 |
Neg logit contributions | |
� | -0.005 |
's | -0.005 |
ages | -0.004 |
aul | -0.004 |
decisions | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
mate | +0.064 |
them | +0.064 |
wreck | +0.057 |
polar | +0.056 |
tow | +0.056 |
Neg logit contributions | |
� | -0.084 |
's | -0.074 |
ages | -0.072 |
aul | -0.068 |
cious | -0.066 |
Token | € |
Token ID | 26391 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ages | +0.102 |
� | +0.101 |
cious | +0.099 |
's | +0.094 |
aul | +0.089 |
Neg logit contributions | |
mate | -0.124 |
them | -0.123 |
inn | -0.117 |
wreck | -0.111 |
load | -0.103 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.156 |
aul | +0.155 |
decisions | +0.151 |
pays | +0.150 |
ience | +0.149 |
Neg logit contributions | |
them | -0.178 |
mate | -0.170 |
tow | -0.153 |
ramp | -0.152 |
wreck | -0.150 |
Token | � |
Token ID | 251 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
� | +0.835 |
ages | +0.757 |
's | +0.749 |
cious | +0.709 |
decisions | +0.699 |
Neg logit contributions | |
mate | -0.851 |
them | -0.836 |
wreck | -0.788 |
ramp | -0.775 |
tow | -0.755 |
Token | even |
Token ID | 10197 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
� | +0.029 |
ages | +0.026 |
's | +0.026 |
aul | +0.025 |
cious | +0.024 |
Neg logit contributions | |
them | -0.026 |
mate | -0.025 |
polar | -0.022 |
tow | -0.022 |
wreck | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
� | +0.197 |
ages | +0.184 |
aul | +0.171 |
's | +0.170 |
cious | +0.168 |
Neg logit contributions | |
them | -0.186 |
mate | -0.182 |
polar | -0.159 |
tant | -0.159 |
inn | -0.155 |
Token | One |
Token ID | 3198 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
� | +0.071 |
ages | +0.065 |
's | +0.062 |
aul | +0.059 |
cious | +0.059 |
Neg logit contributions | |
them | -0.063 |
mate | -0.061 |
polar | -0.054 |
tow | -0.054 |
wreck | -0.054 |
Token | day |
Token ID | 1110 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
them | +0.110 |
mate | +0.104 |
wreck | +0.100 |
polar | +0.098 |
tow | +0.097 |
Neg logit contributions | |
� | -0.130 |
ages | -0.129 |
cious | -0.117 |
's | -0.115 |
aul | -0.115 |
Token | anxious |
Token ID | 18116 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
mate | +0.332 |
them | +0.322 |
tow | +0.300 |
ramp | +0.299 |
wreck | +0.295 |
Neg logit contributions | |
� | -0.254 |
's | -0.213 |
ages | -0.203 |
aul | -0.185 |
cious | -0.180 |
Token | anymore |
Token ID | 7471 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
� | +0.044 |
's | +0.040 |
ages | +0.039 |
aul | +0.037 |
cious | +0.036 |
Neg logit contributions | |
mate | -0.020 |
them | -0.020 |
polar | -0.017 |
wreck | -0.017 |
tow | -0.017 |
Token | � |
Token ID | 6184 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
mate | +0.270 |
them | +0.269 |
wreck | +0.238 |
polar | +0.237 |
tow | +0.234 |
Neg logit contributions | |
� | -0.353 |
's | -0.307 |
ages | -0.301 |
aul | -0.288 |
cious | -0.280 |
Token | � |
Token ID | 95 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
� | +0.023 |
's | +0.021 |
ages | +0.020 |
aul | +0.019 |
cious | +0.018 |
Neg logit contributions | |
mate | -0.021 |
them | -0.020 |
wreck | -0.018 |
tow | -0.018 |
ramp | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
� | +0.007 |
ages | +0.007 |
aul | +0.006 |
's | +0.006 |
cious | +0.006 |
Neg logit contributions | |
mate | -0.010 |
them | -0.009 |
wreck | -0.009 |
ramp | -0.009 |
tow | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.197 |
decisions | +0.183 |
aul | +0.180 |
persever | +0.174 |
ience | +0.173 |
Neg logit contributions | |
them | -0.172 |
mate | -0.164 |
ramp | -0.153 |
wreck | -0.150 |
racer | -0.149 |
Token | � |
Token ID | 251 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
� | +1.063 |
's | +0.948 |
ages | +0.945 |
decisions | +0.899 |
cious | +0.883 |
Neg logit contributions | |
mate | -0.674 |
them | -0.656 |
wreck | -0.592 |
ramp | -0.589 |
tow | -0.569 |
Token | he |
Token ID | 339 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
� | +0.033 |
ages | +0.030 |
's | +0.029 |
aul | +0.029 |
cious | +0.028 |
Neg logit contributions | |
them | -0.026 |
mate | -0.025 |
polar | -0.022 |
tow | -0.022 |
wreck | -0.021 |
Token | knew |
Token ID | 2993 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
� | +0.061 |
ages | +0.054 |
aul | +0.052 |
's | +0.052 |
cious | +0.050 |
Neg logit contributions | |
them | -0.059 |
mate | -0.057 |
polar | -0.052 |
wreck | -0.052 |
tow | -0.051 |
Token | he |
Token ID | 339 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
� | +0.043 |
's | +0.037 |
ages | +0.036 |
aul | +0.034 |
cious | +0.033 |
Neg logit contributions | |
mate | -0.031 |
them | -0.031 |
wreck | -0.027 |
polar | -0.027 |
tow | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
� | +0.060 |
aul | +0.057 |
ages | +0.056 |
cious | +0.053 |
decisions | +0.053 |
Neg logit contributions | |
them | -0.048 |
mate | -0.047 |
wreck | -0.042 |
tow | -0.040 |
polar | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
� | +0.037 |
's | +0.033 |
ages | +0.031 |
aul | +0.028 |
cious | +0.028 |
Neg logit contributions | |
mate | -0.023 |
wreck | -0.022 |
tow | -0.022 |
ramp | -0.021 |
polar | -0.021 |
Token | rocked |
Token ID | 36872 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
� | +0.015 |
aul | +0.013 |
ages | +0.013 |
decisions | +0.013 |
's | +0.012 |
Neg logit contributions | |
them | -0.011 |
mate | -0.010 |
polar | -0.009 |
snowball | -0.009 |
puck | -0.009 |
Token | � |
Token ID | 6184 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
� | +0.032 |
's | +0.028 |
ages | +0.025 |
aul | +0.023 |
cious | +0.022 |
Neg logit contributions | |
wreck | -0.026 |
mate | -0.026 |
polar | -0.025 |
tow | -0.025 |
ramp | -0.025 |
Token | � |
Token ID | 95 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
� | +0.009 |
's | +0.008 |
ages | +0.008 |
aul | +0.008 |
cious | +0.007 |
Neg logit contributions | |
mate | -0.008 |
them | -0.008 |
wreck | -0.007 |
polar | -0.007 |
tow | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
� | +0.000 |
ages | +0.000 |
's | +0.000 |
aul | +0.000 |
bey | +0.000 |
Neg logit contributions | |
mate | -0.000 |
them | -0.000 |
ramp | -0.000 |
tow | -0.000 |
inn | -0.000 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.189 |
decisions | +0.179 |
aul | +0.173 |
List | +0.168 |
Michelle | +0.166 |
Neg logit contributions | |
them | -0.165 |
mate | -0.158 |
ramp | -0.155 |
snowball | -0.147 |
tow | -0.144 |
Token | � |
Token ID | 250 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
� | +0.992 |
's | +0.886 |
ages | +0.874 |
decisions | +0.818 |
cious | +0.812 |
Neg logit contributions | |
mate | -0.745 |
them | -0.732 |
wreck | -0.656 |
ramp | -0.651 |
tow | -0.646 |
Token | higher |
Token ID | 2440 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
mate | +0.006 |
them | +0.006 |
tow | +0.006 |
polar | +0.006 |
inn | +0.006 |
Neg logit contributions | |
� | -0.007 |
's | -0.006 |
ages | -0.006 |
aul | -0.006 |
decisions | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
� | +0.163 |
's | +0.144 |
ages | +0.142 |
aul | +0.136 |
cious | +0.133 |
Neg logit contributions | |
mate | -0.102 |
them | -0.102 |
wreck | -0.088 |
polar | -0.088 |
tow | -0.086 |
Token | higher |
Token ID | 2440 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ages | +0.080 |
� | +0.078 |
cious | +0.076 |
aul | +0.075 |
Michelle | +0.073 |
Neg logit contributions | |
them | -0.053 |
puck | -0.046 |
hon | -0.046 |
mate | -0.046 |
wreck | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
� | +0.170 |
's | +0.151 |
ages | +0.148 |
aul | +0.142 |
cious | +0.138 |
Neg logit contributions | |
mate | -0.102 |
them | -0.101 |
wreck | -0.087 |
polar | -0.087 |
tow | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
� | +0.056 |
ages | +0.054 |
List | +0.051 |
decisions | +0.051 |
aul | +0.051 |
Neg logit contributions | |
them | -0.033 |
mate | -0.031 |
polar | -0.029 |
wreck | -0.029 |
tow | -0.028 |
Token | look |
Token ID | 804 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ages | +0.057 |
� | +0.057 |
aul | +0.052 |
aut | +0.052 |
's | +0.052 |
Neg logit contributions | |
them | -0.047 |
mate | -0.043 |
polar | -0.042 |
wreck | -0.040 |
tow | -0.040 |
Token | � |
Token ID | 6184 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
� | +0.022 |
ages | +0.019 |
's | +0.019 |
aul | +0.018 |
cious | +0.018 |
Neg logit contributions | |
them | -0.019 |
mate | -0.018 |
polar | -0.016 |
wreck | -0.016 |
tow | -0.016 |
Token | � |
Token ID | 95 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ages | +0.030 |
� | +0.029 |
's | +0.028 |
ups | +0.027 |
decisions | +0.027 |
Neg logit contributions | |
mate | -0.020 |
them | -0.018 |
inn | -0.018 |
wreck | -0.017 |
splash | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ages | +0.009 |
� | +0.009 |
decisions | +0.008 |
's | +0.008 |
bey | +0.008 |
Neg logit contributions | |
mate | -0.010 |
inn | -0.009 |
ramp | -0.009 |
them | -0.009 |
tow | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
decisions | +0.205 |
persever | +0.192 |
mindful | +0.189 |
List | +0.188 |
� | +0.187 |
Neg logit contributions | |
them | -0.158 |
room | -0.151 |
ramp | -0.149 |
mate | -0.147 |
tow | -0.142 |
Token | � |
Token ID | 250 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
� | +0.931 |
ages | +0.908 |
decisions | +0.859 |
's | +0.846 |
cious | +0.817 |
Neg logit contributions | |
them | -0.725 |
mate | -0.694 |
wreck | -0.685 |
ramp | -0.670 |
snowball | -0.658 |
Token | it |
Token ID | 340 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
mate | +0.014 |
them | +0.014 |
wreck | +0.013 |
polar | +0.013 |
ramp | +0.013 |
Neg logit contributions | |
� | -0.015 |
's | -0.013 |
ages | -0.012 |
aul | -0.012 |
cious | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
them | +0.086 |
match | +0.081 |
mate | +0.079 |
wreck | +0.077 |
splash | +0.076 |
Neg logit contributions | |
ages | -0.041 |
aul | -0.040 |
List | -0.038 |
cious | -0.037 |
assy | -0.036 |
Token | € |
Token ID | 26391 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
ages | +0.115 |
� | +0.115 |
cious | +0.107 |
decisions | +0.107 |
ups | +0.106 |
Neg logit contributions | |
mate | -0.139 |
inn | -0.126 |
them | -0.125 |
tow | -0.118 |
match | -0.115 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
decisions | +0.180 |
aul | +0.173 |
� | +0.172 |
List | +0.171 |
mindful | +0.169 |
Neg logit contributions | |
mate | -0.172 |
them | -0.169 |
tow | -0.165 |
room | -0.159 |
ramp | -0.158 |
Token | it |
Token ID | 340 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
them | +0.113 |
mate | +0.099 |
wreck | +0.089 |
polar | +0.088 |
snowball | +0.084 |
Neg logit contributions | |
� | -0.156 |
ages | -0.138 |
's | -0.135 |
aul | -0.133 |
cious | -0.132 |
Token | forever |
Token ID | 8097 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
them | +0.107 |
mate | +0.101 |
wreck | +0.090 |
captain | +0.087 |
polar | +0.086 |
Neg logit contributions | |
� | -0.151 |
ages | -0.133 |
cious | -0.130 |
aul | -0.130 |
's | -0.130 |
Token | � |
Token ID | 6184 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
them | +0.209 |
mate | +0.175 |
wreck | +0.167 |
control | +0.148 |
rock | +0.146 |
Neg logit contributions | |
� | -0.421 |
ages | -0.390 |
cious | -0.377 |
aul | -0.374 |
List | -0.373 |
Token | � |
Token ID | 95 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
mate | +0.029 |
them | +0.028 |
tow | +0.025 |
wreck | +0.025 |
inn | +0.025 |
Neg logit contributions | |
� | -0.033 |
's | -0.030 |
ages | -0.030 |
aul | -0.027 |
cious | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
mate | +0.048 |
them | +0.046 |
tow | +0.043 |
ramp | +0.042 |
inn | +0.042 |
Neg logit contributions | |
� | -0.038 |
ages | -0.034 |
's | -0.033 |
aul | -0.032 |
bey | -0.030 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.180 |
decisions | +0.172 |
aul | +0.170 |
ience | +0.164 |
persever | +0.163 |
Neg logit contributions | |
them | -0.123 |
mate | -0.120 |
ramp | -0.108 |
racer | -0.107 |
tow | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
� | +0.858 |
's | +0.754 |
ages | +0.746 |
cious | +0.686 |
aul | +0.680 |
Neg logit contributions | |
mate | -0.884 |
them | -0.857 |
wreck | -0.791 |
tow | -0.782 |
ramp | -0.782 |
Token | things |
Token ID | 1243 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
mate | +0.020 |
them | +0.020 |
tow | +0.018 |
inn | +0.017 |
wreck | +0.017 |
Neg logit contributions | |
� | -0.023 |
's | -0.021 |
ages | -0.021 |
aul | -0.019 |
cious | -0.019 |
Token | are |
Token ID | 389 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
� | +0.277 |
ages | +0.252 |
's | +0.246 |
aul | +0.239 |
cious | +0.238 |
Neg logit contributions | |
them | -0.190 |
mate | -0.184 |
wreck | -0.162 |
tow | -0.155 |
ramp | -0.151 |
Token | only |
Token ID | 691 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
� | +0.012 |
ages | +0.010 |
's | +0.010 |
aul | +0.010 |
cious | +0.010 |
Neg logit contributions | |
them | -0.010 |
mate | -0.010 |
wreck | -0.009 |
tow | -0.009 |
polar | -0.008 |
Token | available |
Token ID | 1695 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
them | +0.117 |
mate | +0.105 |
wreck | +0.094 |
polar | +0.091 |
match | +0.091 |
Neg logit contributions | |
� | -0.166 |
ages | -0.148 |
aul | -0.144 |
's | -0.144 |
cious | -0.141 |
Token | special |
Token ID | 2041 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
mate | +0.170 |
them | +0.163 |
polar | +0.145 |
ramp | +0.145 |
wreck | +0.144 |
Neg logit contributions | |
� | -0.166 |
's | -0.141 |
ages | -0.135 |
cious | -0.125 |
aul | -0.125 |
Token | taxi |
Token ID | 17536 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
� | +0.214 |
's | +0.190 |
ages | +0.176 |
decisions | +0.169 |
aul | +0.164 |
Neg logit contributions | |
mate | -0.141 |
them | -0.138 |
inn | -0.123 |
puck | -0.114 |
polar | -0.113 |
Token | � |
Token ID | 6184 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
mate | +0.185 |
them | +0.179 |
wreck | +0.160 |
tow | +0.159 |
polar | +0.156 |
Neg logit contributions | |
� | -0.296 |
ages | -0.262 |
aul | -0.259 |
's | -0.256 |
List | -0.247 |
Token | � |
Token ID | 95 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
� | +0.032 |
's | +0.028 |
ages | +0.027 |
aul | +0.026 |
cious | +0.025 |
Neg logit contributions | |
mate | -0.030 |
them | -0.029 |
wreck | -0.026 |
tow | -0.026 |
polar | -0.026 |
Token | € |
Token ID | 26391 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
� | +0.015 |
's | +0.013 |
ages | +0.013 |
aul | +0.012 |
cious | +0.011 |
Neg logit contributions | |
mate | -0.018 |
them | -0.018 |
tow | -0.017 |
wreck | -0.017 |
ramp | -0.016 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.208 |
decisions | +0.190 |
aul | +0.186 |
ience | +0.178 |
persever | +0.178 |
Neg logit contributions | |
them | -0.192 |
mate | -0.182 |
tow | -0.179 |
ramp | -0.175 |
wreck | -0.168 |
Token | � |
Token ID | 250 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
� | +0.997 |
's | +0.881 |
ages | +0.875 |
aul | +0.815 |
decisions | +0.814 |
Neg logit contributions | |
mate | -0.743 |
them | -0.738 |
wreck | -0.664 |
tow | -0.655 |
ramp | -0.651 |
Token | it |
Token ID | 340 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
mate | +0.005 |
them | +0.005 |
wreck | +0.005 |
polar | +0.005 |
tow | +0.005 |
Neg logit contributions | |
� | -0.006 |
's | -0.005 |
ages | -0.005 |
aul | -0.004 |
cious | -0.004 |
Token | fit |
Token ID | 4197 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
them | +0.083 |
mate | +0.080 |
wreck | +0.077 |
match | +0.077 |
tow | +0.076 |
Neg logit contributions | |
aul | -0.030 |
ages | -0.030 |
cious | -0.028 |
List | -0.025 |
decisions | -0.025 |
Token | three |
Token ID | 1115 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
them | +0.157 |
mate | +0.156 |
wreck | +0.133 |
polar | +0.132 |
tow | +0.130 |
Neg logit contributions | |
� | -0.217 |
's | -0.191 |
ages | -0.190 |
aul | -0.182 |
cious | -0.176 |
Token | people |
Token ID | 661 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
mate | +0.165 |
them | +0.156 |
wreck | +0.143 |
polar | +0.142 |
ramp | +0.141 |
Neg logit contributions | |
� | -0.232 |
's | -0.204 |
ages | -0.198 |
aul | -0.184 |
cious | -0.182 |
Token | my |
Token ID | 616 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
� | +0.055 |
's | +0.048 |
ages | +0.045 |
aul | +0.043 |
cious | +0.042 |
Neg logit contributions | |
mate | -0.040 |
them | -0.038 |
wreck | -0.035 |
ramp | -0.035 |
polar | -0.034 |
Token | planet |
Token ID | 5440 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
mate | +0.120 |
them | +0.119 |
wreck | +0.106 |
polar | +0.105 |
tow | +0.105 |
Neg logit contributions | |
� | -0.154 |
's | -0.134 |
ages | -0.130 |
aul | -0.124 |
cious | -0.121 |
Token | � |
Token ID | 6184 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
� | +0.050 |
's | +0.043 |
ages | +0.042 |
aul | +0.040 |
cious | +0.039 |
Neg logit contributions | |
mate | -0.036 |
them | -0.035 |
wreck | -0.031 |
polar | -0.031 |
tow | -0.031 |
Token | � |
Token ID | 95 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
� | +0.026 |
ages | +0.024 |
's | +0.023 |
aul | +0.021 |
decisions | +0.021 |
Neg logit contributions | |
mate | -0.028 |
them | -0.027 |
wreck | -0.025 |
tow | -0.025 |
polar | -0.025 |
Token | € |
Token ID | 26391 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
� | +0.012 |
ages | +0.011 |
's | +0.011 |
decisions | +0.011 |
bey | +0.010 |
Neg logit contributions | |
mate | -0.015 |
them | -0.014 |
tow | -0.014 |
wreck | -0.014 |
ramp | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
decisions | +0.218 |
� | +0.218 |
aul | +0.210 |
persever | +0.208 |
ience | +0.206 |
Neg logit contributions | |
them | -0.149 |
mate | -0.147 |
ramp | -0.139 |
tow | -0.137 |
racer | -0.133 |
Token | � |
Token ID | 250 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
� | +0.830 |
ages | +0.766 |
's | +0.743 |
decisions | +0.709 |
cious | +0.692 |
Neg logit contributions | |
mate | -0.858 |
them | -0.851 |
wreck | -0.789 |
ramp | -0.784 |
tow | -0.779 |
Token | let |
Token ID | 1309 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
mate | +0.014 |
them | +0.013 |
wreck | +0.012 |
polar | +0.012 |
tow | +0.012 |
Neg logit contributions | |
� | -0.015 |
's | -0.013 |
ages | -0.012 |
aul | -0.012 |
cious | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ages | +0.030 |
aul | +0.026 |
List | +0.022 |
cious | +0.021 |
� | +0.021 |
Neg logit contributions | |
them | -0.185 |
mate | -0.175 |
polar | -0.159 |
tow | -0.159 |
his | -0.158 |
Token | € |
Token ID | 26391 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
� | +0.113 |
ages | +0.109 |
's | +0.104 |
aul | +0.102 |
cious | +0.100 |
Neg logit contributions | |
mate | -0.151 |
them | -0.137 |
inn | -0.134 |
tow | -0.131 |
wreck | -0.131 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
aul | +0.196 |
decisions | +0.187 |
mindful | +0.185 |
� | +0.184 |
ience | +0.183 |
Neg logit contributions | |
them | -0.173 |
mate | -0.172 |
tow | -0.166 |
racer | -0.161 |
ramp | -0.156 |
Token | lovely |
Token ID | 14081 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
mate | +0.166 |
them | +0.153 |
inn | +0.144 |
ramp | +0.141 |
tow | +0.141 |
Neg logit contributions | |
� | -0.185 |
's | -0.160 |
ages | -0.149 |
aul | -0.143 |
decisions | -0.142 |
Token | things |
Token ID | 1243 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
� | +0.006 |
's | +0.005 |
ages | +0.005 |
aul | +0.005 |
cious | +0.005 |
Neg logit contributions | |
them | -0.005 |
mate | -0.005 |
polar | -0.004 |
wreck | -0.004 |
tow | -0.004 |
Token | � |
Token ID | 6184 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
� | +0.287 |
ages | +0.260 |
's | +0.252 |
aul | +0.249 |
cious | +0.239 |
Neg logit contributions | |
them | -0.203 |
mate | -0.185 |
wreck | -0.165 |
tow | -0.161 |
polar | -0.160 |
Token | � |
Token ID | 95 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
� | +0.018 |
ages | +0.017 |
's | +0.017 |
decisions | +0.016 |
aul | +0.015 |
Neg logit contributions | |
mate | -0.014 |
them | -0.014 |
ramp | -0.013 |
tow | -0.013 |
inn | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
� | +0.005 |
ages | +0.005 |
decisions | +0.004 |
bey | +0.004 |
aul | +0.004 |
Neg logit contributions | |
mate | -0.005 |
them | -0.005 |
tow | -0.005 |
ramp | -0.005 |
room | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
decisions | +0.178 |
� | +0.174 |
persever | +0.170 |
aul | +0.167 |
dedication | +0.162 |
Neg logit contributions | |
them | -0.187 |
mate | -0.171 |
room | -0.163 |
ramp | -0.161 |
tow | -0.157 |
Token | � |
Token ID | 251 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
� | +1.144 |
ages | +1.048 |
's | +1.036 |
decisions | +1.015 |
pays | +0.967 |
Neg logit contributions | |
them | -0.565 |
mate | -0.553 |
wreck | -0.489 |
ramp | -0.482 |
tow | -0.473 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
� | +0.033 |
ages | +0.033 |
ience | +0.031 |
aul | +0.031 |
decisions | +0.030 |
Neg logit contributions | |
them | -0.026 |
mate | -0.021 |
his | -0.020 |
polar | -0.019 |
tow | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
� | +0.110 |
's | +0.094 |
ages | +0.090 |
aul | +0.086 |
cious | +0.085 |
Neg logit contributions | |
them | -0.094 |
mate | -0.093 |
wreck | -0.081 |
inn | -0.081 |
ramp | -0.079 |
Token | slide |
Token ID | 10649 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
mate | +0.054 |
them | +0.052 |
inn | +0.046 |
wreck | +0.045 |
ramp | +0.045 |
Neg logit contributions | |
� | -0.068 |
's | -0.059 |
ages | -0.052 |
aul | -0.052 |
ience | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
mate | +0.007 |
them | +0.007 |
polar | +0.006 |
wreck | +0.006 |
tow | +0.006 |
Neg logit contributions | |
� | -0.009 |
's | -0.008 |
ages | -0.008 |
aul | -0.007 |
cious | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
� | +0.040 |
's | +0.035 |
ages | +0.035 |
aul | +0.033 |
cious | +0.032 |
Neg logit contributions | |
mate | -0.030 |
them | -0.030 |
wreck | -0.027 |
polar | -0.027 |
tow | -0.026 |
Token | forgot |
Token ID | 16453 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
� | +0.006 |
's | +0.005 |
ages | +0.005 |
aul | +0.005 |
cious | +0.005 |
Neg logit contributions | |
mate | -0.005 |
them | -0.005 |
ramp | -0.005 |
snowball | -0.005 |
polar | -0.005 |
Token | � |
Token ID | 6184 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
� | +0.273 |
ages | +0.246 |
's | +0.239 |
aul | +0.236 |
cious | +0.231 |
Neg logit contributions | |
them | -0.163 |
mate | -0.150 |
wreck | -0.134 |
polar | -0.130 |
tow | -0.129 |
Token | � |
Token ID | 95 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
� | +0.025 |
's | +0.022 |
ages | +0.022 |
aul | +0.020 |
decisions | +0.019 |
Neg logit contributions | |
mate | -0.024 |
them | -0.024 |
wreck | -0.022 |
tow | -0.021 |
ramp | -0.021 |
Token | € |
Token ID | 26391 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
� | +0.008 |
ages | +0.007 |
bey | +0.007 |
aul | +0.007 |
decisions | +0.007 |
Neg logit contributions | |
mate | -0.008 |
them | -0.008 |
wreck | -0.007 |
tow | -0.007 |
ramp | -0.007 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.167 |
decisions | +0.162 |
aul | +0.159 |
persever | +0.158 |
List | +0.153 |
Neg logit contributions | |
them | -0.194 |
ramp | -0.177 |
mate | -0.175 |
wreck | -0.174 |
room | -0.173 |
Token | � |
Token ID | 250 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
� | +1.049 |
ages | +0.959 |
's | +0.945 |
decisions | +0.927 |
cious | +0.891 |
Neg logit contributions | |
mate | -0.650 |
them | -0.647 |
wreck | -0.592 |
ramp | -0.576 |
tow | -0.563 |
Token | they |
Token ID | 484 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
mate | +0.014 |
them | +0.014 |
polar | +0.012 |
wreck | +0.012 |
tow | +0.012 |
Neg logit contributions | |
� | -0.014 |
's | -0.011 |
ages | -0.011 |
aul | -0.010 |
cious | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
� | +0.159 |
ages | +0.154 |
aul | +0.150 |
cious | +0.146 |
List | +0.143 |
Neg logit contributions | |
them | -0.123 |
mate | -0.119 |
wreck | -0.110 |
match | -0.103 |
tow | -0.100 |
Token | supposed |
Token ID | 4385 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
them | +0.141 |
mate | +0.128 |
wreck | +0.122 |
polar | +0.117 |
tow | +0.115 |
Neg logit contributions | |
� | -0.181 |
ages | -0.167 |
aul | -0.161 |
's | -0.158 |
bey | -0.155 |
Token | to |
Token ID | 284 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
� | +0.188 |
ages | +0.169 |
aul | +0.165 |
's | +0.164 |
cious | +0.159 |
Neg logit contributions | |
them | -0.124 |
mate | -0.116 |
wreck | -0.106 |
tow | -0.099 |
polar | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
them | +0.059 |
mate | +0.057 |
wreck | +0.053 |
polar | +0.051 |
snowball | +0.051 |
Neg logit contributions | |
� | -0.088 |
aul | -0.086 |
ages | -0.085 |
cious | -0.082 |
decisions | -0.080 |
Token | too |
Token ID | 1165 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
mate | +0.030 |
them | +0.028 |
ramp | +0.026 |
wreck | +0.026 |
polar | +0.026 |
Neg logit contributions | |
� | -0.042 |
's | -0.036 |
ages | -0.034 |
aul | -0.032 |
pays | -0.032 |
Token | late |
Token ID | 2739 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
them | +0.240 |
snowball | +0.231 |
wreck | +0.228 |
polar | +0.224 |
tow | +0.216 |
Neg logit contributions | |
� | -0.220 |
's | -0.201 |
ages | -0.200 |
cious | -0.194 |
aul | -0.188 |
Token | â |
Token ID | 22940 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
� | +0.418 |
ages | +0.381 |
's | +0.371 |
aul | +0.369 |
cious | +0.358 |
Neg logit contributions | |
them | -0.232 |
mate | -0.210 |
wreck | -0.173 |
polar | -0.167 |
tow | -0.165 |
Token | € |
Token ID | 26391 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
� | +0.110 |
ages | +0.102 |
's | +0.101 |
ups | +0.099 |
decisions | +0.098 |
Neg logit contributions | |
mate | -0.134 |
inn | -0.127 |
them | -0.120 |
wreck | -0.118 |
ramp | -0.118 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.171 |
decisions | +0.159 |
aul | +0.156 |
ience | +0.155 |
persever | +0.155 |
Neg logit contributions | |
them | -0.180 |
mate | -0.173 |
ramp | -0.169 |
puck | -0.163 |
tow | -0.162 |
Token | � |
Token ID | 251 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
� | +1.177 |
's | +1.078 |
ages | +1.071 |
decisions | +1.030 |
cious | +1.028 |
Neg logit contributions | |
mate | -0.531 |
them | -0.526 |
wreck | -0.472 |
ramp | -0.463 |
tow | -0.444 |
Token | the |
Token ID | 262 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
� | +0.027 |
ages | +0.025 |
's | +0.024 |
aul | +0.024 |
cious | +0.023 |
Neg logit contributions | |
them | -0.021 |
mate | -0.020 |
polar | -0.017 |
tow | -0.017 |
wreck | -0.017 |
Token | ice |
Token ID | 4771 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
� | +0.064 |
's | +0.057 |
ages | +0.057 |
aul | +0.054 |
cious | +0.052 |
Neg logit contributions | |
mate | -0.041 |
them | -0.040 |
polar | -0.037 |
wreck | -0.037 |
tow | -0.036 |
Token | melted |
Token ID | 24178 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
mate | +0.050 |
them | +0.050 |
wreck | +0.045 |
polar | +0.044 |
tow | +0.043 |
Neg logit contributions | |
� | -0.075 |
's | -0.065 |
ages | -0.063 |
aul | -0.061 |
cious | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
� | +0.010 |
's | +0.009 |
ages | +0.008 |
aul | +0.008 |
decisions | +0.008 |
Neg logit contributions | |
mate | -0.007 |
them | -0.006 |
tow | -0.006 |
wreck | -0.006 |
polar | -0.006 |
Token | something |
Token ID | 1223 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
mate | +0.234 |
them | +0.233 |
wreck | +0.208 |
polar | +0.208 |
tow | +0.207 |
Neg logit contributions | |
� | -0.263 |
's | -0.227 |
ages | -0.222 |
aul | -0.210 |
cious | -0.204 |
Token | incredible |
Token ID | 8082 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
� | +0.302 |
's | +0.261 |
ages | +0.242 |
aul | +0.230 |
cious | +0.226 |
Neg logit contributions | |
mate | -0.256 |
them | -0.246 |
polar | -0.227 |
wreck | -0.224 |
tow | -0.224 |
Token | � |
Token ID | 6184 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
� | +0.001 |
ages | +0.001 |
's | +0.001 |
aul | +0.001 |
cious | +0.001 |
Neg logit contributions | |
them | -0.001 |
mate | -0.001 |
wreck | -0.001 |
polar | -0.001 |
tow | -0.001 |
Token | � |
Token ID | 95 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
� | +0.034 |
ages | +0.033 |
's | +0.031 |
decisions | +0.030 |
bey | +0.029 |
Neg logit contributions | |
mate | -0.027 |
them | -0.025 |
ramp | -0.024 |
wreck | -0.024 |
tow | -0.024 |
Token | € |
Token ID | 26391 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
� | +0.013 |
ages | +0.013 |
bey | +0.012 |
decisions | +0.012 |
aul | +0.012 |
Neg logit contributions | |
mate | -0.016 |
them | -0.014 |
ramp | -0.014 |
tow | -0.014 |
inn | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
decisions | +0.196 |
persever | +0.184 |
aul | +0.184 |
� | +0.183 |
ience | +0.180 |
Neg logit contributions | |
them | -0.169 |
mate | -0.152 |
ramp | -0.148 |
room | -0.148 |
tow | -0.142 |
Token | � |
Token ID | 250 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ages | +1.109 |
decisions | +1.104 |
� | +1.094 |
's | +1.029 |
mindful | +1.018 |
Neg logit contributions | |
them | -0.513 |
mate | -0.496 |
ramp | -0.451 |
tow | -0.430 |
snowball | -0.426 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
mate | +0.016 |
them | +0.016 |
tow | +0.014 |
polar | +0.014 |
wreck | +0.014 |
Neg logit contributions | |
� | -0.017 |
's | -0.015 |
ages | -0.015 |
aul | -0.014 |
decisions | -0.013 |
Token | magical |
Token ID | 10883 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
� | +0.111 |
's | +0.095 |
ages | +0.090 |
cious | +0.087 |
aul | +0.087 |
Neg logit contributions | |
them | -0.079 |
mate | -0.078 |
inn | -0.067 |
tow | -0.067 |
wreck | -0.066 |
Token | plant |
Token ID | 4618 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
� | +0.214 |
's | +0.188 |
ages | +0.179 |
aul | +0.172 |
cious | +0.168 |
Neg logit contributions | |
them | -0.145 |
mate | -0.144 |
wreck | -0.125 |
polar | -0.124 |
tow | -0.124 |
Token | ! |
Token ID | 0 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
� | +0.370 |
ages | +0.357 |
List | +0.336 |
aul | +0.332 |
's | +0.328 |
Neg logit contributions | |
mate | -0.269 |
them | -0.269 |
wreck | -0.226 |
tow | -0.221 |
polar | -0.219 |
Token | her |
Token ID | 607 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
them | +0.019 |
mate | +0.018 |
wreck | +0.016 |
tow | +0.016 |
polar | +0.016 |
Neg logit contributions | |
� | -0.018 |
aul | -0.016 |
ages | -0.016 |
's | -0.015 |
cious | -0.015 |
Token | peace |
Token ID | 4167 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
mate | +0.078 |
them | +0.077 |
wreck | +0.067 |
polar | +0.067 |
tow | +0.066 |
Neg logit contributions | |
� | -0.135 |
's | -0.120 |
ages | -0.117 |
aul | -0.112 |
cious | -0.109 |
Token | � |
Token ID | 6184 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
� | +0.349 |
's | +0.305 |
ages | +0.299 |
aul | +0.286 |
cious | +0.278 |
Neg logit contributions | |
mate | -0.250 |
them | -0.248 |
wreck | -0.218 |
polar | -0.217 |
tow | -0.215 |
Token | � |
Token ID | 95 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
� | +0.011 |
ages | +0.010 |
's | +0.010 |
decisions | +0.009 |
aul | +0.009 |
Neg logit contributions | |
mate | -0.012 |
them | -0.011 |
inn | -0.010 |
tow | -0.010 |
wreck | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
mate | +0.004 |
them | +0.004 |
tow | +0.003 |
inn | +0.003 |
ramp | +0.003 |
Neg logit contributions | |
� | -0.003 |
ages | -0.003 |
's | -0.003 |
aul | -0.003 |
decisions | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.200 |
decisions | +0.190 |
aul | +0.184 |
ages | +0.180 |
pays | +0.177 |
Neg logit contributions | |
them | -0.146 |
mate | -0.141 |
tow | -0.126 |
ramp | -0.124 |
racer | -0.120 |
Token | � |
Token ID | 250 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
� | +0.819 |
's | +0.718 |
ages | +0.714 |
decisions | +0.652 |
cious | +0.649 |
Neg logit contributions | |
mate | -0.910 |
them | -0.891 |
wreck | -0.817 |
tow | -0.811 |
ramp | -0.811 |
Token | she |
Token ID | 673 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
mate | +0.019 |
them | +0.019 |
tow | +0.017 |
inn | +0.016 |
wreck | +0.016 |
Neg logit contributions | |
� | -0.019 |
's | -0.017 |
ages | -0.017 |
aul | -0.016 |
cious | -0.015 |
Token | just |
Token ID | 655 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
aul | +0.230 |
� | +0.226 |
ages | +0.223 |
cious | +0.222 |
Michelle | +0.217 |
Neg logit contributions | |
them | -0.223 |
mate | -0.219 |
wreck | -0.199 |
match | -0.195 |
tow | -0.192 |
Token | needs |
Token ID | 2476 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
them | +0.034 |
mate | +0.032 |
wreck | +0.030 |
polar | +0.028 |
tow | +0.028 |
Neg logit contributions | |
� | -0.047 |
ages | -0.045 |
aul | -0.044 |
cious | -0.043 |
's | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
� | +0.239 |
's | +0.208 |
ages | +0.202 |
aul | +0.192 |
cious | +0.187 |
Neg logit contributions | |
mate | -0.189 |
them | -0.186 |
wreck | -0.167 |
polar | -0.167 |
tow | -0.165 |
Token | a |
Token ID | 257 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
them | +0.040 |
mate | +0.037 |
wreck | +0.034 |
polar | +0.033 |
tow | +0.032 |
Neg logit contributions | |
� | -0.060 |
ages | -0.054 |
's | -0.053 |
cious | -0.051 |
aul | -0.050 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
� | +0.091 |
's | +0.079 |
aul | +0.066 |
cious | +0.065 |
ages | +0.062 |
Neg logit contributions | |
them | -0.096 |
mate | -0.092 |
inn | -0.088 |
room | -0.085 |
ramp | -0.083 |
Token | penny |
Token ID | 26369 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
mate | +0.103 |
them | +0.103 |
polar | +0.091 |
tow | +0.090 |
ramp | +0.090 |
Neg logit contributions | |
� | -0.118 |
's | -0.103 |
ages | -0.096 |
aul | -0.093 |
decisions | -0.090 |
Token | â |
Token ID | 22940 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
� | +0.031 |
ages | +0.027 |
aul | +0.026 |
's | +0.026 |
List | +0.026 |
Neg logit contributions | |
mate | -0.018 |
them | -0.018 |
wreck | -0.016 |
polar | -0.015 |
ramp | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
� | +0.117 |
ages | +0.109 |
ience | +0.105 |
decisions | +0.104 |
ups | +0.102 |
Neg logit contributions | |
mate | -0.134 |
inn | -0.126 |
them | -0.119 |
room | -0.115 |
match | -0.115 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
� | +0.176 |
decisions | +0.149 |
List | +0.143 |
mindful | +0.141 |
ience | +0.141 |
Neg logit contributions | |
them | -0.211 |
mate | -0.211 |
tow | -0.196 |
ramp | -0.191 |
wreck | -0.190 |
Token | � |
Token ID | 251 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
� | +1.140 |
's | +1.010 |
ages | +0.999 |
decisions | +0.952 |
cious | +0.938 |
Neg logit contributions | |
mate | -0.607 |
them | -0.601 |
wreck | -0.527 |
ramp | -0.517 |
tow | -0.509 |
Token | it |
Token ID | 270 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
� | +0.035 |
ages | +0.031 |
's | +0.030 |
aul | +0.029 |
pays | +0.029 |
Neg logit contributions | |
them | -0.023 |
mate | -0.021 |
polar | -0.019 |
tow | -0.019 |
wreck | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
� | +0.066 |
's | +0.056 |
ages | +0.055 |
aul | +0.053 |
cious | +0.051 |
Neg logit contributions | |
mate | -0.057 |
them | -0.057 |
wreck | -0.051 |
polar | -0.051 |
tow | -0.050 |
Token | special |
Token ID | 2041 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
mate | +0.020 |
them | +0.019 |
wreck | +0.017 |
ramp | +0.017 |
tow | +0.017 |
Neg logit contributions | |
� | -0.020 |
's | -0.017 |
ages | -0.016 |
aul | -0.015 |
cious | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
� | +0.186 |
's | +0.161 |
ages | +0.158 |
aul | +0.150 |
cious | +0.146 |
Neg logit contributions | |
mate | -0.147 |
them | -0.146 |
wreck | -0.130 |
polar | -0.130 |
tow | -0.128 |
Token | set |
Token ID | 900 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
� | +0.041 |
's | +0.036 |
ages | +0.035 |
aul | +0.033 |
cious | +0.032 |
Neg logit contributions | |
mate | -0.033 |
them | -0.032 |
wreck | -0.030 |
polar | -0.029 |
snowball | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
mate | +0.140 |
them | +0.138 |
wreck | +0.123 |
polar | +0.123 |
tow | +0.121 |
Neg logit contributions | |
� | -0.189 |
's | -0.165 |
ages | -0.161 |
aul | -0.153 |
cious | -0.149 |
Token | colorful |
Token ID | 20239 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
� | +0.091 |
's | +0.080 |
ages | +0.075 |
aul | +0.071 |
decisions | +0.070 |
Neg logit contributions | |
mate | -0.065 |
ramp | -0.057 |
wreck | -0.056 |
polar | -0.055 |
them | -0.055 |
Token | patterns |
Token ID | 7572 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
mate | +0.095 |
them | +0.094 |
wreck | +0.084 |
polar | +0.084 |
tow | +0.083 |
Neg logit contributions | |
� | -0.107 |
's | -0.093 |
ages | -0.090 |
aul | -0.086 |
cious | -0.083 |
Token | on |
Token ID | 319 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
� | +0.040 |
's | +0.035 |
ages | +0.033 |
aul | +0.031 |
cious | +0.031 |
Neg logit contributions | |
mate | -0.033 |
them | -0.031 |
polar | -0.030 |
wreck | -0.030 |
tow | -0.029 |
Token | them |
Token ID | 606 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
mate | +0.049 |
polar | +0.048 |
wreck | +0.045 |
ramp | +0.044 |
snowball | +0.043 |
Neg logit contributions | |
� | -0.060 |
's | -0.052 |
aul | -0.043 |
Michelle | -0.043 |
pays | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
them | +0.339 |
mate | +0.321 |
wreck | +0.268 |
tow | +0.265 |
ramp | +0.256 |
Neg logit contributions | |
� | -0.561 |
ages | -0.496 |
's | -0.486 |
aul | -0.486 |
List | -0.475 |
Token | |
Token ID | 220 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
� | +0.030 |
ages | +0.027 |
's | +0.025 |
aul | +0.025 |
ience | +0.024 |
Neg logit contributions | |
them | -0.028 |
mate | -0.025 |
tow | -0.024 |
inn | -0.023 |
polar | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
� | +0.083 |
's | +0.072 |
ages | +0.072 |
ience | +0.069 |
aul | +0.069 |
Neg logit contributions | |
them | -0.065 |
mate | -0.061 |
tow | -0.054 |
inn | -0.053 |
ramp | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
� | +0.034 |
's | +0.029 |
ages | +0.025 |
aul | +0.025 |
List | +0.024 |
Neg logit contributions | |
mate | -0.039 |
wreck | -0.036 |
polar | -0.036 |
them | -0.036 |
ramp | -0.034 |
Token | At |
Token ID | 2953 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
� | +0.037 |
's | +0.031 |
ages | +0.031 |
aul | +0.029 |
cious | +0.028 |
Neg logit contributions | |
mate | -0.035 |
them | -0.034 |
wreck | -0.031 |
polar | -0.031 |
tow | -0.031 |
Token | Jake |
Token ID | 14757 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
mate | +0.177 |
them | +0.176 |
polar | +0.157 |
wreck | +0.156 |
tow | +0.156 |
Neg logit contributions | |
� | -0.201 |
's | -0.174 |
ages | -0.171 |
aul | -0.161 |
cious | -0.157 |
Token | said |
Token ID | 531 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
them | +0.049 |
mate | +0.047 |
inn | +0.042 |
wreck | +0.041 |
polar | +0.040 |
Neg logit contributions | |
� | -0.055 |
ages | -0.050 |
decisions | -0.048 |
aul | -0.047 |
cious | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
� | +0.007 |
's | +0.006 |
ages | +0.006 |
aul | +0.005 |
decisions | +0.005 |
Neg logit contributions | |
mate | -0.005 |
them | -0.004 |
tow | -0.004 |
polar | -0.004 |
wreck | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
� | +0.045 |
's | +0.040 |
ages | +0.039 |
aul | +0.038 |
cious | +0.037 |
Neg logit contributions | |
them | -0.029 |
mate | -0.029 |
polar | -0.025 |
wreck | -0.025 |
tow | -0.024 |
Token | Yes |
Token ID | 5297 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
mate | +0.097 |
them | +0.097 |
wreck | +0.092 |
polar | +0.091 |
ramp | +0.088 |
Neg logit contributions | |
� | -0.125 |
's | -0.103 |
ages | -0.100 |
aul | -0.095 |
cious | -0.094 |
Token | please |
Token ID | 3387 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
wreck | +0.128 |
mate | +0.128 |
polar | +0.125 |
them | +0.122 |
ramp | +0.120 |
Neg logit contributions | |
� | -0.165 |
's | -0.142 |
ages | -0.119 |
ience | -0.118 |
aul | -0.118 |
Token | ! |
Token ID | 0 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
mate | +0.318 |
them | +0.313 |
wreck | +0.268 |
polar | +0.267 |
tow | +0.266 |
Neg logit contributions | |
� | -0.559 |
's | -0.495 |
ages | -0.485 |
aul | -0.466 |
cious | -0.456 |
Token | But |
Token ID | 887 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
mate | +0.077 |
them | +0.075 |
tow | +0.070 |
polar | +0.068 |
ramp | +0.067 |
Neg logit contributions | |
� | -0.059 |
ages | -0.053 |
's | -0.053 |
aul | -0.051 |
cious | -0.049 |
Token | I |
Token ID | 314 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
� | +0.056 |
ages | +0.051 |
's | +0.049 |
aul | +0.047 |
cious | +0.047 |
Neg logit contributions | |
them | -0.039 |
mate | -0.039 |
wreck | -0.034 |
polar | -0.033 |
tow | -0.033 |
Token | 'd |
Token ID | 1549 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
� | +0.209 |
ages | +0.184 |
's | +0.183 |
aul | +0.175 |
cious | +0.172 |
Neg logit contributions | |
them | -0.169 |
mate | -0.168 |
wreck | -0.151 |
polar | -0.148 |
tow | -0.148 |
Token | like |
Token ID | 588 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
mate | +0.149 |
them | +0.143 |
polar | +0.129 |
tow | +0.128 |
wreck | +0.128 |
Neg logit contributions | |
� | -0.220 |
's | -0.194 |
ages | -0.185 |
aul | -0.176 |
cious | -0.172 |
Token | play |
Token ID | 711 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
� | +0.034 |
's | +0.030 |
ages | +0.028 |
aul | +0.027 |
cious | +0.027 |
Neg logit contributions | |
mate | -0.016 |
them | -0.015 |
inn | -0.013 |
polar | -0.013 |
wreck | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
tow | +0.230 |
polar | +0.226 |
spoiler | +0.212 |
wreck | +0.210 |
mate | +0.207 |
Neg logit contributions | |
's | -0.194 |
� | -0.177 |
ages | -0.141 |
aut | -0.132 |
aul | -0.131 |
Token | toy |
Token ID | 13373 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
� | +0.086 |
's | +0.081 |
ages | +0.075 |
aul | +0.073 |
cious | +0.070 |
Neg logit contributions | |
mate | -0.051 |
them | -0.041 |
inn | -0.041 |
tow | -0.040 |
ramp | -0.039 |
Token | soldiers |
Token ID | 5795 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
mate | +0.143 |
tow | +0.137 |
inn | +0.132 |
polar | +0.127 |
them | +0.121 |
Neg logit contributions | |
� | -0.264 |
's | -0.264 |
ages | -0.235 |
aul | -0.221 |
ups | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
mate | +0.176 |
them | +0.166 |
polar | +0.165 |
tow | +0.162 |
wreck | +0.161 |
Neg logit contributions | |
� | -0.193 |
's | -0.177 |
ages | -0.159 |
aul | -0.147 |
cious | -0.142 |
Token | pretend |
Token ID | 16614 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
� | +0.035 |
's | +0.032 |
ages | +0.029 |
pays | +0.028 |
cious | +0.027 |
Neg logit contributions | |
mate | -0.020 |
inn | -0.018 |
them | -0.017 |
polar | -0.016 |
snowball | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
mate | +0.404 |
them | +0.380 |
polar | +0.362 |
inn | +0.360 |
tow | +0.359 |
Neg logit contributions | |
� | -0.384 |
's | -0.338 |
ages | -0.319 |
aul | -0.291 |
cious | -0.285 |
Token | were |
Token ID | 547 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
� | +0.104 |
's | +0.096 |
ages | +0.080 |
pays | +0.077 |
cious | +0.074 |
Neg logit contributions | |
mate | -0.098 |
inn | -0.090 |
snowball | -0.089 |
them | -0.087 |
ramp | -0.086 |
Token | in |
Token ID | 287 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
mate | +0.147 |
them | +0.132 |
inn | +0.129 |
ramp | +0.124 |
tow | +0.123 |
Neg logit contributions | |
� | -0.260 |
's | -0.242 |
ages | -0.227 |
aul | -0.209 |
cious | -0.208 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
� | +0.022 |
's | +0.019 |
decisions | +0.015 |
List | +0.015 |
pays | +0.015 |
Neg logit contributions | |
mate | -0.026 |
inn | -0.024 |
polar | -0.022 |
wreck | -0.022 |
ramp | -0.022 |
Token | war |
Token ID | 1175 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
� | +0.080 |
's | +0.078 |
cious | +0.056 |
ience | +0.056 |
ages | +0.053 |
Neg logit contributions | |
mate | -0.062 |
icle | -0.061 |
inn | -0.060 |
them | -0.058 |
uit | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
them | +0.088 |
mate | +0.085 |
wreck | +0.074 |
tow | +0.072 |
polar | +0.072 |
Neg logit contributions | |
� | -0.130 |
ages | -0.113 |
's | -0.113 |
aul | -0.109 |
cious | -0.106 |
Token | pe |
Token ID | 613 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
� | +0.004 |
aul | +0.003 |
's | +0.003 |
ages | +0.003 |
decisions | +0.003 |
Neg logit contributions | |
them | -0.003 |
mate | -0.003 |
polar | -0.002 |
wreck | -0.002 |
tow | -0.002 |
Token | ck |
Token ID | 694 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
� | +0.004 |
ages | +0.003 |
's | +0.003 |
bey | +0.003 |
cious | +0.003 |
Neg logit contributions | |
mate | -0.003 |
them | -0.003 |
tow | -0.003 |
wreck | -0.003 |
ramp | -0.003 |
Token | ed |
Token ID | 276 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
them | +0.073 |
mate | +0.073 |
polar | +0.067 |
wreck | +0.067 |
tow | +0.066 |
Neg logit contributions | |
� | -0.044 |
's | -0.035 |
ages | -0.034 |
aul | -0.032 |
cious | -0.030 |
Token | at |
Token ID | 379 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
� | +0.255 |
's | +0.228 |
ages | +0.212 |
aul | +0.202 |
cious | +0.198 |
Neg logit contributions | |
mate | -0.169 |
them | -0.152 |
wreck | -0.151 |
ramp | -0.150 |
polar | -0.149 |
Token | them |
Token ID | 606 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
� | +0.112 |
's | +0.103 |
Michelle | +0.096 |
aul | +0.092 |
pays | +0.090 |
Neg logit contributions | |
mate | -0.052 |
ramp | -0.049 |
inn | -0.046 |
polar | -0.045 |
puck | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
them | +0.360 |
mate | +0.346 |
wreck | +0.296 |
tow | +0.288 |
ramp | +0.284 |
Neg logit contributions | |
� | -0.588 |
ages | -0.527 |
aul | -0.512 |
's | -0.509 |
cious | -0.495 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
mate | +0.031 |
them | +0.030 |
wreck | +0.028 |
polar | +0.028 |
ramp | +0.027 |
Neg logit contributions | |
� | -0.031 |
's | -0.026 |
ages | -0.025 |
aul | -0.024 |
List | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
them | +0.085 |
mate | +0.082 |
wreck | +0.073 |
polar | +0.073 |
snowball | +0.072 |
Neg logit contributions | |
� | -0.144 |
ages | -0.127 |
aul | -0.124 |
decisions | -0.123 |
's | -0.122 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
� | +0.002 |
's | +0.002 |
ages | +0.002 |
cious | +0.002 |
aul | +0.002 |
Neg logit contributions | |
mate | -0.002 |
them | -0.002 |
wreck | -0.002 |
tow | -0.002 |
ramp | -0.002 |
Token | screamed |
Token ID | 25421 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
them | +0.076 |
mate | +0.076 |
wreck | +0.067 |
polar | +0.067 |
tow | +0.066 |
Neg logit contributions | |
� | -0.101 |
's | -0.087 |
ages | -0.087 |
aul | -0.083 |
cious | -0.080 |
Token | can |
Token ID | 460 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
� | +0.259 |
's | +0.221 |
ages | +0.195 |
aul | +0.183 |
bey | +0.180 |
Neg logit contributions | |
mate | -0.237 |
them | -0.220 |
polar | -0.217 |
ramp | -0.209 |
tow | -0.209 |
Token | smell |
Token ID | 8508 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
mate | +0.056 |
polar | +0.054 |
snowball | +0.051 |
tant | +0.049 |
ramp | +0.049 |
Neg logit contributions | |
� | -0.073 |
's | -0.063 |
ages | -0.050 |
aul | -0.050 |
bey | -0.049 |
Token | them |
Token ID | 606 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
mate | +0.015 |
ramp | +0.012 |
tow | +0.012 |
inn | +0.011 |
racer | +0.011 |
Neg logit contributions | |
� | -0.027 |
's | -0.025 |
aul | -0.023 |
decisions | -0.023 |
ages | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
them | +0.366 |
mate | +0.314 |
wreck | +0.269 |
polar | +0.262 |
captain | +0.262 |
Neg logit contributions | |
� | -0.609 |
ages | -0.552 |
aul | -0.523 |
's | -0.519 |
cious | -0.518 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
mate | +0.001 |
them | +0.001 |
wreck | +0.001 |
polar | +0.001 |
tow | +0.001 |
Neg logit contributions | |
� | -0.001 |
's | -0.001 |
ages | -0.001 |
aul | -0.001 |
cious | -0.001 |
Token | them |
Token ID | 606 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
� | +0.225 |
's | +0.210 |
ages | +0.197 |
aul | +0.195 |
decisions | +0.192 |
Neg logit contributions | |
mate | -0.031 |
ramp | -0.017 |
tow | -0.016 |
wreck | -0.015 |
inn | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
them | +0.352 |
mate | +0.318 |
wreck | +0.269 |
polar | +0.261 |
ramp | +0.260 |
Neg logit contributions | |
� | -0.614 |
ages | -0.551 |
's | -0.530 |
aul | -0.526 |
cious | -0.520 |
Token | but |
Token ID | 475 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
mate | +0.002 |
them | +0.002 |
tow | +0.002 |
polar | +0.002 |
wreck | +0.002 |
Neg logit contributions | |
� | -0.003 |
's | -0.003 |
ages | -0.002 |
aul | -0.002 |
cious | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
them | +0.178 |
mate | +0.171 |
wreck | +0.156 |
polar | +0.155 |
tow | +0.153 |
Neg logit contributions | |
� | -0.158 |
ages | -0.136 |
's | -0.132 |
aul | -0.127 |
cious | -0.123 |
Token | can |
Token ID | 460 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
� | +0.253 |
's | +0.220 |
ages | +0.212 |
aul | +0.202 |
cious | +0.196 |
Neg logit contributions | |
mate | -0.202 |
them | -0.198 |
polar | -0.178 |
wreck | -0.177 |
tow | -0.177 |
Token | 't |
Token ID | 470 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
mate | +0.059 |
polar | +0.053 |
snowball | +0.051 |
ramp | +0.051 |
them | +0.051 |
Neg logit contributions | |
� | -0.071 |
's | -0.061 |
ages | -0.053 |
aul | -0.052 |
cious | -0.050 |
Token | us |
Token ID | 514 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
� | +0.116 |
's | +0.106 |
ages | +0.105 |
aul | +0.102 |
cious | +0.101 |
Neg logit contributions | |
them | -0.018 |
mate | -0.015 |
polar | -0.009 |
wreck | -0.009 |
tow | -0.008 |
Token | our |
Token ID | 674 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
them | +0.142 |
mate | +0.133 |
polar | +0.119 |
wreck | +0.119 |
snowball | +0.115 |
Neg logit contributions | |
� | -0.174 |
ages | -0.150 |
's | -0.149 |
aul | -0.143 |
cious | -0.142 |
Token | coins |
Token ID | 10796 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
mate | +0.110 |
them | +0.099 |
inn | +0.098 |
ramp | +0.093 |
polar | +0.093 |
Neg logit contributions | |
� | -0.118 |
's | -0.107 |
ages | -0.101 |
aul | -0.095 |
decisions | -0.094 |
Token | back |
Token ID | 736 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
mate | +0.028 |
them | +0.028 |
polar | +0.025 |
wreck | +0.025 |
tow | +0.025 |
Neg logit contributions | |
� | -0.042 |
's | -0.037 |
ages | -0.036 |
aul | -0.034 |
cious | -0.033 |
Token | ." |
Token ID | 526 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
mate | +0.028 |
them | +0.027 |
wreck | +0.024 |
polar | +0.024 |
tow | +0.024 |
Neg logit contributions | |
� | -0.042 |
's | -0.037 |
ages | -0.036 |
aul | -0.035 |
cious | -0.034 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
them | +0.151 |
mate | +0.119 |
tow | +0.118 |
polar | +0.115 |
his | +0.112 |
Neg logit contributions | |
� | -0.214 |
ages | -0.207 |
's | -0.190 |
ience | -0.190 |
cious | -0.189 |
Token | says |
Token ID | 1139 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +0.000 |
ages | +0.000 |
cious | +0.000 |
aul | +0.000 |
's | +0.000 |
Neg logit contributions | |
them | -0.001 |
mate | -0.001 |
snowball | -0.001 |
polar | -0.001 |
wreck | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
� | +0.094 |
ages | +0.083 |
aul | +0.082 |
's | +0.081 |
cious | +0.079 |
Neg logit contributions | |
them | -0.052 |
mate | -0.048 |
tow | -0.039 |
polar | -0.038 |
wreck | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
mate | +0.085 |
wreck | +0.080 |
polar | +0.075 |
them | +0.074 |
ramp | +0.074 |
Neg logit contributions | |
� | -0.051 |
's | -0.041 |
ages | -0.035 |
List | -0.032 |
aul | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
mate | +0.020 |
wreck | +0.018 |
captain | +0.017 |
polar | +0.017 |
racer | +0.017 |
Neg logit contributions | |
� | -0.013 |
's | -0.011 |
ages | -0.009 |
aul | -0.009 |
List | -0.009 |
Token | They |
Token ID | 2990 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
mate | +0.014 |
them | +0.014 |
wreck | +0.013 |
polar | +0.013 |
tow | +0.012 |
Neg logit contributions | |
� | -0.016 |
's | -0.014 |
ages | -0.013 |
aul | -0.012 |
cious | -0.012 |
Token | back |
Token ID | 736 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
� | +0.003 |
's | +0.003 |
ages | +0.003 |
aul | +0.002 |
cious | +0.002 |
Neg logit contributions | |
mate | -0.003 |
them | -0.002 |
wreck | -0.002 |
ramp | -0.002 |
tow | -0.002 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
them | +0.043 |
mate | +0.042 |
polar | +0.037 |
wreck | +0.037 |
tow | +0.036 |
Neg logit contributions | |
� | -0.058 |
ages | -0.050 |
's | -0.050 |
aul | -0.048 |
cious | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
them | +0.053 |
mate | +0.050 |
wreck | +0.043 |
tow | +0.042 |
polar | +0.042 |
Neg logit contributions | |
� | -0.089 |
ages | -0.079 |
's | -0.078 |
aul | -0.076 |
cious | -0.075 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
them | +0.042 |
mate | +0.037 |
tow | +0.035 |
ramp | +0.031 |
polar | +0.030 |
Neg logit contributions | |
ages | -0.063 |
ience | -0.060 |
� | -0.058 |
decisions | -0.058 |
aul | -0.057 |
Token | L |
Token ID | 43 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
� | +0.038 |
ages | +0.034 |
's | +0.033 |
cious | +0.032 |
ience | +0.031 |
Neg logit contributions | |
them | -0.033 |
mate | -0.032 |
tow | -0.028 |
wreck | -0.028 |
polar | -0.028 |
Token | ily |
Token ID | 813 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
mate | +0.053 |
ramp | +0.049 |
wreck | +0.049 |
tow | +0.047 |
polar | +0.047 |
Neg logit contributions | |
� | -0.048 |
's | -0.043 |
aul | -0.039 |
ages | -0.037 |
bey | -0.036 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
them | +0.060 |
his | +0.049 |
polar | +0.048 |
rock | +0.047 |
wreck | +0.046 |
Neg logit contributions | |
� | -0.114 |
decisions | -0.113 |
ages | -0.113 |
cious | -0.108 |
List | -0.106 |
Token | to |
Token ID | 284 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
them | +0.094 |
mate | +0.092 |
wreck | +0.082 |
polar | +0.082 |
tow | +0.081 |
Neg logit contributions | |
� | -0.126 |
's | -0.110 |
ages | -0.108 |
aul | -0.102 |
cious | -0.100 |
Token | play |
Token ID | 711 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
� | +0.035 |
's | +0.030 |
ages | +0.027 |
aul | +0.026 |
cious | +0.026 |
Neg logit contributions | |
mate | -0.023 |
them | -0.021 |
inn | -0.020 |
polar | -0.020 |
wreck | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
tow | +0.224 |
polar | +0.221 |
crashing | +0.211 |
spoiler | +0.209 |
wreck | +0.205 |
Neg logit contributions | |
's | -0.187 |
� | -0.183 |
aul | -0.135 |
ages | -0.126 |
rawling | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
� | +0.057 |
's | +0.053 |
ages | +0.046 |
aul | +0.045 |
Michelle | +0.043 |
Neg logit contributions | |
mate | -0.072 |
ramp | -0.063 |
wreck | -0.062 |
inn | -0.062 |
captain | -0.062 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
� | +0.013 |
ages | +0.012 |
decisions | +0.012 |
aul | +0.011 |
List | +0.011 |
Neg logit contributions | |
them | -0.011 |
mate | -0.010 |
polar | -0.009 |
wreck | -0.009 |
captain | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
� | +0.171 |
ages | +0.151 |
's | +0.149 |
aul | +0.145 |
cious | +0.142 |
Neg logit contributions | |
them | -0.113 |
mate | -0.111 |
polar | -0.097 |
wreck | -0.095 |
tow | -0.095 |
Token | said |
Token ID | 531 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
� | +0.064 |
aul | +0.062 |
decisions | +0.061 |
ages | +0.058 |
lette | +0.057 |
Neg logit contributions | |
them | -0.047 |
his | -0.045 |
polar | -0.042 |
hon | -0.042 |
mate | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
� | +0.007 |
's | +0.006 |
ages | +0.006 |
aul | +0.006 |
cious | +0.006 |
Neg logit contributions | |
mate | -0.005 |
them | -0.005 |
wreck | -0.004 |
polar | -0.004 |
tow | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
� | +0.055 |
's | +0.048 |
ages | +0.048 |
aul | +0.046 |
cious | +0.044 |
Neg logit contributions | |
them | -0.033 |
mate | -0.033 |
tow | -0.028 |
polar | -0.028 |
wreck | -0.028 |
Token | It |
Token ID | 1026 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
mate | +0.109 |
them | +0.105 |
tow | +0.094 |
inn | +0.093 |
racer | +0.091 |
Neg logit contributions | |
� | -0.098 |
's | -0.093 |
ages | -0.093 |
decisions | -0.087 |
aul | -0.085 |
Token | 's |
Token ID | 338 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
them | +0.046 |
match | +0.043 |
mate | +0.043 |
bear | +0.041 |
zoom | +0.040 |
Neg logit contributions | |
cious | -0.029 |
aul | -0.029 |
oney | -0.026 |
assy | -0.026 |
enna | -0.026 |
Token | OK |
Token ID | 7477 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
� | +0.446 |
ages | +0.436 |
cious | +0.423 |
aul | +0.389 |
's | +0.387 |
Neg logit contributions | |
them | -0.738 |
mate | -0.703 |
snowball | -0.647 |
polar | -0.645 |
tow | -0.640 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
� | +0.355 |
's | +0.311 |
ages | +0.307 |
aul | +0.292 |
cious | +0.285 |
Neg logit contributions | |
mate | -0.250 |
them | -0.248 |
polar | -0.218 |
wreck | -0.217 |
tow | -0.215 |
Token | That |
Token ID | 1320 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
ages | +0.032 |
cious | +0.031 |
� | +0.031 |
aul | +0.029 |
's | +0.029 |
Neg logit contributions | |
mate | -0.034 |
tow | -0.032 |
them | -0.032 |
polar | -0.030 |
ramp | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
oney | +0.248 |
cious | +0.246 |
aul | +0.231 |
riet | +0.230 |
enna | +0.229 |
Neg logit contributions | |
snowball | -0.236 |
wreck | -0.228 |
rock | -0.227 |
mate | -0.222 |
lot | -0.222 |
Token | was |
Token ID | 373 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
mate | +0.000 |
them | +0.000 |
captain | +0.000 |
ramp | +0.000 |
polar | +0.000 |
Neg logit contributions | |
� | -0.000 |
's | -0.000 |
aul | -0.000 |
ages | -0.000 |
bey | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
them | +0.038 |
mate | +0.037 |
polar | +0.034 |
tow | +0.033 |
wreck | +0.033 |
Neg logit contributions | |
� | -0.045 |
ages | -0.039 |
's | -0.039 |
aul | -0.037 |
cious | -0.036 |
Token | little |
Token ID | 1310 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
� | +0.073 |
's | +0.064 |
aul | +0.058 |
ages | +0.056 |
cious | +0.055 |
Neg logit contributions | |
mate | -0.070 |
them | -0.070 |
inn | -0.061 |
tow | -0.058 |
wreck | -0.058 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
mate | +0.030 |
them | +0.030 |
tow | +0.026 |
wreck | +0.026 |
polar | +0.025 |
Neg logit contributions | |
� | -0.037 |
's | -0.033 |
ages | -0.031 |
aul | -0.030 |
cious | -0.029 |
Token | named |
Token ID | 3706 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
them | +0.053 |
mate | +0.053 |
polar | +0.044 |
tow | +0.043 |
wreck | +0.043 |
Neg logit contributions | |
� | -0.141 |
ages | -0.127 |
's | -0.125 |
aul | -0.122 |
decisions | -0.119 |
Token | Mia |
Token ID | 32189 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
them | +0.116 |
mate | +0.100 |
tow | +0.075 |
inn | +0.072 |
polar | +0.066 |
Neg logit contributions | |
� | -0.367 |
ages | -0.354 |
decisions | -0.340 |
aul | -0.334 |
ience | -0.331 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
them | +0.047 |
mate | +0.045 |
polar | +0.040 |
wreck | +0.039 |
tow | +0.038 |
Neg logit contributions | |
� | -0.082 |
ages | -0.074 |
's | -0.070 |
decisions | -0.069 |
aul | -0.069 |
Token | She |
Token ID | 1375 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
� | +0.002 |
's | +0.001 |
ages | +0.001 |
aul | +0.001 |
cious | +0.001 |
Neg logit contributions | |
mate | -0.002 |
them | -0.002 |
wreck | -0.001 |
polar | -0.001 |
tow | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
� | +0.054 |
decisions | +0.050 |
ages | +0.046 |
aul | +0.045 |
ience | +0.045 |
Neg logit contributions | |
them | -0.041 |
mate | -0.039 |
polar | -0.038 |
wreck | -0.036 |
snowball | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
� | +0.081 |
's | +0.069 |
ages | +0.068 |
aul | +0.065 |
cious | +0.064 |
Neg logit contributions | |
them | -0.056 |
mate | -0.053 |
polar | -0.048 |
wreck | -0.048 |
tow | -0.046 |
Token | spend |
Token ID | 4341 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
� | +0.027 |
's | +0.024 |
ages | +0.023 |
aul | +0.023 |
cious | +0.022 |
Neg logit contributions | |
mate | -0.015 |
them | -0.014 |
wreck | -0.012 |
inn | -0.012 |
polar | -0.012 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
mate | +0.258 |
them | +0.255 |
polar | +0.231 |
tow | +0.231 |
inn | +0.229 |
Neg logit contributions | |
� | -0.324 |
's | -0.289 |
ages | -0.256 |
aul | -0.238 |
pays | -0.235 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
� | +0.086 |
's | +0.076 |
ages | +0.068 |
aul | +0.064 |
pays | +0.063 |
Neg logit contributions | |
mate | -0.073 |
them | -0.069 |
tow | -0.065 |
polar | -0.065 |
ramp | -0.065 |
Token | from |
Token ID | 422 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
mate | +0.067 |
them | +0.063 |
puck | +0.062 |
tow | +0.062 |
ramp | +0.062 |
Neg logit contributions | |
� | -0.048 |
's | -0.039 |
ages | -0.030 |
pays | -0.029 |
decisions | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
� | +0.245 |
's | +0.196 |
Michelle | +0.175 |
Louise | +0.171 |
pays | +0.162 |
Neg logit contributions | |
mate | -0.298 |
inn | -0.277 |
puck | -0.272 |
polar | -0.269 |
tow | -0.267 |
Token | bedroom |
Token ID | 14043 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
mate | +0.060 |
them | +0.060 |
inn | +0.052 |
tow | +0.052 |
polar | +0.052 |
Neg logit contributions | |
� | -0.082 |
's | -0.074 |
ages | -0.069 |
aul | -0.066 |
cious | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
mate | +0.093 |
them | +0.092 |
polar | +0.081 |
wreck | +0.080 |
tow | +0.080 |
Neg logit contributions | |
� | -0.143 |
's | -0.126 |
ages | -0.123 |
aul | -0.117 |
cious | -0.114 |
Token | She |
Token ID | 1375 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
� | +0.020 |
bey | +0.020 |
ages | +0.020 |
ience | +0.020 |
decisions | +0.019 |
Neg logit contributions | |
them | -0.013 |
mate | -0.012 |
tow | -0.011 |
his | -0.010 |
ramp | -0.010 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
� | +0.058 |
's | +0.050 |
ages | +0.048 |
aul | +0.046 |
cious | +0.044 |
Neg logit contributions | |
mate | -0.054 |
them | -0.053 |
wreck | -0.048 |
polar | -0.047 |
tow | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
� | +0.282 |
's | +0.247 |
ages | +0.222 |
aul | +0.212 |
pays | +0.209 |
Neg logit contributions | |
mate | -0.243 |
them | -0.226 |
tow | -0.220 |
ramp | -0.214 |
polar | -0.214 |
Token | listened |
Token ID | 16399 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
� | +0.052 |
ages | +0.050 |
decisions | +0.049 |
aul | +0.048 |
cious | +0.045 |
Neg logit contributions | |
them | -0.037 |
mate | -0.030 |
wreck | -0.029 |
hon | -0.029 |
his | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
� | +0.540 |
ages | +0.480 |
's | +0.473 |
aul | +0.463 |
decisions | +0.443 |
Neg logit contributions | |
them | -0.372 |
mate | -0.356 |
wreck | -0.308 |
tow | -0.304 |
polar | -0.302 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
� | +0.023 |
's | +0.020 |
ages | +0.020 |
aul | +0.019 |
cious | +0.018 |
Neg logit contributions | |
mate | -0.020 |
them | -0.020 |
polar | -0.018 |
wreck | -0.018 |
tow | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
them | +0.117 |
mate | +0.116 |
ramp | +0.091 |
snowball | +0.091 |
wreck | +0.090 |
Neg logit contributions | |
� | -0.235 |
ages | -0.221 |
List | -0.217 |
aul | -0.216 |
cious | -0.216 |
Token | You |
Token ID | 921 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
mate | +0.007 |
tow | +0.007 |
them | +0.007 |
ramp | +0.006 |
polar | +0.006 |
Neg logit contributions | |
ages | -0.006 |
� | -0.006 |
aul | -0.005 |
ience | -0.005 |
cious | -0.005 |
Token | can |
Token ID | 460 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
� | +0.199 |
ages | +0.185 |
aul | +0.176 |
's | +0.175 |
cious | +0.175 |
Neg logit contributions | |
them | -0.132 |
mate | -0.128 |
wreck | -0.119 |
tow | -0.115 |
polar | -0.113 |
Token | play |
Token ID | 711 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
mate | +0.060 |
tant | +0.057 |
polar | +0.054 |
snowball | +0.052 |
them | +0.051 |
Neg logit contributions | |
� | -0.082 |
's | -0.069 |
ages | -0.051 |
bey | -0.051 |
ama | -0.050 |
Token | with |
Token ID | 351 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tow | +0.260 |
polar | +0.249 |
crashing | +0.233 |
inn | +0.228 |
detector | +0.227 |
Neg logit contributions | |
� | -0.191 |
's | -0.182 |
ages | -0.110 |
you | -0.101 |
doesn | -0.100 |
Token | my |
Token ID | 616 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
� | +0.078 |
's | +0.071 |
aul | +0.058 |
ages | +0.057 |
Michelle | +0.056 |
Neg logit contributions | |
mate | -0.083 |
tow | -0.077 |
inn | -0.077 |
polar | -0.076 |
ramp | -0.074 |
Token | car |
Token ID | 1097 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
mate | +0.106 |
them | +0.102 |
inn | +0.100 |
tow | +0.092 |
polar | +0.083 |
Neg logit contributions | |
� | -0.172 |
's | -0.162 |
ages | -0.144 |
decisions | -0.136 |
aul | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
mate | +0.276 |
them | +0.273 |
tow | +0.271 |
polar | +0.270 |
inn | +0.251 |
Neg logit contributions | |
� | -0.310 |
's | -0.288 |
ages | -0.250 |
aul | -0.225 |
pays | -0.222 |
Token | And |
Token ID | 843 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
mate | +0.018 |
them | +0.017 |
tow | +0.016 |
polar | +0.016 |
wreck | +0.016 |
Neg logit contributions | |
� | -0.015 |
's | -0.013 |
ages | -0.013 |
aul | -0.012 |
cious | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
� | +0.180 |
ages | +0.152 |
's | +0.151 |
aul | +0.143 |
cious | +0.136 |
Neg logit contributions | |
them | -0.231 |
mate | -0.230 |
wreck | -0.207 |
tow | -0.206 |
polar | -0.206 |
Token | off |
Token ID | 572 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
� | +0.237 |
's | +0.207 |
ages | +0.181 |
pays | +0.176 |
aul | +0.169 |
Neg logit contributions | |
mate | -0.224 |
them | -0.216 |
polar | -0.209 |
tow | -0.204 |
wreck | -0.204 |
Token | she |
Token ID | 673 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
� | +0.060 |
's | +0.052 |
ages | +0.046 |
pays | +0.043 |
aul | +0.043 |
Neg logit contributions | |
mate | -0.062 |
them | -0.058 |
wreck | -0.057 |
polar | -0.057 |
snowball | -0.056 |
Token | would |
Token ID | 561 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
� | +0.258 |
ages | +0.232 |
aul | +0.225 |
decisions | +0.221 |
cious | +0.219 |
Neg logit contributions | |
them | -0.207 |
mate | -0.197 |
wreck | -0.189 |
polar | -0.180 |
tow | -0.176 |
Token | look |
Token ID | 804 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
mate | +0.081 |
inn | +0.075 |
them | +0.074 |
polar | +0.073 |
snowball | +0.071 |
Neg logit contributions | |
� | -0.107 |
's | -0.090 |
adow | -0.073 |
listens | -0.073 |
pays | -0.073 |
Token | up |
Token ID | 510 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
� | +0.008 |
's | +0.007 |
ages | +0.006 |
aul | +0.006 |
pays | +0.006 |
Neg logit contributions | |
mate | -0.007 |
them | -0.007 |
polar | -0.007 |
wreck | -0.007 |
tow | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
� | +0.357 |
ages | +0.319 |
's | +0.308 |
aul | +0.296 |
cious | +0.294 |
Neg logit contributions | |
them | -0.264 |
mate | -0.250 |
wreck | -0.219 |
tow | -0.217 |
polar | -0.216 |
Token | her |
Token ID | 607 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
� | +0.087 |
's | +0.076 |
ages | +0.070 |
aul | +0.068 |
decisions | +0.067 |
Neg logit contributions | |
mate | -0.076 |
them | -0.069 |
polar | -0.069 |
wreck | -0.067 |
ramp | -0.067 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
mate | +0.054 |
them | +0.054 |
wreck | +0.047 |
polar | +0.047 |
tow | +0.047 |
Neg logit contributions | |
� | -0.082 |
's | -0.071 |
ages | -0.071 |
aul | -0.068 |
cious | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
� | +0.027 |
ages | +0.025 |
aul | +0.023 |
cious | +0.023 |
ience | +0.023 |
Neg logit contributions | |
them | -0.018 |
mate | -0.017 |
polar | -0.015 |
wreck | -0.015 |
tow | -0.015 |
Token | say |
Token ID | 910 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
� | +0.053 |
ages | +0.047 |
aul | +0.045 |
cious | +0.045 |
ience | +0.045 |
Neg logit contributions | |
them | -0.039 |
mate | -0.036 |
wreck | -0.033 |
polar | -0.032 |
tow | -0.032 |
Token | � |
Token ID | 6184 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
them | +0.016 |
mate | +0.015 |
tow | +0.013 |
wreck | +0.012 |
polar | +0.012 |
Neg logit contributions | |
� | -0.024 |
ages | -0.022 |
's | -0.021 |
aul | -0.021 |
aut | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
� | +0.082 |
's | +0.070 |
ages | +0.070 |
aul | +0.066 |
cious | +0.064 |
Neg logit contributions | |
them | -0.078 |
mate | -0.078 |
polar | -0.069 |
wreck | -0.069 |
tow | -0.069 |
Token | day |
Token ID | 1110 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
them | +0.106 |
mate | +0.098 |
wreck | +0.095 |
polar | +0.094 |
tow | +0.094 |
Neg logit contributions | |
ages | -0.146 |
� | -0.141 |
aul | -0.133 |
cious | -0.131 |
ience | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
� | +0.181 |
ages | +0.170 |
aul | +0.166 |
decisions | +0.164 |
's | +0.160 |
Neg logit contributions | |
them | -0.109 |
mate | -0.100 |
inn | -0.086 |
polar | -0.085 |
his | -0.081 |
Token | there |
Token ID | 612 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
� | +0.037 |
's | +0.030 |
ages | +0.027 |
cious | +0.026 |
aul | +0.025 |
Neg logit contributions | |
mate | -0.037 |
them | -0.034 |
ramp | -0.034 |
wreck | -0.033 |
tow | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
� | +0.024 |
's | +0.021 |
ages | +0.019 |
aul | +0.018 |
cious | +0.017 |
Neg logit contributions | |
mate | -0.023 |
them | -0.022 |
polar | -0.020 |
wreck | -0.020 |
ramp | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
mate | +0.025 |
them | +0.025 |
wreck | +0.022 |
polar | +0.022 |
tow | +0.022 |
Neg logit contributions | |
� | -0.026 |
's | -0.023 |
ages | -0.022 |
aul | -0.021 |
cious | -0.020 |
Token | long |
Token ID | 890 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
� | +0.098 |
's | +0.085 |
aul | +0.076 |
ages | +0.075 |
cious | +0.074 |
Neg logit contributions | |
them | -0.087 |
mate | -0.086 |
inn | -0.075 |
tow | -0.072 |
wreck | -0.072 |
Token | circle |
Token ID | 9197 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
them | +0.006 |
mate | +0.006 |
tow | +0.005 |
wreck | +0.005 |
polar | +0.005 |
Neg logit contributions | |
� | -0.008 |
's | -0.007 |
ages | -0.007 |
aul | -0.006 |
cious | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
them | +0.173 |
mate | +0.173 |
polar | +0.153 |
wreck | +0.152 |
tow | +0.151 |
Neg logit contributions | |
� | -0.247 |
's | -0.221 |
ages | -0.210 |
aul | -0.196 |
cious | -0.194 |
Token | It |
Token ID | 632 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
� | +0.024 |
ages | +0.021 |
's | +0.021 |
aul | +0.019 |
ience | +0.019 |
Neg logit contributions | |
them | -0.022 |
mate | -0.022 |
tow | -0.020 |
wreck | -0.020 |
polar | -0.020 |
Token | needed |
Token ID | 2622 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
mate | +0.056 |
them | +0.054 |
tow | +0.049 |
polar | +0.049 |
wreck | +0.048 |
Neg logit contributions | |
� | -0.054 |
's | -0.047 |
ages | -0.042 |
aul | -0.039 |
pays | -0.038 |
Token | said |
Token ID | 531 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
� | +0.029 |
ages | +0.025 |
aul | +0.025 |
's | +0.024 |
decisions | +0.024 |
Neg logit contributions | |
them | -0.029 |
mate | -0.028 |
polar | -0.026 |
captain | -0.026 |
wreck | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
them | +0.002 |
mate | +0.002 |
tow | +0.001 |
control | +0.001 |
wreck | +0.001 |
Neg logit contributions | |
� | -0.004 |
aul | -0.003 |
ages | -0.003 |
pays | -0.003 |
bey | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
� | +0.028 |
ages | +0.025 |
aul | +0.025 |
decisions | +0.024 |
's | +0.024 |
Neg logit contributions | |
them | -0.023 |
mate | -0.021 |
tow | -0.020 |
polar | -0.019 |
captain | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
� | +0.027 |
's | +0.023 |
ages | +0.021 |
aul | +0.020 |
cious | +0.019 |
Neg logit contributions | |
mate | -0.030 |
them | -0.028 |
wreck | -0.027 |
polar | -0.027 |
ramp | -0.026 |
Token | Sab |
Token ID | 39646 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
� | +0.027 |
's | +0.023 |
ages | +0.022 |
aul | +0.020 |
cious | +0.020 |
Neg logit contributions | |
mate | -0.030 |
them | -0.030 |
wreck | -0.027 |
polar | -0.027 |
tow | -0.027 |
Token | ina |
Token ID | 1437 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
� | +0.092 |
ages | +0.077 |
's | +0.074 |
aul | +0.069 |
decisions | +0.068 |
Neg logit contributions | |
mate | -0.113 |
them | -0.113 |
polar | -0.102 |
inn | -0.100 |
captain | -0.099 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
decisions | +0.098 |
ages | +0.095 |
� | +0.093 |
rewarding | +0.092 |
aul | +0.089 |
Neg logit contributions | |
them | -0.068 |
row | -0.056 |
stuffed | -0.056 |
mate | -0.055 |
wreck | -0.055 |
Token | sad |
Token ID | 6507 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
� | +0.092 |
ages | +0.092 |
aul | +0.087 |
cious | +0.084 |
bey | +0.084 |
Neg logit contributions | |
them | -0.078 |
mate | -0.069 |
tow | -0.065 |
wreck | -0.064 |
his | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
mate | +0.050 |
them | +0.050 |
wreck | +0.044 |
polar | +0.044 |
tow | +0.043 |
Neg logit contributions | |
� | -0.068 |
's | -0.059 |
ages | -0.058 |
aul | -0.055 |
cious | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
� | +0.027 |
ages | +0.027 |
uch | +0.025 |
ience | +0.025 |
bey | +0.024 |
Neg logit contributions | |
them | -0.019 |
mate | -0.017 |
his | -0.015 |
captain | -0.015 |
tow | -0.014 |
Token | apologised |
Token ID | 46397 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
� | +0.052 |
ages | +0.048 |
decisions | +0.046 |
aul | +0.045 |
's | +0.044 |
Neg logit contributions | |
them | -0.048 |
mate | -0.045 |
wreck | -0.043 |
polar | -0.042 |
captain | -0.041 |
Token | idea |
Token ID | 2126 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
� | +0.033 |
's | +0.029 |
ages | +0.028 |
aul | +0.027 |
cious | +0.026 |
Neg logit contributions | |
mate | -0.023 |
them | -0.022 |
polar | -0.020 |
wreck | -0.020 |
tow | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
them | +0.289 |
mate | +0.286 |
wreck | +0.236 |
tow | +0.236 |
polar | +0.232 |
Neg logit contributions | |
� | -0.435 |
ages | -0.386 |
's | -0.381 |
aul | -0.377 |
cious | -0.363 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
� | +0.007 |
ages | +0.006 |
's | +0.006 |
aul | +0.006 |
cious | +0.006 |
Neg logit contributions | |
them | -0.006 |
mate | -0.006 |
tow | -0.005 |
polar | -0.005 |
ramp | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
� | +0.063 |
's | +0.054 |
ages | +0.052 |
aul | +0.049 |
cious | +0.048 |
Neg logit contributions | |
mate | -0.059 |
them | -0.058 |
wreck | -0.053 |
polar | -0.052 |
tow | -0.052 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
mate | +0.071 |
them | +0.065 |
polar | +0.063 |
ramp | +0.063 |
wreck | +0.062 |
Neg logit contributions | |
� | -0.082 |
's | -0.074 |
aul | -0.064 |
bey | -0.063 |
ages | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
mate | +0.137 |
them | +0.134 |
wreck | +0.123 |
polar | +0.122 |
tow | +0.122 |
Neg logit contributions | |
� | -0.137 |
's | -0.118 |
ages | -0.113 |
aul | -0.106 |
cious | -0.103 |
Token | time |
Token ID | 640 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
� | +0.099 |
's | +0.087 |
ages | +0.086 |
aul | +0.082 |
cious | +0.080 |
Neg logit contributions | |
mate | -0.063 |
them | -0.063 |
polar | -0.055 |
wreck | -0.055 |
tow | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
� | +0.045 |
ages | +0.042 |
's | +0.040 |
aul | +0.040 |
decisions | +0.038 |
Neg logit contributions | |
them | -0.029 |
mate | -0.029 |
wreck | -0.025 |
polar | -0.024 |
tow | -0.024 |
Token | there |
Token ID | 612 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
� | +0.025 |
's | +0.022 |
ages | +0.019 |
aul | +0.018 |
bey | +0.018 |
Neg logit contributions | |
mate | -0.027 |
them | -0.026 |
tow | -0.025 |
wreck | -0.025 |
polar | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
� | +0.012 |
's | +0.011 |
ages | +0.008 |
aul | +0.008 |
bey | +0.008 |
Neg logit contributions | |
mate | -0.015 |
them | -0.014 |
captain | -0.014 |
ramp | -0.014 |
polar | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
them | +0.026 |
mate | +0.024 |
polar | +0.022 |
snowball | +0.022 |
tow | +0.022 |
Neg logit contributions | |
� | -0.031 |
ages | -0.028 |
's | -0.027 |
aul | -0.026 |
ience | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
his | +0.115 |
them | +0.111 |
stuffed | +0.091 |
t | +0.087 |
mate | +0.086 |
Neg logit contributions | |
aul | -0.130 |
ages | -0.126 |
lette | -0.125 |
� | -0.125 |
aut | -0.124 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
� | +0.236 |
's | +0.207 |
ages | +0.191 |
aul | +0.179 |
cious | +0.177 |
Neg logit contributions | |
mate | -0.224 |
them | -0.215 |
wreck | -0.197 |
tow | -0.195 |
ramp | -0.194 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
them | +0.235 |
mate | +0.230 |
wreck | +0.204 |
polar | +0.204 |
tow | +0.203 |
Neg logit contributions | |
� | -0.281 |
's | -0.243 |
ages | -0.242 |
aul | -0.227 |
cious | -0.224 |
Token | little |
Token ID | 1310 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
� | +0.008 |
's | +0.008 |
decisions | +0.007 |
aul | +0.007 |
ages | +0.007 |
Neg logit contributions | |
mate | -0.008 |
inn | -0.007 |
them | -0.006 |
room | -0.006 |
tow | -0.006 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
mate | +0.031 |
them | +0.030 |
inn | +0.027 |
wreck | +0.026 |
tow | +0.026 |
Neg logit contributions | |
� | -0.042 |
's | -0.037 |
ages | -0.035 |
aul | -0.034 |
cious | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | -8.90e+00 |
Pos logit contributions | |
them | +0.139 |
mate | +0.130 |
wreck | +0.122 |
polar | +0.120 |
tow | +0.117 |
Neg logit contributions | |
� | -0.171 |
ages | -0.156 |
aul | -0.150 |
's | -0.143 |
cious | -0.143 |
Token | kind |
Token ID | 1611 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
� | +0.616 |
's | +0.551 |
ages | +0.517 |
decisions | +0.497 |
cious | +0.472 |
Neg logit contributions | |
mate | -0.580 |
them | -0.538 |
inn | -0.500 |
ramp | -0.484 |
wreck | -0.474 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
� | +0.235 |
's | +0.211 |
ages | +0.199 |
aul | +0.190 |
decisions | +0.186 |
Neg logit contributions | |
mate | -0.186 |
them | -0.179 |
ramp | -0.163 |
wreck | -0.161 |
inn | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
them | +0.080 |
mate | +0.076 |
wreck | +0.067 |
tow | +0.067 |
polar | +0.066 |
Neg logit contributions | |
� | -0.126 |
ages | -0.114 |
's | -0.110 |
aul | -0.109 |
cious | -0.106 |
Token | She |
Token ID | 1375 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
them | +0.037 |
mate | +0.036 |
tow | +0.033 |
polar | +0.032 |
wreck | +0.032 |
Neg logit contributions | |
� | -0.043 |
ages | -0.039 |
's | -0.037 |
cious | -0.037 |
bey | -0.036 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +0.030 |
's | +0.026 |
ages | +0.024 |
aul | +0.022 |
cious | +0.021 |
Neg logit contributions | |
mate | -0.036 |
them | -0.034 |
wreck | -0.031 |
ramp | -0.031 |
tow | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
them | +0.004 |
mate | +0.004 |
tow | +0.003 |
wreck | +0.003 |
polar | +0.003 |
Neg logit contributions | |
� | -0.006 |
ages | -0.006 |
's | -0.005 |
aul | -0.005 |
decisions | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
� | +0.025 |
's | +0.022 |
ages | +0.022 |
aul | +0.021 |
cious | +0.020 |
Neg logit contributions | |
them | -0.015 |
mate | -0.015 |
wreck | -0.013 |
polar | -0.013 |
tow | -0.013 |
Token | Sure |
Token ID | 19457 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
mate | +0.113 |
them | +0.112 |
inn | +0.096 |
tow | +0.094 |
racer | +0.092 |
Neg logit contributions | |
� | -0.126 |
ages | -0.116 |
's | -0.112 |
decisions | -0.108 |
aul | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
mate | +0.269 |
them | +0.266 |
wreck | +0.235 |
polar | +0.235 |
tow | +0.233 |
Neg logit contributions | |
� | -0.364 |
's | -0.318 |
ages | -0.312 |
aul | -0.297 |
cious | -0.289 |
Token | let |
Token ID | 1309 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
� | +0.024 |
ages | +0.022 |
's | +0.021 |
aul | +0.021 |
cious | +0.020 |
Neg logit contributions | |
them | -0.018 |
mate | -0.017 |
tow | -0.015 |
polar | -0.015 |
wreck | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | -8.93e+00 |
Pos logit contributions | |
ages | +0.035 |
List | +0.035 |
cious | +0.033 |
rewarding | +0.032 |
adow | +0.031 |
Neg logit contributions | |
them | -0.123 |
mate | -0.102 |
snowball | -0.094 |
lot | -0.094 |
his | -0.093 |
Token | print |
Token ID | 3601 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
� | +0.747 |
's | +0.660 |
ages | +0.639 |
aul | +0.613 |
cious | +0.596 |
Neg logit contributions | |
mate | -0.443 |
them | -0.434 |
polar | -0.382 |
wreck | -0.378 |
tow | -0.375 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
� | +0.042 |
ages | +0.037 |
cious | +0.036 |
's | +0.036 |
aul | +0.035 |
Neg logit contributions | |
them | -0.031 |
mate | -0.029 |
wreck | -0.025 |
tow | -0.024 |
snowball | -0.024 |
Token | picture |
Token ID | 4286 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
� | +0.077 |
's | +0.067 |
ages | +0.063 |
aul | +0.061 |
cious | +0.058 |
Neg logit contributions | |
mate | -0.063 |
them | -0.062 |
polar | -0.056 |
wreck | -0.055 |
tow | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
� | +0.032 |
's | +0.028 |
ages | +0.028 |
aul | +0.027 |
cious | +0.026 |
Neg logit contributions | |
mate | -0.018 |
them | -0.018 |
wreck | -0.015 |
tow | -0.015 |
polar | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
them | +0.177 |
mate | +0.160 |
wreck | +0.142 |
tow | +0.139 |
polar | +0.135 |
Neg logit contributions | |
� | -0.234 |
ages | -0.210 |
's | -0.201 |
cious | -0.196 |
aul | -0.193 |
Token | And |
Token ID | 1870 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
� | +0.038 |
's | +0.032 |
ages | +0.031 |
aul | +0.029 |
cious | +0.028 |
Neg logit contributions | |
mate | -0.039 |
them | -0.039 |
wreck | -0.036 |
polar | -0.036 |
tow | -0.035 |
Token | he |
Token ID | 339 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
them | +0.071 |
mate | +0.066 |
his | +0.059 |
captain | +0.055 |
polar | +0.053 |
Neg logit contributions | |
ages | -0.105 |
� | -0.103 |
aul | -0.101 |
aut | -0.096 |
cious | -0.095 |
Token | did |
Token ID | 750 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
� | +0.033 |
ages | +0.030 |
aul | +0.029 |
's | +0.028 |
decisions | +0.028 |
Neg logit contributions | |
mate | -0.031 |
them | -0.030 |
wreck | -0.026 |
polar | -0.026 |
tow | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
them | +0.102 |
mate | +0.099 |
wreck | +0.084 |
tow | +0.084 |
ramp | +0.082 |
Neg logit contributions | |
� | -0.157 |
ages | -0.140 |
's | -0.139 |
aul | -0.138 |
cious | -0.133 |
Token | Pete |
Token ID | 17542 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
mate | +0.050 |
them | +0.049 |
inn | +0.044 |
tow | +0.043 |
puck | +0.040 |
Neg logit contributions | |
� | -0.087 |
ages | -0.085 |
cious | -0.083 |
's | -0.082 |
ience | -0.079 |
Token | 's |
Token ID | 338 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
� | +0.238 |
ages | +0.218 |
aul | +0.215 |
decisions | +0.209 |
cious | +0.206 |
Neg logit contributions | |
them | -0.216 |
mate | -0.216 |
wreck | -0.192 |
polar | -0.187 |
tow | -0.185 |
Token | speech |
Token ID | 4046 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
� | +0.636 |
ages | +0.560 |
cious | +0.545 |
aul | +0.545 |
's | +0.526 |
Neg logit contributions | |
mate | -0.571 |
them | -0.530 |
wreck | -0.494 |
tow | -0.473 |
control | -0.470 |
Token | was |
Token ID | 373 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
� | +0.107 |
's | +0.089 |
ages | +0.088 |
aul | +0.084 |
cious | +0.079 |
Neg logit contributions | |
mate | -0.146 |
them | -0.144 |
wreck | -0.131 |
tow | -0.131 |
polar | -0.131 |
Token | one |
Token ID | 530 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
mate | +0.031 |
them | +0.031 |
wreck | +0.028 |
tow | +0.028 |
polar | +0.027 |
Neg logit contributions | |
� | -0.036 |
's | -0.031 |
ages | -0.031 |
aul | -0.030 |
cious | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
� | +0.035 |
ages | +0.033 |
aul | +0.032 |
cious | +0.031 |
's | +0.031 |
Neg logit contributions | |
mate | -0.021 |
them | -0.018 |
wreck | -0.017 |
tow | -0.017 |
racer | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
mate | +0.148 |
ramp | +0.143 |
them | +0.139 |
polar | +0.139 |
wreck | +0.135 |
Neg logit contributions | |
� | -0.208 |
's | -0.171 |
pays | -0.161 |
ages | -0.159 |
decisions | -0.157 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
� | +0.028 |
ages | +0.026 |
ience | +0.025 |
aul | +0.025 |
cious | +0.024 |
Neg logit contributions | |
them | -0.021 |
mate | -0.018 |
tow | -0.018 |
wreck | -0.018 |
ramp | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
� | +0.168 |
's | +0.141 |
ages | +0.137 |
aul | +0.129 |
cious | +0.124 |
Neg logit contributions | |
mate | -0.202 |
them | -0.202 |
wreck | -0.183 |
polar | -0.183 |
tow | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
� | +0.009 |
ages | +0.009 |
's | +0.008 |
aul | +0.008 |
decisions | +0.008 |
Neg logit contributions | |
them | -0.006 |
mate | -0.006 |
polar | -0.005 |
tow | -0.005 |
wreck | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
� | +0.039 |
ages | +0.035 |
's | +0.035 |
aul | +0.034 |
decisions | +0.033 |
Neg logit contributions | |
them | -0.023 |
mate | -0.021 |
tow | -0.018 |
polar | -0.018 |
wreck | -0.018 |
Token | It |
Token ID | 1026 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
them | +0.114 |
mate | +0.107 |
wreck | +0.098 |
tow | +0.097 |
snowball | +0.096 |
Neg logit contributions | |
� | -0.100 |
ages | -0.090 |
's | -0.087 |
aul | -0.086 |
cious | -0.082 |
Token | 's |
Token ID | 338 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
them | +0.046 |
snowball | +0.043 |
wreck | +0.043 |
hon | +0.043 |
match | +0.042 |
Neg logit contributions | |
aul | -0.021 |
cious | -0.019 |
assy | -0.018 |
ages | -0.017 |
enna | -0.017 |
Token | OK |
Token ID | 7477 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
� | +0.481 |
ages | +0.415 |
aul | +0.413 |
's | +0.392 |
cious | +0.391 |
Neg logit contributions | |
them | -0.717 |
mate | -0.693 |
polar | -0.651 |
snowball | -0.639 |
wreck | -0.633 |
Token | , |
Token ID | 11 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
� | +0.358 |
's | +0.312 |
ages | +0.310 |
aul | +0.298 |
cious | +0.290 |
Neg logit contributions | |
mate | -0.249 |
them | -0.249 |
polar | -0.218 |
wreck | -0.214 |
tow | -0.212 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
� | +0.040 |
ages | +0.038 |
aul | +0.036 |
cious | +0.036 |
's | +0.036 |
Neg logit contributions | |
them | -0.023 |
mate | -0.021 |
tow | -0.018 |
wreck | -0.018 |
polar | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
� | +0.017 |
ages | +0.015 |
List | +0.015 |
aul | +0.014 |
cious | +0.014 |
Neg logit contributions | |
them | -0.009 |
mate | -0.008 |
polar | -0.007 |
wreck | -0.007 |
tow | -0.007 |
Token | That |
Token ID | 1320 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
ages | +0.024 |
� | +0.023 |
cious | +0.022 |
aul | +0.021 |
's | +0.021 |
Neg logit contributions | |
them | -0.024 |
mate | -0.024 |
tow | -0.023 |
polar | -0.023 |
wreck | -0.022 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
� | +0.001 |
's | +0.000 |
ages | +0.000 |
pays | +0.000 |
aul | +0.000 |
Neg logit contributions | |
mate | -0.000 |
them | -0.000 |
wreck | -0.000 |
polar | -0.000 |
tow | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
mate | +0.061 |
them | +0.061 |
wreck | +0.053 |
polar | +0.053 |
tow | +0.053 |
Neg logit contributions | |
� | -0.091 |
's | -0.080 |
ages | -0.078 |
aul | -0.074 |
cious | -0.073 |
Token | Now |
Token ID | 2735 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
mate | +0.048 |
them | +0.044 |
tow | +0.043 |
racer | +0.039 |
ramp | +0.038 |
Neg logit contributions | |
ages | -0.054 |
� | -0.051 |
ups | -0.050 |
ience | -0.049 |
's | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
them | +0.038 |
mate | +0.032 |
captain | +0.027 |
tow | +0.026 |
match | +0.026 |
Neg logit contributions | |
ages | -0.058 |
� | -0.057 |
aul | -0.054 |
cious | -0.053 |
aut | -0.052 |
Token | let |
Token ID | 1309 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
� | +0.003 |
ages | +0.003 |
aul | +0.003 |
cious | +0.003 |
's | +0.003 |
Neg logit contributions | |
them | -0.002 |
mate | -0.002 |
tow | -0.002 |
polar | -0.002 |
captain | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
ages | +0.031 |
cious | +0.029 |
mindful | +0.028 |
aul | +0.026 |
List | +0.026 |
Neg logit contributions | |
them | -0.122 |
mate | -0.104 |
snowball | -0.099 |
polar | -0.098 |
tow | -0.097 |
Token | go |
Token ID | 467 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
� | +0.743 |
's | +0.653 |
ages | +0.624 |
aul | +0.599 |
cious | +0.578 |
Neg logit contributions | |
mate | -0.459 |
them | -0.446 |
polar | -0.395 |
wreck | -0.392 |
tow | -0.388 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
� | +0.096 |
's | +0.088 |
ages | +0.075 |
pays | +0.069 |
bey | +0.069 |
Neg logit contributions | |
mate | -0.096 |
tant | -0.084 |
them | -0.084 |
wreck | -0.083 |
polar | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
� | +0.153 |
's | +0.134 |
ages | +0.125 |
aul | +0.120 |
pays | +0.115 |
Neg logit contributions | |
mate | -0.126 |
them | -0.120 |
polar | -0.112 |
wreck | -0.112 |
tow | -0.111 |
Token | have |
Token ID | 423 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
� | +0.004 |
ages | +0.004 |
aul | +0.004 |
ience | +0.004 |
cious | +0.003 |
Neg logit contributions | |
them | -0.001 |
mate | -0.001 |
wreck | -0.001 |
match | -0.001 |
tow | -0.001 |
Token | some |
Token ID | 617 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
them | +0.015 |
mate | +0.012 |
snowball | +0.012 |
polar | +0.012 |
tow | +0.011 |
Neg logit contributions | |
� | -0.020 |
ages | -0.018 |
cious | -0.017 |
aul | -0.017 |
bey | -0.017 |