Token | voice |
Token ID | 3809 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
izing | +0.042 |
ning | +0.040 |
king | +0.040 |
bul | +0.039 |
ening | +0.039 |
Neg logit contributions | |
am | -0.025 |
done | -0.021 |
| -0.021 |
| -0.021 |
'm | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.018 |
| +0.017 |
story | +0.016 |
big | +0.015 |
Neg logit contributions | |
izing | -0.073 |
ning | -0.071 |
king | -0.070 |
yles | -0.070 |
rily | -0.069 |
Token | but |
Token ID | 475 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
izing | +0.061 |
yles | +0.059 |
ning | +0.058 |
ellery | +0.058 |
rily | +0.057 |
Neg logit contributions | |
am | -0.033 |
| -0.031 |
done | -0.030 |
big | -0.028 |
story | -0.028 |
Token | John |
Token ID | 1757 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
izing | +0.003 |
yles | +0.002 |
ning | +0.002 |
king | +0.002 |
ellery | +0.002 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
story | -0.001 |
big | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
am | +0.003 |
done | +0.003 |
| +0.003 |
story | +0.003 |
big | +0.003 |
Neg logit contributions | |
izing | -0.010 |
yles | -0.010 |
ning | -0.010 |
king | -0.009 |
ellery | -0.009 |
Token | anyways |
Token ID | 32845 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
am | +0.025 |
done | +0.022 |
story | +0.019 |
| +0.018 |
bad | +0.016 |
Neg logit contributions | |
izing | -0.072 |
king | -0.071 |
rily | -0.071 |
ning | -0.071 |
bing | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
am | +0.072 |
done | +0.055 |
ossible | +0.054 |
| +0.053 |
met | +0.052 |
Neg logit contributions | |
izing | -0.187 |
rily | -0.178 |
king | -0.173 |
ning | -0.171 |
bing | -0.170 |
Token | He |
Token ID | 679 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.025 |
bad | +0.022 |
story | +0.021 |
big | +0.020 |
Neg logit contributions | |
izing | -0.084 |
yles | -0.083 |
ning | -0.082 |
rily | -0.080 |
shadow | -0.079 |
Token | â |
Token ID | 22940 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.020 |
| +0.020 |
story | +0.019 |
big | +0.017 |
Neg logit contributions | |
izing | -0.064 |
ning | -0.062 |
yles | -0.062 |
king | -0.061 |
ellery | -0.061 |
Token | € |
Token ID | 26391 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
izing | +0.071 |
ning | +0.067 |
king | +0.066 |
yles | +0.066 |
ellery | +0.064 |
Neg logit contributions | |
am | -0.071 |
| -0.066 |
done | -0.066 |
big | -0.065 |
story | -0.065 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
bad | +0.006 |
story | +0.006 |
big | +0.006 |
Neg logit contributions | |
yles | -0.019 |
izing | -0.019 |
ning | -0.018 |
king | -0.018 |
ellery | -0.018 |
Token | down |
Token ID | 866 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
izing | +0.052 |
ning | +0.051 |
king | +0.050 |
yles | +0.050 |
rily | +0.050 |
Neg logit contributions | |
am | -0.039 |
story | -0.036 |
done | -0.036 |
| -0.034 |
big | -0.033 |
Token | side |
Token ID | 1735 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
am | +0.017 |
done | +0.016 |
story | +0.015 |
| +0.014 |
bad | +0.013 |
Neg logit contributions | |
izing | -0.037 |
ning | -0.036 |
rily | -0.035 |
king | -0.035 |
yles | -0.035 |
Token | - |
Token ID | 12 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
am | +0.014 |
done | +0.011 |
| +0.010 |
story | +0.009 |
big | +0.008 |
Neg logit contributions | |
izing | -0.071 |
yles | -0.069 |
ning | -0.069 |
king | -0.069 |
rily | -0.068 |
Token | by |
Token ID | 1525 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
izing | +0.117 |
rily | +0.110 |
yles | +0.110 |
ning | +0.107 |
ellery | +0.107 |
Neg logit contributions | |
am | -0.108 |
| -0.105 |
done | -0.103 |
to | -0.099 |
big | -0.094 |
Token | - |
Token ID | 12 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
am | +0.040 |
done | +0.034 |
| +0.033 |
story | +0.032 |
bad | +0.030 |
Neg logit contributions | |
izing | -0.085 |
king | -0.083 |
yles | -0.082 |
ning | -0.082 |
rily | -0.081 |
Token | side |
Token ID | 1589 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
izing | +0.116 |
rily | +0.109 |
yles | +0.109 |
ning | +0.106 |
ellery | +0.105 |
Neg logit contributions | |
am | -0.109 |
| -0.106 |
done | -0.105 |
to | -0.101 |
big | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
am | +0.069 |
done | +0.048 |
story | +0.043 |
'm | +0.043 |
| +0.041 |
Neg logit contributions | |
izing | -0.204 |
rily | -0.191 |
bing | -0.191 |
king | -0.190 |
ning | -0.188 |
Token | They |
Token ID | 1119 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.020 |
story | +0.017 |
bad | +0.016 |
big | +0.016 |
Neg logit contributions | |
yles | -0.055 |
izing | -0.054 |
ning | -0.053 |
king | -0.053 |
rily | -0.053 |
Token | were |
Token ID | 547 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
am | +0.020 |
| +0.017 |
done | +0.017 |
story | +0.017 |
big | +0.015 |
Neg logit contributions | |
izing | -0.054 |
yles | -0.053 |
ning | -0.052 |
king | -0.052 |
ellery | -0.051 |
Token | having |
Token ID | 1719 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.007 |
| +0.007 |
big | +0.006 |
story | +0.006 |
Neg logit contributions | |
izing | -0.017 |
yles | -0.017 |
ning | -0.016 |
ellery | -0.016 |
king | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
am | +0.038 |
story | +0.032 |
done | +0.031 |
| +0.030 |
own | +0.028 |
Neg logit contributions | |
yles | -0.054 |
izing | -0.054 |
ning | -0.053 |
ellery | -0.052 |
rily | -0.051 |
Token | hesitated |
Token ID | 41723 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
izing | +0.029 |
yles | +0.028 |
ning | +0.028 |
king | +0.028 |
ellery | +0.028 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
| -0.010 |
story | -0.009 |
big | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
am | +0.036 |
done | +0.031 |
story | +0.030 |
ossible | +0.028 |
| +0.027 |
Neg logit contributions | |
izing | -0.060 |
king | -0.059 |
rily | -0.058 |
bing | -0.056 |
ning | -0.055 |
Token | walked |
Token ID | 6807 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
am | +0.018 |
done | +0.016 |
| +0.016 |
story | +0.016 |
big | +0.015 |
Neg logit contributions | |
izing | -0.024 |
yles | -0.023 |
ning | -0.023 |
king | -0.022 |
ellery | -0.022 |
Token | towards |
Token ID | 3371 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
izing | +0.012 |
king | +0.012 |
rily | +0.011 |
ning | +0.011 |
bing | +0.011 |
Neg logit contributions | |
am | -0.010 |
done | -0.009 |
story | -0.009 |
| -0.008 |
ossible | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
am | +0.013 |
done | +0.011 |
| +0.011 |
story | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.027 |
yles | -0.026 |
ning | -0.026 |
king | -0.025 |
rily | -0.025 |
Token | anyways |
Token ID | 32845 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
am | +0.028 |
done | +0.024 |
| +0.021 |
story | +0.021 |
big | +0.019 |
Neg logit contributions | |
izing | -0.096 |
ning | -0.093 |
king | -0.093 |
rily | -0.092 |
bing | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
am | +0.066 |
done | +0.055 |
ossible | +0.047 |
| +0.045 |
story | +0.044 |
Neg logit contributions | |
izing | -0.191 |
rily | -0.184 |
king | -0.178 |
ning | -0.178 |
ants | -0.177 |
Token | The |
Token ID | 383 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
am | +0.021 |
done | +0.019 |
story | +0.017 |
bad | +0.016 |
big | +0.016 |
Neg logit contributions | |
izing | -0.056 |
yles | -0.054 |
ning | -0.054 |
rily | -0.054 |
king | -0.053 |
Token | farmer |
Token ID | 18739 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
izing | +0.024 |
yles | +0.024 |
rily | +0.023 |
ellery | +0.023 |
ning | +0.023 |
Neg logit contributions | |
am | -0.016 |
| -0.015 |
done | -0.015 |
big | -0.014 |
story | -0.014 |
Token | offered |
Token ID | 4438 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.013 |
ellery | +0.013 |
ning | +0.013 |
rily | +0.013 |
Neg logit contributions | |
am | -0.005 |
done | -0.005 |
| -0.005 |
to | -0.005 |
story | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
izing | +0.019 |
ning | +0.019 |
king | +0.019 |
yles | +0.019 |
rily | +0.019 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
story | -0.009 |
| -0.009 |
big | -0.008 |
Token | but |
Token ID | 475 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
am | +0.023 |
story | +0.021 |
done | +0.020 |
ossible | +0.020 |
| +0.019 |
Neg logit contributions | |
izing | -0.046 |
king | -0.043 |
rily | -0.043 |
bing | -0.042 |
ning | -0.042 |
Token | Julie |
Token ID | 21946 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
am | +0.013 |
done | +0.012 |
story | +0.012 |
| +0.012 |
big | +0.011 |
Neg logit contributions | |
izing | -0.025 |
yles | -0.023 |
ning | -0.023 |
rily | -0.023 |
bing | -0.023 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
| +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.005 |
yles | -0.005 |
ning | -0.005 |
king | -0.005 |
rily | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
izing | +0.006 |
yles | +0.006 |
ning | +0.006 |
king | +0.006 |
ellery | +0.006 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
| -0.003 |
story | -0.003 |
big | -0.003 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
am | +0.020 |
story | +0.017 |
| +0.017 |
done | +0.017 |
ossible | +0.015 |
Neg logit contributions | |
izing | -0.032 |
yles | -0.032 |
king | -0.031 |
ning | -0.031 |
rily | -0.031 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
am | +0.057 |
ossible | +0.053 |
done | +0.053 |
story | +0.049 |
| +0.048 |
Neg logit contributions | |
izing | -0.071 |
king | -0.064 |
ellery | -0.063 |
yles | -0.063 |
ning | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
am | +0.045 |
done | +0.038 |
| +0.030 |
story | +0.029 |
big | +0.028 |
Neg logit contributions | |
izing | -0.209 |
yles | -0.201 |
king | -0.199 |
ellery | -0.198 |
ning | -0.198 |
Token | She |
Token ID | 1375 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
am | +0.025 |
done | +0.025 |
story | +0.022 |
bad | +0.022 |
big | +0.021 |
Neg logit contributions | |
izing | -0.049 |
yles | -0.047 |
ning | -0.047 |
rily | -0.046 |
ellery | -0.046 |
Token | slowly |
Token ID | 6364 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
am | +0.024 |
done | +0.021 |
| +0.021 |
story | +0.020 |
big | +0.019 |
Neg logit contributions | |
izing | -0.069 |
yles | -0.067 |
ning | -0.066 |
king | -0.066 |
ellery | -0.065 |
Token | walked |
Token ID | 6807 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
am | +0.019 |
done | +0.018 |
| +0.018 |
to | +0.017 |
big | +0.017 |
Neg logit contributions | |
izing | -0.034 |
yles | -0.033 |
ning | -0.032 |
rily | -0.032 |
ellery | -0.032 |
Token | back |
Token ID | 736 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
izing | +0.026 |
king | +0.026 |
rily | +0.026 |
ning | +0.025 |
bing | +0.025 |
Neg logit contributions | |
am | -0.016 |
done | -0.014 |
story | -0.014 |
| -0.012 |
bad | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
izing | +0.014 |
yles | +0.013 |
ning | +0.013 |
king | +0.013 |
bing | +0.013 |
Neg logit contributions | |
am | -0.010 |
done | -0.010 |
| -0.009 |
story | -0.009 |
big | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
izing | +0.041 |
yles | +0.041 |
ellery | +0.040 |
ning | +0.039 |
king | +0.039 |
Neg logit contributions | |
am | -0.019 |
done | -0.016 |
| -0.016 |
story | -0.016 |
to | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
am | +0.054 |
story | +0.044 |
| +0.044 |
| +0.044 |
done | +0.042 |
Neg logit contributions | |
izing | -0.098 |
king | -0.096 |
ning | -0.092 |
yles | -0.091 |
bing | -0.091 |
Token | being |
Token ID | 852 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.013 |
ning | +0.012 |
rily | +0.012 |
king | +0.012 |
Neg logit contributions | |
am | -0.012 |
done | -0.012 |
| -0.012 |
to | -0.011 |
big | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
izing | +0.027 |
yles | +0.027 |
ning | +0.026 |
rily | +0.026 |
ellery | +0.026 |
Neg logit contributions | |
am | -0.013 |
done | -0.013 |
| -0.012 |
big | -0.012 |
to | -0.012 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
am | +0.031 |
done | +0.029 |
story | +0.028 |
| +0.028 |
big | +0.027 |
Neg logit contributions | |
izing | -0.045 |
yles | -0.043 |
king | -0.043 |
ning | -0.043 |
ellery | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
am | +0.059 |
done | +0.050 |
story | +0.047 |
ossible | +0.046 |
big | +0.046 |
Neg logit contributions | |
izing | -0.185 |
yles | -0.176 |
king | -0.175 |
bing | -0.175 |
ning | -0.171 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.022 |
story | +0.017 |
bad | +0.016 |
big | +0.015 |
Neg logit contributions | |
yles | -0.068 |
izing | -0.066 |
ellery | -0.065 |
ksh | -0.064 |
rily | -0.064 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
done | +0.037 |
am | +0.032 |
bad | +0.031 |
own | +0.027 |
tum | +0.027 |
Neg logit contributions | |
yles | -0.094 |
ning | -0.092 |
med | -0.091 |
etti | -0.089 |
rily | -0.088 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
am | +0.044 |
done | +0.038 |
consequences | +0.037 |
learned | +0.036 |
care | +0.033 |
Neg logit contributions | |
yles | -0.078 |
ants | -0.074 |
rily | -0.073 |
izing | -0.072 |
ang | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
am | +0.030 |
done | +0.029 |
story | +0.025 |
way | +0.023 |
bad | +0.022 |
Neg logit contributions | |
yles | -0.064 |
izing | -0.063 |
rily | -0.061 |
king | -0.061 |
ellery | -0.061 |
Token | â |
Token ID | 22940 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
izing | +0.035 |
yles | +0.033 |
ning | +0.033 |
king | +0.033 |
ellery | +0.033 |
Neg logit contributions | |
am | -0.021 |
| -0.020 |
done | -0.020 |
story | -0.018 |
big | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
izing | +0.081 |
ning | +0.076 |
king | +0.076 |
yles | +0.074 |
bing | +0.074 |
Neg logit contributions | |
am | -0.063 |
big | -0.059 |
done | -0.059 |
| -0.058 |
story | -0.057 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
izing | +0.020 |
yles | +0.019 |
ning | +0.019 |
king | +0.019 |
ellery | +0.018 |
Neg logit contributions | |
am | -0.024 |
done | -0.023 |
| -0.022 |
story | -0.022 |
big | -0.021 |
Token | t |
Token ID | 83 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
izing | +0.053 |
yles | +0.051 |
ning | +0.050 |
ellery | +0.050 |
king | +0.050 |
Neg logit contributions | |
am | -0.015 |
done | -0.013 |
| -0.013 |
story | -0.012 |
big | -0.011 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
am | +0.009 |
| +0.008 |
done | +0.008 |
story | +0.008 |
big | +0.007 |
Neg logit contributions | |
izing | -0.017 |
yles | -0.017 |
ning | -0.017 |
king | -0.017 |
rily | -0.016 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
am | +0.024 |
done | +0.019 |
| +0.018 |
story | +0.017 |
big | +0.017 |
Neg logit contributions | |
izing | -0.082 |
ning | -0.080 |
king | -0.077 |
yles | -0.077 |
ting | -0.076 |
Token | ! |
Token ID | 0 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
am | +0.052 |
done | +0.046 |
story | +0.038 |
| +0.037 |
big | +0.037 |
Neg logit contributions | |
izing | -0.198 |
ning | -0.188 |
yles | -0.188 |
king | -0.187 |
rily | -0.185 |
Token | It |
Token ID | 632 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
done | +0.014 |
am | +0.013 |
story | +0.010 |
bad | +0.008 |
big | +0.007 |
Neg logit contributions | |
izing | -0.106 |
yles | -0.104 |
ning | -0.103 |
rily | -0.101 |
king | -0.100 |
Token | was |
Token ID | 373 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
am | +0.006 |
done | +0.006 |
| +0.005 |
story | +0.005 |
ossible | +0.005 |
Neg logit contributions | |
izing | -0.031 |
ning | -0.030 |
yles | -0.029 |
bul | -0.029 |
bing | -0.028 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
am | +0.004 |
| +0.003 |
story | +0.003 |
done | +0.003 |
ossible | +0.003 |
Neg logit contributions | |
izing | -0.008 |
ning | -0.008 |
yles | -0.008 |
rily | -0.008 |
ellery | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
am | +0.028 |
done | +0.024 |
| +0.023 |
story | +0.022 |
big | +0.021 |
Neg logit contributions | |
izing | -0.066 |
ning | -0.064 |
king | -0.062 |
yles | -0.062 |
rily | -0.062 |
Token | his |
Token ID | 465 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
izing | +0.055 |
bing | +0.052 |
yles | +0.052 |
ning | +0.051 |
rily | +0.051 |
Neg logit contributions | |
am | -0.035 |
story | -0.032 |
| -0.029 |
done | -0.029 |
ossible | -0.028 |
Token | hunger |
Token ID | 16460 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
am | +0.047 |
done | +0.043 |
| +0.043 |
| +0.040 |
ossible | +0.038 |
Neg logit contributions | |
izing | -0.062 |
ning | -0.059 |
burn | -0.059 |
rily | -0.059 |
bing | -0.059 |
Token | began |
Token ID | 2540 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
am | +0.019 |
| +0.017 |
ossible | +0.016 |
story | +0.016 |
done | +0.016 |
Neg logit contributions | |
izing | -0.047 |
rily | -0.044 |
ning | -0.044 |
king | -0.044 |
bing | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
am | +0.026 |
done | +0.019 |
| +0.016 |
story | +0.016 |
ossible | +0.015 |
Neg logit contributions | |
ning | -0.102 |
izing | -0.100 |
king | -0.100 |
bing | -0.098 |
rily | -0.098 |
Token | sub |
Token ID | 850 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
izing | +0.004 |
ning | +0.004 |
burn | +0.004 |
rily | +0.004 |
king | +0.004 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
| -0.003 |
story | -0.002 |
to | -0.002 |
Token | side |
Token ID | 1589 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
izing | +0.078 |
yles | +0.078 |
ants | +0.076 |
ellery | +0.075 |
ning | +0.075 |
Neg logit contributions | |
| -0.051 |
am | -0.048 |
done | -0.047 |
to | -0.045 |
big | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
am | +0.062 |
done | +0.046 |
ossible | +0.040 |
| +0.039 |
| +0.038 |
Neg logit contributions | |
izing | -0.196 |
bing | -0.185 |
ning | -0.184 |
rily | -0.184 |
king | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.018 |
story | +0.016 |
bad | +0.014 |
big | +0.014 |
Neg logit contributions | |
izing | -0.073 |
yles | -0.071 |
ning | -0.071 |
rily | -0.070 |
king | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.007 |
bad | +0.005 |
story | +0.004 |
way | +0.004 |
Neg logit contributions | |
izing | -0.041 |
yles | -0.040 |
ants | -0.040 |
rily | -0.040 |
bing | -0.040 |
Token | When |
Token ID | 2215 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
yles | +0.033 |
ning | +0.032 |
ellery | +0.032 |
izing | +0.032 |
ries | +0.032 |
Neg logit contributions | |
| -0.021 |
am | -0.021 |
big | -0.019 |
done | -0.019 |
story | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
am | +0.024 |
done | +0.021 |
story | +0.020 |
| +0.020 |
own | +0.019 |
Neg logit contributions | |
izing | -0.042 |
ning | -0.040 |
yles | -0.040 |
rily | -0.039 |
bing | -0.038 |
Token | â |
Token ID | 22940 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
am | +0.043 |
done | +0.043 |
story | +0.040 |
| +0.039 |
big | +0.038 |
Neg logit contributions | |
izing | -0.058 |
yles | -0.055 |
ning | -0.055 |
rily | -0.054 |
bing | -0.053 |
Token | € |
Token ID | 26391 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
izing | +0.103 |
ellery | +0.096 |
king | +0.095 |
yles | +0.094 |
ning | +0.094 |
Neg logit contributions | |
am | -0.081 |
big | -0.078 |
| -0.078 |
story | -0.076 |
to | -0.076 |
Token | ™ |
Token ID | 8151 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
am | +0.009 |
done | +0.008 |
bad | +0.008 |
story | +0.008 |
big | +0.008 |
Neg logit contributions | |
yles | -0.007 |
izing | -0.006 |
ellery | -0.006 |
king | -0.006 |
ning | -0.006 |
Token | t |
Token ID | 83 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
izing | +0.003 |
yles | +0.003 |
king | +0.003 |
ning | +0.003 |
ants | +0.003 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
story | -0.001 |
bad | -0.001 |
big | -0.001 |
Token | run |
Token ID | 1057 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
done | +0.013 |
am | +0.012 |
story | +0.012 |
ossible | +0.011 |
| +0.011 |
Neg logit contributions | |
izing | -0.023 |
king | -0.023 |
ivating | -0.022 |
yles | -0.022 |
rily | -0.022 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
izing | +0.032 |
king | +0.030 |
ning | +0.029 |
rily | +0.029 |
ivating | +0.029 |
Neg logit contributions | |
am | -0.018 |
story | -0.017 |
done | -0.017 |
ossible | -0.016 |
| -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
am | +0.049 |
done | +0.042 |
story | +0.035 |
| +0.033 |
ossible | +0.032 |
Neg logit contributions | |
izing | -0.200 |
yles | -0.193 |
king | -0.191 |
ning | -0.191 |
ellery | -0.190 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
done | +0.028 |
am | +0.027 |
story | +0.023 |
bad | +0.019 |
time | +0.018 |
Neg logit contributions | |
rily | -0.058 |
izing | -0.057 |
ting | -0.057 |
ivating | -0.056 |
yles | -0.056 |
Token | he |
Token ID | 339 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
am | +0.028 |
done | +0.026 |
story | +0.023 |
own | +0.021 |
whole | +0.020 |
Neg logit contributions | |
izing | -0.052 |
ting | -0.051 |
rily | -0.049 |
bing | -0.047 |
yles | -0.046 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
am | +0.031 |
done | +0.027 |
story | +0.027 |
| +0.027 |
bad | +0.024 |
Neg logit contributions | |
izing | -0.059 |
ning | -0.058 |
yles | -0.058 |
king | -0.058 |
ellery | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
am | +0.015 |
done | +0.014 |
story | +0.013 |
| +0.012 |
time | +0.012 |
Neg logit contributions | |
izing | -0.034 |
ning | -0.034 |
king | -0.033 |
yles | -0.033 |
bing | -0.033 |
Token | but |
Token ID | 475 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
izing | +0.044 |
king | +0.041 |
yles | +0.041 |
ning | +0.041 |
rily | +0.041 |
Neg logit contributions | |
am | -0.030 |
done | -0.027 |
story | -0.026 |
| -0.026 |
big | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.020 |
story | +0.020 |
| +0.019 |
big | +0.019 |
Neg logit contributions | |
izing | -0.028 |
yles | -0.027 |
rily | -0.027 |
ellery | -0.026 |
bing | -0.025 |
Token | followed |
Token ID | 3940 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
am | +0.037 |
done | +0.032 |
| +0.032 |
story | +0.031 |
big | +0.030 |
Neg logit contributions | |
izing | -0.073 |
yles | -0.070 |
ning | -0.069 |
rily | -0.069 |
king | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
izing | +0.022 |
yles | +0.022 |
ning | +0.021 |
rily | +0.021 |
ellery | +0.021 |
Neg logit contributions | |
am | -0.012 |
done | -0.011 |
| -0.010 |
story | -0.010 |
big | -0.009 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
am | +0.055 |
done | +0.047 |
| +0.044 |
| +0.044 |
'm | +0.043 |
Neg logit contributions | |
izing | -0.063 |
bing | -0.062 |
rily | -0.061 |
yles | -0.061 |
ning | -0.059 |
Token | anyway |
Token ID | 6949 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
am | +0.016 |
done | +0.014 |
| +0.013 |
story | +0.012 |
big | +0.012 |
Neg logit contributions | |
izing | -0.048 |
yles | -0.047 |
ning | -0.046 |
king | -0.046 |
rily | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
am | +0.056 |
done | +0.042 |
story | +0.036 |
| +0.036 |
big | +0.033 |
Neg logit contributions | |
izing | -0.199 |
rily | -0.190 |
king | -0.188 |
ning | -0.185 |
bing | -0.184 |
Token | She |
Token ID | 1375 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
am | +0.039 |
done | +0.039 |
bad | +0.036 |
story | +0.034 |
big | +0.033 |
Neg logit contributions | |
rily | -0.069 |
yles | -0.068 |
izing | -0.068 |
ning | -0.067 |
ants | -0.067 |
Token | threw |
Token ID | 9617 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
am | +0.032 |
done | +0.028 |
| +0.028 |
story | +0.027 |
big | +0.025 |
Neg logit contributions | |
izing | -0.068 |
yles | -0.066 |
ning | -0.066 |
king | -0.065 |
rily | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
izing | +0.112 |
yles | +0.108 |
king | +0.106 |
ning | +0.106 |
ellery | +0.106 |
Neg logit contributions | |
am | -0.034 |
| -0.032 |
done | -0.030 |
big | -0.030 |
to | -0.029 |
Token | salt |
Token ID | 8268 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
am | +0.005 |
| +0.004 |
done | +0.004 |
He | +0.004 |
story | +0.004 |
Neg logit contributions | |
izing | -0.005 |
king | -0.005 |
ning | -0.005 |
rily | -0.004 |
chick | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
izing | +0.033 |
yles | +0.032 |
ning | +0.031 |
ellery | +0.031 |
rily | +0.031 |
Neg logit contributions | |
am | -0.020 |
done | -0.018 |
| -0.018 |
story | -0.017 |
big | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
am | +0.051 |
| +0.045 |
| +0.045 |
done | +0.043 |
time | +0.043 |
Neg logit contributions | |
izing | -0.101 |
ellery | -0.098 |
ants | -0.096 |
yles | -0.096 |
rily | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
am | +0.004 |
| +0.003 |
done | +0.003 |
story | +0.002 |
big | +0.001 |
Neg logit contributions | |
izing | -0.045 |
yles | -0.043 |
ning | -0.043 |
king | -0.043 |
ellery | -0.043 |
Token | be |
Token ID | 307 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
izing | +0.058 |
yles | +0.056 |
ning | +0.055 |
rily | +0.055 |
king | +0.054 |
Neg logit contributions | |
am | -0.036 |
done | -0.033 |
| -0.033 |
story | -0.031 |
big | -0.031 |
Token | upset |
Token ID | 9247 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
izing | +0.026 |
yles | +0.025 |
ning | +0.024 |
king | +0.024 |
ellery | +0.024 |
Neg logit contributions | |
am | -0.015 |
done | -0.014 |
| -0.014 |
story | -0.013 |
big | -0.013 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
am | +0.026 |
done | +0.023 |
story | +0.022 |
ossible | +0.021 |
| +0.021 |
Neg logit contributions | |
izing | -0.065 |
ning | -0.062 |
king | -0.061 |
yles | -0.061 |
bing | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
am | +0.051 |
done | +0.043 |
story | +0.037 |
big | +0.036 |
ossible | +0.034 |
Neg logit contributions | |
izing | -0.198 |
yles | -0.188 |
bing | -0.187 |
king | -0.187 |
ning | -0.186 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.026 |
story | +0.024 |
big | +0.023 |
bad | +0.023 |
Neg logit contributions | |
izing | -0.037 |
yles | -0.036 |
ning | -0.035 |
ants | -0.035 |
ellery | -0.034 |
Token | my |
Token ID | 1820 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ning | +0.020 |
burn | +0.019 |
izing | +0.019 |
king | +0.019 |
ellery | +0.018 |
Neg logit contributions | |
am | -0.031 |
| -0.028 |
big | -0.027 |
bad | -0.027 |
done | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
am | +0.009 |
done | +0.007 |
| +0.007 |
story | +0.006 |
time | +0.006 |
Neg logit contributions | |
izing | -0.030 |
ning | -0.029 |
king | -0.029 |
bing | -0.028 |
rily | -0.028 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
story | +0.006 |
| +0.006 |
time | +0.005 |
Neg logit contributions | |
izing | -0.015 |
yles | -0.014 |
ning | -0.014 |
king | -0.014 |
ellery | -0.014 |
Token | But |
Token ID | 887 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
am | +0.019 |
done | +0.017 |
story | +0.015 |
bad | +0.015 |
big | +0.014 |
Neg logit contributions | |
izing | -0.032 |
rily | -0.032 |
ning | -0.032 |
yles | -0.032 |
ksh | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
am | +0.009 |
done | +0.008 |
story | +0.008 |
| +0.008 |
big | +0.007 |
Neg logit contributions | |
izing | -0.010 |
yles | -0.009 |
ning | -0.009 |
king | -0.009 |
bing | -0.009 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
am | +0.037 |
| +0.035 |
| +0.032 |
done | +0.032 |
He | +0.031 |
Neg logit contributions | |
ning | -0.054 |
bing | -0.053 |
izing | -0.052 |
ellery | -0.052 |
yles | -0.052 |
Token | found |
Token ID | 1043 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
am | +0.016 |
story | +0.014 |
| +0.014 |
done | +0.013 |
big | +0.013 |
Neg logit contributions | |
izing | -0.038 |
ning | -0.037 |
king | -0.037 |
yles | -0.037 |
ting | -0.036 |
Token | him |
Token ID | 683 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
izing | +0.033 |
ning | +0.033 |
yles | +0.032 |
ellery | +0.032 |
rily | +0.032 |
Neg logit contributions | |
am | -0.018 |
story | -0.016 |
done | -0.016 |
| -0.016 |
ossible | -0.014 |
Token | anyways |
Token ID | 32845 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
am | +0.039 |
| +0.034 |
done | +0.033 |
story | +0.032 |
ossible | +0.031 |
Neg logit contributions | |
izing | -0.070 |
ning | -0.069 |
king | -0.068 |
ellery | -0.067 |
bing | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
am | +0.077 |
ossible | +0.068 |
| +0.064 |
done | +0.063 |
story | +0.062 |
Neg logit contributions | |
izing | -0.155 |
rily | -0.147 |
ning | -0.144 |
king | -0.144 |
bing | -0.141 |
Token | |
Token ID | 220 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
am | +0.022 |
done | +0.021 |
story | +0.018 |
bad | +0.018 |
big | +0.017 |
Neg logit contributions | |
izing | -0.052 |
yles | -0.051 |
ning | -0.050 |
rily | -0.050 |
king | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
am | +0.019 |
done | +0.017 |
story | +0.015 |
bad | +0.013 |
big | +0.010 |
Neg logit contributions | |
yles | -0.134 |
izing | -0.132 |
ning | -0.132 |
ants | -0.131 |
rily | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.007 |
bad | +0.005 |
story | +0.004 |
big | +0.003 |
Neg logit contributions | |
izing | -0.047 |
yles | -0.047 |
ants | -0.046 |
bing | -0.046 |
ning | -0.045 |
Token | They |
Token ID | 2990 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
izing | +0.028 |
yles | +0.028 |
ning | +0.027 |
ellery | +0.027 |
rily | +0.027 |
Neg logit contributions | |
am | -0.020 |
| -0.019 |
done | -0.018 |
big | -0.017 |
story | -0.017 |
Token | together |
Token ID | 1978 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
izing | +0.003 |
king | +0.003 |
rily | +0.003 |
bing | +0.003 |
ning | +0.003 |
Neg logit contributions | |
am | -0.003 |
done | -0.002 |
story | -0.002 |
| -0.002 |
bad | -0.002 |
Token | side |
Token ID | 1735 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
am | +0.052 |
done | +0.044 |
story | +0.042 |
| +0.041 |
bad | +0.039 |
Neg logit contributions | |
izing | -0.120 |
king | -0.117 |
ning | -0.117 |
bing | -0.115 |
yles | -0.115 |
Token | - |
Token ID | 12 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
am | +0.017 |
done | +0.014 |
| +0.013 |
story | +0.012 |
big | +0.011 |
Neg logit contributions | |
izing | -0.083 |
yles | -0.080 |
ning | -0.080 |
king | -0.079 |
ellery | -0.079 |
Token | by |
Token ID | 1525 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
izing | +0.105 |
yles | +0.100 |
ning | +0.098 |
rily | +0.098 |
ellery | +0.097 |
Neg logit contributions | |
am | -0.094 |
done | -0.089 |
| -0.089 |
story | -0.084 |
to | -0.083 |
Token | - |
Token ID | 12 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
am | +0.037 |
done | +0.033 |
| +0.032 |
story | +0.031 |
big | +0.029 |
Neg logit contributions | |
izing | -0.083 |
king | -0.080 |
yles | -0.080 |
ning | -0.080 |
ellery | -0.078 |
Token | side |
Token ID | 1589 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
izing | +0.110 |
yles | +0.105 |
rily | +0.103 |
ning | +0.103 |
ellery | +0.102 |
Neg logit contributions | |
am | -0.096 |
done | -0.091 |
| -0.091 |
to | -0.086 |
story | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
am | +0.065 |
done | +0.047 |
story | +0.042 |
ossible | +0.040 |
'm | +0.040 |
Neg logit contributions | |
izing | -0.193 |
king | -0.180 |
bing | -0.180 |
ning | -0.179 |
rily | -0.176 |
Token | |
Token ID | 220 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
am | +0.024 |
done | +0.022 |
bad | +0.020 |
big | +0.019 |
story | +0.019 |
Neg logit contributions | |
yles | -0.063 |
izing | -0.062 |
ellery | -0.061 |
ning | -0.061 |
ants | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
am | +0.016 |
done | +0.014 |
story | +0.012 |
bad | +0.011 |
big | +0.008 |
Neg logit contributions | |
yles | -0.126 |
izing | -0.124 |
ning | -0.124 |
ants | -0.124 |
king | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
am | +0.006 |
done | +0.005 |
bad | +0.004 |
story | +0.003 |
big | +0.003 |
Neg logit contributions | |
yles | -0.053 |
izing | -0.053 |
ants | -0.051 |
ning | -0.051 |
rily | -0.051 |
Token | No |
Token ID | 2949 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.012 |
ning | +0.012 |
king | +0.012 |
rily | +0.012 |
Neg logit contributions | |
am | -0.011 |
| -0.010 |
done | -0.010 |
story | -0.010 |
big | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
am | +0.024 |
story | +0.022 |
He | +0.020 |
| +0.020 |
big | +0.019 |
Neg logit contributions | |
izing | -0.043 |
king | -0.042 |
yles | -0.041 |
ning | -0.041 |
ellery | -0.041 |
Token | refused |
Token ID | 6520 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
izing | +0.058 |
yles | +0.057 |
ning | +0.056 |
ellery | +0.056 |
bul | +0.055 |
Neg logit contributions | |
am | -0.031 |
| -0.029 |
story | -0.029 |
done | -0.028 |
| -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
am | +0.028 |
ossible | +0.023 |
done | +0.021 |
story | +0.021 |
| +0.020 |
Neg logit contributions | |
izing | -0.088 |
ning | -0.083 |
king | -0.082 |
ellery | -0.081 |
yles | -0.081 |
Token | be |
Token ID | 307 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
izing | +0.036 |
king | +0.034 |
ning | +0.034 |
yles | +0.034 |
ellery | +0.033 |
Neg logit contributions | |
am | -0.017 |
| -0.016 |
done | -0.016 |
story | -0.014 |
big | -0.014 |
Token | miserable |
Token ID | 22444 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
izing | +0.024 |
king | +0.023 |
ning | +0.023 |
yles | +0.023 |
ellery | +0.023 |
Neg logit contributions | |
am | -0.017 |
| -0.015 |
story | -0.015 |
done | -0.014 |
ossible | -0.014 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
am | +0.019 |
done | +0.017 |
story | +0.016 |
| +0.016 |
ossible | +0.015 |
Neg logit contributions | |
izing | -0.051 |
ning | -0.048 |
yles | -0.048 |
king | -0.048 |
rily | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
am | +0.053 |
done | +0.047 |
big | +0.039 |
ossible | +0.038 |
story | +0.038 |
Neg logit contributions | |
izing | -0.190 |
yles | -0.179 |
bing | -0.178 |
king | -0.178 |
ning | -0.178 |
Token | |
Token ID | 220 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
done | +0.027 |
am | +0.025 |
bad | +0.023 |
big | +0.022 |
story | +0.020 |
Neg logit contributions | |
yles | -0.068 |
izing | -0.068 |
ellery | -0.067 |
ning | -0.066 |
bul | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
am | +0.014 |
done | +0.011 |
story | +0.009 |
bad | +0.007 |
big | +0.006 |
Neg logit contributions | |
izing | -0.138 |
yles | -0.137 |
ning | -0.136 |
ants | -0.134 |
king | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
done | +0.010 |
am | +0.010 |
bad | +0.008 |
way | +0.007 |
time | +0.007 |
Neg logit contributions | |
izing | -0.050 |
yles | -0.049 |
bing | -0.048 |
ning | -0.048 |
ants | -0.048 |
Token | The |
Token ID | 464 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
izing | +0.018 |
yles | +0.018 |
ning | +0.017 |
king | +0.017 |
rily | +0.017 |
Neg logit contributions | |
am | -0.014 |
| -0.014 |
done | -0.013 |
story | -0.013 |
big | -0.012 |
Token | t |
Token ID | 83 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
izing | +0.022 |
yles | +0.022 |
ning | +0.022 |
king | +0.021 |
rily | +0.021 |
Neg logit contributions | |
am | -0.007 |
done | -0.006 |
| -0.006 |
story | -0.006 |
big | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
am | +0.004 |
| +0.004 |
done | +0.004 |
story | +0.004 |
ossible | +0.004 |
Neg logit contributions | |
izing | -0.009 |
burn | -0.009 |
king | -0.009 |
ning | -0.009 |
shadow | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
am | +0.007 |
story | +0.005 |
| +0.005 |
done | +0.004 |
He | +0.004 |
Neg logit contributions | |
ellery | -0.021 |
ning | -0.021 |
yles | -0.021 |
izing | -0.020 |
burn | -0.020 |
Token | be |
Token ID | 307 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
izing | +0.029 |
burn | +0.028 |
ning | +0.027 |
ellery | +0.027 |
king | +0.027 |
Neg logit contributions | |
am | -0.015 |
| -0.014 |
done | -0.014 |
| -0.013 |
story | -0.013 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
izing | +0.018 |
ning | +0.017 |
yles | +0.017 |
king | +0.017 |
ellery | +0.017 |
Neg logit contributions | |
am | -0.010 |
| -0.009 |
done | -0.009 |
story | -0.009 |
big | -0.008 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
am | +0.011 |
done | +0.010 |
| +0.009 |
story | +0.009 |
big | +0.008 |
Neg logit contributions | |
izing | -0.041 |
ning | -0.039 |
yles | -0.039 |
king | -0.039 |
rily | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
am | +0.046 |
done | +0.040 |
story | +0.032 |
| +0.032 |
big | +0.032 |
Neg logit contributions | |
izing | -0.198 |
yles | -0.190 |
ning | -0.189 |
king | -0.189 |
ellery | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
am | +0.026 |
done | +0.024 |
bad | +0.020 |
story | +0.019 |
big | +0.018 |
Neg logit contributions | |
yles | -0.071 |
izing | -0.071 |
ning | -0.069 |
rily | -0.069 |
ellery | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
am | +0.010 |
done | +0.010 |
bad | +0.008 |
consequences | +0.008 |
way | +0.007 |
Neg logit contributions | |
izing | -0.035 |
yles | -0.035 |
bing | -0.034 |
ants | -0.034 |
shadow | -0.034 |
Token | But |
Token ID | 1537 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
izing | +0.036 |
yles | +0.035 |
ning | +0.035 |
rily | +0.034 |
king | +0.034 |
Neg logit contributions | |
am | -0.035 |
| -0.034 |
done | -0.033 |
big | -0.032 |
story | -0.032 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
am | +0.010 |
| +0.009 |
done | +0.009 |
story | +0.009 |
to | +0.009 |
Neg logit contributions | |
izing | -0.010 |
yles | -0.009 |
ning | -0.009 |
king | -0.009 |
ellery | -0.009 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
izing | +0.052 |
yles | +0.050 |
ning | +0.050 |
king | +0.049 |
rily | +0.049 |
Neg logit contributions | |
am | -0.029 |
story | -0.025 |
done | -0.025 |
| -0.025 |
big | -0.023 |
Token | 't |
Token ID | 470 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
am | +0.021 |
| +0.019 |
done | +0.019 |
story | +0.018 |
big | +0.018 |
Neg logit contributions | |
izing | -0.036 |
yles | -0.035 |
ning | -0.035 |
king | -0.034 |
ellery | -0.034 |
Token | want |
Token ID | 765 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
am | +0.008 |
| +0.008 |
done | +0.008 |
story | +0.007 |
big | +0.007 |
Neg logit contributions | |
izing | -0.019 |
yles | -0.019 |
ellery | -0.019 |
rily | -0.018 |
king | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
am | +0.013 |
done | +0.012 |
ossible | +0.010 |
story | +0.009 |
learned | +0.008 |
Neg logit contributions | |
ning | -0.049 |
ellery | -0.049 |
burn | -0.048 |
izing | -0.048 |
yles | -0.048 |
Token | wait |
Token ID | 4043 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
izing | +0.030 |
yles | +0.029 |
ning | +0.029 |
ellery | +0.029 |
burn | +0.029 |
Neg logit contributions | |
am | -0.015 |
done | -0.014 |
| -0.013 |
story | -0.013 |
to | -0.012 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
am | +0.034 |
story | +0.026 |
done | +0.024 |
| +0.024 |
learned | +0.023 |
Neg logit contributions | |
izing | -0.087 |
rily | -0.086 |
king | -0.084 |
ning | -0.083 |
yles | -0.083 |
Token | ! |
Token ID | 0 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
am | +0.046 |
done | +0.037 |
story | +0.031 |
| +0.030 |
big | +0.030 |
Neg logit contributions | |
izing | -0.197 |
yles | -0.194 |
ning | -0.192 |
king | -0.191 |
ellery | -0.191 |
Token | |
Token ID | 220 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
done | +0.016 |
am | +0.016 |
story | +0.014 |
bad | +0.013 |
big | +0.013 |
Neg logit contributions | |
rily | -0.027 |
yles | -0.027 |
izing | -0.027 |
ning | -0.027 |
ender | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
done | +0.018 |
am | +0.016 |
bad | +0.014 |
story | +0.014 |
learned | +0.010 |
Neg logit contributions | |
yles | -0.089 |
ning | -0.087 |
ants | -0.087 |
rily | -0.087 |
izing | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
done | +0.005 |
am | +0.004 |
bad | +0.003 |
story | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
yles | -0.021 |
izing | -0.021 |
rily | -0.020 |
shadow | -0.020 |
ning | -0.020 |
Token | But |
Token ID | 1537 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
izing | +0.040 |
yles | +0.039 |
ning | +0.038 |
ellery | +0.038 |
king | +0.038 |
Neg logit contributions | |
am | -0.037 |
| -0.035 |
done | -0.034 |
story | -0.033 |
big | -0.033 |
Token | play |
Token ID | 711 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
am | +0.009 |
done | +0.008 |
| +0.008 |
story | +0.007 |
big | +0.007 |
Neg logit contributions | |
izing | -0.020 |
yles | -0.019 |
ning | -0.019 |
king | -0.019 |
ellery | -0.019 |
Token | side |
Token ID | 1735 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
am | +0.003 |
done | +0.003 |
story | +0.002 |
ossible | +0.002 |
| +0.002 |
Neg logit contributions | |
izing | -0.005 |
bing | -0.005 |
ning | -0.005 |
king | -0.005 |
rily | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
| +0.006 |
story | +0.006 |
big | +0.005 |
Neg logit contributions | |
izing | -0.024 |
yles | -0.023 |
ning | -0.023 |
king | -0.023 |
ellery | -0.023 |
Token | by |
Token ID | 1525 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
izing | +0.119 |
yles | +0.114 |
ning | +0.112 |
king | +0.111 |
ellery | +0.110 |
Neg logit contributions | |
am | -0.115 |
done | -0.108 |
| -0.108 |
story | -0.105 |
big | -0.102 |
Token | - |
Token ID | 12 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.023 |
| +0.022 |
story | +0.021 |
bad | +0.020 |
Neg logit contributions | |
izing | -0.068 |
king | -0.066 |
yles | -0.066 |
ning | -0.066 |
bing | -0.065 |
Token | side |
Token ID | 1589 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
izing | +0.122 |
yles | +0.117 |
ning | +0.115 |
king | +0.114 |
ellery | +0.113 |
Neg logit contributions | |
am | -0.109 |
done | -0.102 |
| -0.102 |
story | -0.099 |
big | -0.096 |
Token | with |
Token ID | 351 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
am | +0.068 |
done | +0.051 |
bad | +0.045 |
'm | +0.044 |
| +0.044 |
Neg logit contributions | |
izing | -0.186 |
bing | -0.176 |
ning | -0.173 |
king | -0.173 |
rily | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
izing | +0.018 |
yles | +0.018 |
ning | +0.017 |
king | +0.017 |
ellery | +0.017 |
Neg logit contributions | |
am | -0.006 |
| -0.006 |
done | -0.006 |
big | -0.005 |
story | -0.005 |
Token | infant |
Token ID | 11212 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
am | +0.028 |
| +0.026 |
done | +0.025 |
story | +0.024 |
ossible | +0.022 |
Neg logit contributions | |
izing | -0.039 |
yles | -0.038 |
rily | -0.038 |
ning | -0.038 |
king | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
am | +0.003 |
done | +0.002 |
| +0.002 |
story | +0.002 |
bad | +0.002 |
Neg logit contributions | |
izing | -0.007 |
ning | -0.007 |
yles | -0.007 |
king | -0.007 |
ellery | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.021 |
story | +0.019 |
bad | +0.018 |
big | +0.018 |
Neg logit contributions | |
izing | -0.058 |
yles | -0.057 |
ning | -0.056 |
rily | -0.056 |
king | -0.055 |
Token | her |
Token ID | 607 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
izing | +0.033 |
yles | +0.032 |
ning | +0.032 |
king | +0.031 |
ellery | +0.031 |
Neg logit contributions | |
am | -0.015 |
| -0.015 |
done | -0.014 |
to | -0.013 |
big | -0.013 |
Token | too |
Token ID | 1165 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.024 |
| +0.024 |
story | +0.022 |
big | +0.021 |
Neg logit contributions | |
izing | -0.072 |
yles | -0.070 |
ning | -0.069 |
king | -0.069 |
ellery | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
am | +0.062 |
done | +0.050 |
story | +0.046 |
| +0.045 |
| +0.040 |
Neg logit contributions | |
izing | -0.169 |
king | -0.161 |
rily | -0.159 |
ning | -0.157 |
yles | -0.157 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
izing | +0.044 |
yles | +0.043 |
ning | +0.042 |
ellery | +0.042 |
king | +0.042 |
Neg logit contributions | |
am | -0.020 |
done | -0.018 |
| -0.017 |
story | -0.017 |
big | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
izing | +0.032 |
yles | +0.031 |
ning | +0.031 |
king | +0.030 |
ellery | +0.030 |
Neg logit contributions | |
am | -0.015 |
| -0.014 |
done | -0.014 |
story | -0.013 |
big | -0.013 |
Token | too |
Token ID | 1165 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
am | +0.026 |
done | +0.024 |
| +0.023 |
story | +0.021 |
big | +0.020 |
Neg logit contributions | |
izing | -0.070 |
yles | -0.067 |
ning | -0.067 |
king | -0.066 |
rily | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
am | +0.049 |
done | +0.038 |
story | +0.032 |
| +0.029 |
ossible | +0.025 |
Neg logit contributions | |
izing | -0.199 |
king | -0.190 |
rily | -0.189 |
yles | -0.187 |
ellery | -0.186 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
am | +0.028 |
done | +0.026 |
bad | +0.023 |
story | +0.022 |
big | +0.022 |
Neg logit contributions | |
yles | -0.067 |
izing | -0.067 |
ning | -0.065 |
ellery | -0.065 |
rily | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
am | +0.008 |
done | +0.007 |
bad | +0.006 |
way | +0.005 |
felt | +0.004 |
Neg logit contributions | |
yles | -0.033 |
ants | -0.032 |
izing | -0.032 |
bing | -0.031 |
rily | -0.031 |
Token | Jack |
Token ID | 14295 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
izing | +0.025 |
ning | +0.024 |
yles | +0.024 |
king | +0.024 |
rily | +0.024 |
Neg logit contributions | |
am | -0.021 |
| -0.021 |
done | -0.020 |
story | -0.019 |
big | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
am | +0.005 |
done | +0.005 |
| +0.005 |
story | +0.004 |
big | +0.004 |
Neg logit contributions | |
izing | -0.015 |
ning | -0.015 |
yles | -0.015 |
king | -0.015 |
ellery | -0.014 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
yles | +0.003 |
izing | +0.003 |
king | +0.003 |
ning | +0.003 |
ellery | +0.003 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
bad | -0.003 |
big | -0.003 |
story | -0.003 |
Token | t |
Token ID | 83 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
izing | +0.011 |
ning | +0.011 |
yles | +0.011 |
king | +0.010 |
ants | +0.010 |
Neg logit contributions | |
am | -0.004 |
done | -0.004 |
story | -0.004 |
| -0.003 |
big | -0.003 |
Token | feel |
Token ID | 1254 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
am | +0.007 |
| +0.007 |
ossible | +0.007 |
| +0.007 |
done | +0.007 |
Neg logit contributions | |
izing | -0.014 |
burn | -0.013 |
king | -0.013 |
shadow | -0.013 |
ning | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
ossible | +0.016 |
am | +0.015 |
story | +0.014 |
done | +0.014 |
| +0.012 |
Neg logit contributions | |
izing | -0.022 |
rily | -0.021 |
ting | -0.020 |
ivating | -0.020 |
king | -0.020 |
Token | alone |
Token ID | 3436 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
izing | +0.012 |
ivating | +0.011 |
rily | +0.011 |
bly | +0.011 |
bing | +0.011 |
Neg logit contributions | |
am | -0.008 |
ossible | -0.007 |
story | -0.007 |
done | -0.007 |
| -0.007 |
Token | anymore |
Token ID | 7471 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.018 |
ossible | +0.018 |
story | +0.017 |
| +0.016 |
Neg logit contributions | |
izing | -0.062 |
ning | -0.060 |
rily | -0.059 |
ting | -0.059 |
king | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
am | +0.056 |
done | +0.050 |
big | +0.042 |
ossible | +0.042 |
story | +0.039 |
Neg logit contributions | |
izing | -0.184 |
yles | -0.174 |
rily | -0.173 |
king | -0.173 |
ning | -0.173 |
Token | He |
Token ID | 679 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
done | +0.022 |
am | +0.022 |
bad | +0.019 |
big | +0.019 |
story | +0.017 |
Neg logit contributions | |
izing | -0.045 |
ning | -0.044 |
yles | -0.043 |
ellery | -0.043 |
bul | -0.043 |
Token | â |
Token ID | 22940 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.024 |
| +0.023 |
story | +0.022 |
big | +0.021 |
Neg logit contributions | |
izing | -0.052 |
ning | -0.052 |
yles | -0.051 |
ellery | -0.050 |
rily | -0.050 |
Token | € |
Token ID | 26391 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
izing | +0.067 |
king | +0.061 |
ning | +0.061 |
bing | +0.058 |
ellery | +0.058 |
Neg logit contributions | |
am | -0.080 |
big | -0.079 |
| -0.077 |
story | -0.076 |
to | -0.075 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
am | +0.002 |
bad | +0.002 |
done | +0.002 |
big | +0.002 |
time | +0.002 |
Neg logit contributions | |
yles | -0.003 |
izing | -0.003 |
ellery | -0.003 |
king | -0.003 |
ning | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
am | +0.046 |
done | +0.037 |
ossible | +0.037 |
'm | +0.036 |
whole | +0.036 |
Neg logit contributions | |
izing | -0.070 |
ning | -0.064 |
bing | -0.063 |
king | -0.062 |
ting | -0.061 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
izing | +0.062 |
ning | +0.060 |
king | +0.059 |
yles | +0.059 |
rily | +0.057 |
Neg logit contributions | |
am | -0.037 |
story | -0.032 |
| -0.032 |
done | -0.031 |
big | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
am | +0.021 |
story | +0.017 |
done | +0.015 |
ossible | +0.015 |
time | +0.013 |
Neg logit contributions | |
izing | -0.059 |
shadow | -0.058 |
ning | -0.057 |
king | -0.057 |
ellery | -0.055 |
Token | take |
Token ID | 1011 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
| +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.002 |
ning | -0.002 |
burn | -0.002 |
yles | -0.002 |
rily | -0.002 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
izing | +0.072 |
yles | +0.070 |
ning | +0.070 |
ellery | +0.068 |
king | +0.068 |
Neg logit contributions | |
am | -0.050 |
done | -0.046 |
| -0.045 |
story | -0.044 |
big | -0.041 |
Token | anyway |
Token ID | 6949 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
am | +0.022 |
done | +0.018 |
story | +0.016 |
| +0.015 |
grown | +0.015 |
Neg logit contributions | |
ning | -0.057 |
king | -0.056 |
ellery | -0.055 |
burn | -0.054 |
bing | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
am | +0.060 |
done | +0.048 |
story | +0.041 |
| +0.040 |
| +0.039 |
Neg logit contributions | |
izing | -0.182 |
rily | -0.175 |
ning | -0.173 |
bing | -0.170 |
king | -0.169 |
Token | |
Token ID | 220 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
am | +0.015 |
done | +0.013 |
story | +0.012 |
bad | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.042 |
ning | -0.041 |
yles | -0.041 |
bing | -0.040 |
king | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
am | +0.022 |
done | +0.021 |
bad | +0.017 |
story | +0.017 |
big | +0.013 |
Neg logit contributions | |
yles | -0.122 |
ning | -0.120 |
izing | -0.120 |
ants | -0.119 |
rily | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
bad | +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.013 |
yles | -0.013 |
ning | -0.013 |
king | -0.012 |
bing | -0.012 |
Token | They |
Token ID | 2990 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
izing | +0.039 |
yles | +0.038 |
rily | +0.037 |
ellery | +0.037 |
ning | +0.037 |
Neg logit contributions | |
| -0.036 |
am | -0.036 |
done | -0.035 |
big | -0.033 |
story | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
am | +0.018 |
done | +0.015 |
story | +0.014 |
| +0.013 |
'm | +0.012 |
Neg logit contributions | |
izing | -0.035 |
king | -0.034 |
ning | -0.033 |
yles | -0.033 |
ting | -0.032 |
Token | but |
Token ID | 475 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
izing | +0.081 |
yles | +0.077 |
ning | +0.076 |
king | +0.076 |
ellery | +0.075 |
Neg logit contributions | |
am | -0.049 |
done | -0.045 |
| -0.045 |
story | -0.042 |
big | -0.042 |
Token | he |
Token ID | 339 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
am | +0.003 |
| +0.003 |
done | +0.003 |
big | +0.002 |
to | +0.002 |
Neg logit contributions | |
izing | -0.011 |
yles | -0.011 |
ning | -0.011 |
king | -0.011 |
ellery | -0.011 |
Token | followed |
Token ID | 3940 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
am | +0.024 |
done | +0.022 |
| +0.021 |
story | +0.019 |
big | +0.019 |
Neg logit contributions | |
izing | -0.063 |
yles | -0.061 |
ning | -0.060 |
rily | -0.059 |
king | -0.059 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
izing | +0.050 |
yles | +0.048 |
ning | +0.047 |
king | +0.047 |
ellery | +0.047 |
Neg logit contributions | |
am | -0.028 |
done | -0.026 |
| -0.026 |
story | -0.024 |
big | -0.024 |
Token | anyway |
Token ID | 6949 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
am | +0.030 |
done | +0.025 |
| +0.023 |
story | +0.023 |
bad | +0.022 |
Neg logit contributions | |
izing | -0.082 |
ning | -0.082 |
king | -0.081 |
yles | -0.080 |
bing | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
am | +0.056 |
done | +0.043 |
story | +0.037 |
| +0.033 |
'm | +0.033 |
Neg logit contributions | |
izing | -0.192 |
rily | -0.185 |
king | -0.182 |
ning | -0.181 |
bing | -0.180 |
Token | When |
Token ID | 1649 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
am | +0.013 |
done | +0.012 |
story | +0.011 |
| +0.010 |
bad | +0.010 |
Neg logit contributions | |
izing | -0.024 |
ning | -0.023 |
rily | -0.023 |
yles | -0.023 |
king | -0.023 |
Token | they |
Token ID | 484 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
am | +0.029 |
done | +0.026 |
story | +0.025 |
| +0.025 |
big | +0.023 |
Neg logit contributions | |
izing | -0.049 |
yles | -0.048 |
ning | -0.047 |
ellery | -0.046 |
burn | -0.045 |
Token | got |
Token ID | 1392 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
am | +0.032 |
story | +0.031 |
done | +0.027 |
| +0.026 |
lesson | +0.026 |
Neg logit contributions | |
yles | -0.058 |
ellery | -0.056 |
king | -0.056 |
izing | -0.056 |
ting | -0.055 |
Token | to |
Token ID | 284 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
yles | +0.000 |
ning | +0.000 |
izing | +0.000 |
ellery | +0.000 |
king | +0.000 |
Neg logit contributions | |
am | -0.000 |
story | -0.000 |
done | -0.000 |
| -0.000 |
time | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
izing | +0.048 |
yles | +0.047 |
ellery | +0.045 |
ning | +0.045 |
rily | +0.045 |
Neg logit contributions | |
am | -0.018 |
| -0.017 |
done | -0.017 |
big | -0.016 |
to | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
am | +0.005 |
done | +0.005 |
story | +0.004 |
| +0.004 |
time | +0.004 |
Neg logit contributions | |
izing | -0.014 |
yles | -0.013 |
ning | -0.013 |
king | -0.013 |
ellery | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
izing | +0.004 |
ning | +0.004 |
rily | +0.004 |
king | +0.004 |
yles | +0.004 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
own | -0.002 |
ossible | -0.002 |
time | -0.002 |
Token | No |
Token ID | 2949 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
izing | +0.134 |
rily | +0.133 |
yles | +0.131 |
ellery | +0.128 |
ants | +0.125 |
Neg logit contributions | |
am | -0.142 |
| -0.138 |
whole | -0.126 |
time | -0.122 |
to | -0.122 |
Token | T |
Token ID | 309 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
am | +0.003 |
done | +0.003 |
| +0.003 |
story | +0.003 |
big | +0.003 |
Neg logit contributions | |
yles | -0.007 |
izing | -0.007 |
rily | -0.007 |
king | -0.007 |
ellery | -0.007 |
Token | resp |
Token ID | 4363 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
izing | +0.112 |
yles | +0.111 |
ning | +0.105 |
rily | +0.103 |
king | +0.102 |
Neg logit contributions | |
am | -0.128 |
| -0.121 |
done | -0.119 |
story | -0.119 |
to | -0.115 |
Token | assing |
Token ID | 19696 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
rily | +0.312 |
bul | +0.304 |
bly | +0.286 |
ants | +0.286 |
izing | +0.285 |
Neg logit contributions | |
| -0.267 |
am | -0.262 |
find | -0.248 |
to | -0.238 |
learned | -0.235 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
izing | +0.052 |
yles | +0.050 |
ning | +0.049 |
ellery | +0.049 |
king | +0.049 |
Neg logit contributions | |
am | -0.044 |
done | -0.041 |
| -0.041 |
story | -0.039 |
big | -0.038 |
Token | But |
Token ID | 887 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
am | +0.005 |
done | +0.004 |
story | +0.004 |
bad | +0.004 |
big | +0.004 |
Neg logit contributions | |
izing | -0.006 |
ning | -0.006 |
rily | -0.006 |
ender | -0.006 |
ellery | -0.006 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
izing | +0.025 |
yles | +0.024 |
king | +0.024 |
rily | +0.024 |
ning | +0.024 |
Neg logit contributions | |
am | -0.010 |
| -0.009 |
done | -0.009 |
to | -0.009 |
big | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
am | +0.000 |
done | +0.000 |
| +0.000 |
story | +0.000 |
big | +0.000 |
Neg logit contributions | |
izing | -0.000 |
ning | -0.000 |
yles | -0.000 |
king | -0.000 |
ellery | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.037 |
ning | +0.037 |
king | +0.036 |
ellery | +0.036 |
Neg logit contributions | |
am | -0.018 |
done | -0.016 |
| -0.016 |
story | -0.015 |
big | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
izing | +0.008 |
yles | +0.008 |
ning | +0.008 |
king | +0.007 |
ellery | +0.007 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
story | -0.003 |
| -0.003 |
time | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
izing | +0.012 |
ning | +0.011 |
yles | +0.011 |
king | +0.011 |
rily | +0.011 |
Neg logit contributions | |
am | -0.007 |
done | -0.007 |
| -0.006 |
story | -0.006 |
big | -0.006 |
Token | No |
Token ID | 2949 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
izing | +0.112 |
rily | +0.108 |
yles | +0.104 |
ellery | +0.104 |
ning | +0.100 |
Neg logit contributions | |
am | -0.131 |
| -0.127 |
to | -0.114 |
whole | -0.112 |
time | -0.112 |
Token | T |
Token ID | 309 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
| +0.006 |
story | +0.006 |
big | +0.006 |
Neg logit contributions | |
izing | -0.014 |
yles | -0.013 |
ning | -0.013 |
king | -0.013 |
ellery | -0.013 |
Token | resp |
Token ID | 4363 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
izing | +0.089 |
yles | +0.087 |
ning | +0.082 |
rily | +0.081 |
ellery | +0.081 |
Neg logit contributions | |
am | -0.126 |
| -0.120 |
done | -0.119 |
story | -0.117 |
to | -0.115 |
Token | assing |
Token ID | 19696 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
rily | +0.291 |
bul | +0.286 |
izing | +0.273 |
ants | +0.264 |
yles | +0.264 |
Neg logit contributions | |
am | -0.269 |
| -0.266 |
find | -0.246 |
to | -0.242 |
| -0.237 |
Token | ". |
Token ID | 1911 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
izing | +0.048 |
yles | +0.046 |
ellery | +0.045 |
ning | +0.045 |
rily | +0.045 |
Neg logit contributions | |
am | -0.038 |
| -0.036 |
done | -0.036 |
story | -0.034 |
to | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
done | +0.010 |
am | +0.009 |
story | +0.009 |
bad | +0.007 |
whole | +0.007 |
Neg logit contributions | |
izing | -0.032 |
yles | -0.031 |
ants | -0.031 |
rily | -0.031 |
ning | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
izing | +0.003 |
ants | +0.003 |
yles | +0.003 |
bing | +0.003 |
ning | +0.003 |
Neg logit contributions | |
done | -0.001 |
am | -0.000 |
story | -0.000 |
bad | -0.000 |
time | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
izing | +0.044 |
yles | +0.042 |
ning | +0.041 |
king | +0.041 |
ellery | +0.041 |
Neg logit contributions | |
am | -0.039 |
| -0.037 |
done | -0.036 |
story | -0.034 |
big | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
izing | +0.045 |
yles | +0.044 |
ning | +0.043 |
ellery | +0.043 |
rily | +0.043 |
Neg logit contributions | |
am | -0.014 |
done | -0.013 |
| -0.012 |
story | -0.011 |
to | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
am | +0.005 |
done | +0.004 |
| +0.004 |
story | +0.004 |
big | +0.004 |
Neg logit contributions | |
izing | -0.012 |
yles | -0.012 |
ning | -0.011 |
king | -0.011 |
ellery | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
izing | +0.021 |
ning | +0.020 |
yles | +0.020 |
king | +0.020 |
rily | +0.020 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
| -0.010 |
ossible | -0.009 |
story | -0.009 |
Token | No |
Token ID | 2949 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
izing | +0.097 |
ellery | +0.094 |
rily | +0.092 |
yles | +0.092 |
ants | +0.090 |
Neg logit contributions | |
am | -0.111 |
| -0.105 |
done | -0.098 |
to | -0.096 |
time | -0.096 |
Token | T |
Token ID | 309 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
am | +0.003 |
done | +0.002 |
| +0.002 |
story | +0.002 |
big | +0.002 |
Neg logit contributions | |
izing | -0.008 |
yles | -0.008 |
ning | -0.007 |
king | -0.007 |
ellery | -0.007 |
Token | resp |
Token ID | 4363 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
izing | +0.093 |
yles | +0.090 |
ning | +0.087 |
ellery | +0.086 |
king | +0.084 |
Neg logit contributions | |
am | -0.127 |
| -0.120 |
done | -0.120 |
story | -0.118 |
to | -0.114 |
Token | assing |
Token ID | 19696 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
rily | +0.288 |
bul | +0.282 |
ants | +0.273 |
izing | +0.267 |
yles | +0.259 |
Neg logit contributions | |
am | -0.259 |
| -0.256 |
find | -0.239 |
to | -0.235 |
learned | -0.232 |
Token | " |
Token ID | 1 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
izing | +0.049 |
yles | +0.047 |
ning | +0.046 |
ellery | +0.046 |
king | +0.046 |
Neg logit contributions | |
am | -0.037 |
done | -0.035 |
| -0.035 |
story | -0.033 |
big | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
izing | +0.038 |
ning | +0.037 |
yles | +0.037 |
king | +0.037 |
rily | +0.036 |
Neg logit contributions | |
am | -0.021 |
done | -0.019 |
story | -0.018 |
| -0.017 |
big | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
izing | +0.090 |
yles | +0.087 |
ning | +0.085 |
king | +0.085 |
ellery | +0.083 |
Neg logit contributions | |
am | -0.049 |
| -0.045 |
done | -0.045 |
story | -0.044 |
big | -0.041 |
Token | Private |
Token ID | 29067 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
izing | +0.096 |
ellery | +0.090 |
rily | +0.089 |
yles | +0.087 |
ning | +0.087 |
Neg logit contributions | |
am | -0.108 |
| -0.102 |
done | -0.096 |
to | -0.092 |
whole | -0.090 |
Token | that |
Token ID | 326 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
izing | +0.017 |
ning | +0.016 |
yles | +0.016 |
king | +0.016 |
ellery | +0.016 |
Neg logit contributions | |
am | -0.006 |
done | -0.006 |
| -0.005 |
story | -0.005 |
big | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
izing | +0.002 |
yles | +0.002 |
ning | +0.002 |
rily | +0.002 |
ellery | +0.002 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
story | -0.001 |
| -0.001 |
time | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
izing | +0.012 |
ning | +0.011 |
yles | +0.011 |
king | +0.011 |
rily | +0.011 |
Neg logit contributions | |
am | -0.006 |
done | -0.005 |
| -0.005 |
story | -0.005 |
big | -0.005 |
Token | No |
Token ID | 2949 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
izing | +0.102 |
rily | +0.097 |
yles | +0.096 |
ellery | +0.095 |
ning | +0.092 |
Neg logit contributions | |
am | -0.115 |
| -0.111 |
to | -0.101 |
time | -0.100 |
done | -0.100 |
Token | T |
Token ID | 309 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
am | +0.006 |
done | +0.006 |
| +0.006 |
story | +0.005 |
big | +0.005 |
Neg logit contributions | |
izing | -0.011 |
yles | -0.011 |
ning | -0.010 |
king | -0.010 |
ellery | -0.010 |
Token | resp |
Token ID | 4363 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
izing | +0.092 |
yles | +0.090 |
ning | +0.085 |
ellery | +0.084 |
rily | +0.083 |
Neg logit contributions | |
am | -0.115 |
| -0.112 |
story | -0.109 |
done | -0.109 |
to | -0.107 |
Token | assing |
Token ID | 19696 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
rily | +0.292 |
bul | +0.289 |
izing | +0.275 |
bly | +0.270 |
ants | +0.261 |
Neg logit contributions | |
| -0.257 |
am | -0.250 |
find | -0.242 |
to | -0.233 |
| -0.225 |
Token | ". |
Token ID | 1911 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
izing | +0.039 |
yles | +0.037 |
ellery | +0.036 |
ning | +0.036 |
rily | +0.036 |
Neg logit contributions | |
am | -0.029 |
| -0.027 |
done | -0.027 |
to | -0.025 |
story | -0.025 |
Token | And |
Token ID | 843 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
done | +0.014 |
am | +0.013 |
whole | +0.012 |
story | +0.011 |
rest | +0.011 |
Neg logit contributions | |
rily | -0.017 |
izing | -0.016 |
yles | -0.016 |
king | -0.015 |
ender | -0.015 |
Token | behind |
Token ID | 2157 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
izing | +0.021 |
yles | +0.021 |
rily | +0.020 |
king | +0.020 |
ning | +0.020 |
Neg logit contributions | |
am | -0.015 |
done | -0.013 |
story | -0.013 |
whole | -0.013 |
| -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
izing | +0.032 |
yles | +0.031 |
ning | +0.031 |
king | +0.030 |
ellery | +0.030 |
Neg logit contributions | |
am | -0.019 |
done | -0.017 |
| -0.017 |
story | -0.016 |
big | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
am | +0.006 |
| +0.005 |
done | +0.005 |
big | +0.005 |
to | +0.005 |
Neg logit contributions | |
izing | -0.021 |
yles | -0.021 |
king | -0.020 |
ning | -0.020 |
rily | -0.020 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.012 |
ning | +0.012 |
ellery | +0.012 |
rily | +0.012 |
Neg logit contributions | |
am | -0.004 |
big | -0.004 |
| -0.004 |
story | -0.004 |
done | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
izing | +0.027 |
ning | +0.026 |
yles | +0.025 |
king | +0.025 |
rily | +0.025 |
Neg logit contributions | |
am | -0.019 |
done | -0.018 |
| -0.017 |
story | -0.016 |
big | -0.016 |
Token | raspberry |
Token ID | 38973 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
izing | +0.131 |
yles | +0.127 |
ning | +0.125 |
king | +0.124 |
ellery | +0.124 |
Neg logit contributions | |
am | -0.064 |
done | -0.058 |
| -0.058 |
story | -0.054 |
big | -0.053 |
Token | - |
Token ID | 12 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
izing | +0.053 |
ning | +0.051 |
yles | +0.050 |
ellery | +0.050 |
king | +0.049 |
Neg logit contributions | |
am | -0.029 |
done | -0.027 |
| -0.026 |
story | -0.024 |
ossible | -0.024 |
Token | col |
Token ID | 4033 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
izing | +0.179 |
yles | +0.172 |
king | +0.167 |
rily | +0.164 |
ning | +0.163 |
Neg logit contributions | |
| -0.199 |
am | -0.193 |
to | -0.192 |
big | -0.189 |
done | -0.178 |
Token | oured |
Token ID | 8167 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
izing | +0.220 |
bly | +0.212 |
bul | +0.209 |
shadow | +0.203 |
pole | +0.202 |
Neg logit contributions | |
to | -0.262 |
done | -0.261 |
| -0.235 |
am | -0.233 |
ossible | -0.230 |
Token | object |
Token ID | 2134 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
izing | +0.045 |
ning | +0.042 |
yles | +0.042 |
ellery | +0.042 |
king | +0.041 |
Neg logit contributions | |
am | -0.040 |
done | -0.037 |
| -0.037 |
story | -0.035 |
big | -0.034 |
Token | hiding |
Token ID | 11816 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
izing | +0.111 |
yles | +0.109 |
rily | +0.105 |
king | +0.105 |
ellery | +0.105 |
Neg logit contributions | |
am | -0.030 |
| -0.027 |
done | -0.026 |
to | -0.026 |
big | -0.025 |
Token | under |
Token ID | 739 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
izing | +0.035 |
rily | +0.033 |
yles | +0.033 |
ning | +0.033 |
ellery | +0.033 |
Neg logit contributions | |
am | -0.031 |
done | -0.029 |
| -0.028 |
story | -0.028 |
big | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
izing | +0.012 |
yles | +0.011 |
ning | +0.011 |
king | +0.011 |
ellery | +0.011 |
Neg logit contributions | |
am | -0.004 |
| -0.003 |
done | -0.003 |
story | -0.003 |
big | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
izing | +0.045 |
ning | +0.044 |
yles | +0.043 |
king | +0.043 |
ants | +0.043 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
story | -0.010 |
| -0.009 |
big | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
izing | +0.093 |
yles | +0.090 |
ning | +0.088 |
ellery | +0.088 |
king | +0.088 |
Neg logit contributions | |
am | -0.052 |
| -0.049 |
done | -0.047 |
big | -0.045 |
to | -0.044 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
am | +0.012 |
story | +0.011 |
done | +0.011 |
lesson | +0.010 |
| +0.010 |
Neg logit contributions | |
ellery | -0.026 |
chick | -0.026 |
ning | -0.025 |
yles | -0.025 |
bug | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ning | +0.005 |
izing | +0.004 |
yles | +0.004 |
ellery | +0.004 |
ants | +0.004 |
Neg logit contributions | |
am | -0.002 |
done | -0.002 |
story | -0.001 |
| -0.001 |
own | -0.001 |
Token | red |
Token ID | 2266 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
izing | +0.029 |
yles | +0.029 |
ellery | +0.028 |
rily | +0.028 |
ants | +0.028 |
Neg logit contributions | |
am | -0.005 |
big | -0.004 |
story | -0.004 |
| -0.004 |
done | -0.004 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
yles | +0.093 |
izing | +0.090 |
ellery | +0.086 |
king | +0.084 |
rily | +0.084 |
Neg logit contributions | |
am | -0.076 |
big | -0.073 |
story | -0.073 |
| -0.072 |
to | -0.070 |
Token | ish |
Token ID | 680 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
izing | +0.200 |
yles | +0.195 |
king | +0.181 |
ivating | +0.180 |
rily | +0.180 |
Neg logit contributions | |
am | -0.317 |
| -0.303 |
big | -0.297 |
to | -0.295 |
done | -0.287 |
Token | in |
Token ID | 287 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
izing | +0.116 |
yles | +0.113 |
ning | +0.110 |
king | +0.110 |
ellery | +0.110 |
Neg logit contributions | |
am | -0.048 |
| -0.043 |
done | -0.043 |
story | -0.040 |
big | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
izing | +0.024 |
yles | +0.023 |
ning | +0.023 |
king | +0.023 |
ellery | +0.023 |
Neg logit contributions | |
am | -0.008 |
done | -0.007 |
| -0.007 |
story | -0.006 |
big | -0.006 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
am | +0.023 |
done | +0.022 |
lesson | +0.019 |
ossible | +0.018 |
story | +0.018 |
Neg logit contributions | |
ning | -0.035 |
burn | -0.033 |
chick | -0.032 |
ting | -0.032 |
ellery | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
am | +0.004 |
done | +0.003 |
story | +0.003 |
lesson | +0.003 |
bad | +0.003 |
Neg logit contributions | |
izing | -0.011 |
ning | -0.011 |
king | -0.010 |
bing | -0.010 |
ting | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
izing | +0.035 |
yles | +0.033 |
ning | +0.033 |
bing | +0.033 |
king | +0.033 |
Neg logit contributions | |
am | -0.010 |
done | -0.009 |
story | -0.009 |
| -0.007 |
own | -0.007 |
Token | Benny |
Token ID | 44275 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
izing | +0.068 |
yles | +0.064 |
ning | +0.063 |
king | +0.062 |
bing | +0.062 |
Neg logit contributions | |
am | -0.054 |
done | -0.052 |
story | -0.049 |
| -0.047 |
big | -0.045 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ning | +0.018 |
izing | +0.017 |
ellery | +0.017 |
chick | +0.017 |
bing | +0.017 |
Neg logit contributions | |
am | -0.008 |
done | -0.008 |
story | -0.007 |
| -0.006 |
lesson | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ning | +0.008 |
izing | +0.008 |
yles | +0.008 |
ellery | +0.008 |
bing | +0.008 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
story | -0.003 |
own | -0.002 |
time | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
izing | +0.024 |
yles | +0.024 |
ellery | +0.023 |
rily | +0.023 |
ning | +0.023 |
Neg logit contributions | |
am | -0.005 |
big | -0.004 |
| -0.004 |
story | -0.004 |
done | -0.004 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
yles | +0.119 |
izing | +0.115 |
king | +0.112 |
ants | +0.112 |
ellery | +0.112 |
Neg logit contributions | |
big | -0.052 |
am | -0.051 |
story | -0.048 |
bad | -0.047 |
| -0.046 |
Token | ish |
Token ID | 680 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
izing | +0.196 |
yles | +0.190 |
king | +0.176 |
ivating | +0.175 |
rily | +0.173 |
Neg logit contributions | |
am | -0.315 |
| -0.302 |
big | -0.297 |
to | -0.295 |
done | -0.288 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
izing | +0.107 |
yles | +0.105 |
ellery | +0.102 |
ning | +0.101 |
king | +0.101 |
Neg logit contributions | |
am | -0.047 |
| -0.042 |
done | -0.042 |
story | -0.040 |
big | -0.040 |
Token | he |
Token ID | 339 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
izing | +0.081 |
yles | +0.076 |
ning | +0.075 |
rily | +0.075 |
ellery | +0.075 |
Neg logit contributions | |
am | -0.042 |
done | -0.038 |
story | -0.038 |
| -0.034 |
time | -0.034 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
am | +0.014 |
done | +0.012 |
story | +0.012 |
| +0.011 |
time | +0.010 |
Neg logit contributions | |
izing | -0.024 |
ellery | -0.023 |
ning | -0.023 |
king | -0.022 |
ants | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
am | +0.014 |
story | +0.011 |
done | +0.011 |
ossible | +0.009 |
| +0.008 |
Neg logit contributions | |
ning | -0.053 |
ellery | -0.053 |
izing | -0.053 |
yles | -0.052 |
ries | -0.051 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
am | +0.027 |
done | +0.026 |
ossible | +0.025 |
story | +0.024 |
| +0.024 |
Neg logit contributions | |
izing | -0.036 |
ning | -0.035 |
ting | -0.033 |
ivating | -0.033 |
bing | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
am | +0.022 |
done | +0.018 |
story | +0.017 |
ossible | +0.016 |
bad | +0.015 |
Neg logit contributions | |
izing | -0.055 |
ning | -0.053 |
rily | -0.053 |
king | -0.053 |
bing | -0.052 |
Token | It |
Token ID | 632 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
story | +0.001 |
bad | +0.001 |
| +0.001 |
Neg logit contributions | |
izing | -0.002 |
ning | -0.002 |
rily | -0.002 |
yles | -0.002 |
king | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
am | +0.004 |
done | +0.003 |
story | +0.003 |
| +0.002 |
ossible | +0.002 |
Neg logit contributions | |
izing | -0.019 |
ning | -0.019 |
yles | -0.018 |
rily | -0.018 |
king | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
izing | +0.013 |
ning | +0.012 |
yles | +0.012 |
king | +0.012 |
ellery | +0.012 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
| -0.003 |
story | -0.003 |
big | -0.003 |
Token | tort |
Token ID | 7619 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
izing | +0.001 |
yles | +0.001 |
ning | +0.001 |
ellery | +0.001 |
king | +0.001 |
Neg logit contributions | |
am | -0.001 |
| -0.000 |
done | -0.000 |
big | -0.000 |
story | -0.000 |
Token | oise |
Token ID | 25678 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
izing | +0.198 |
rily | +0.194 |
ender | +0.179 |
ksh | +0.171 |
yles | +0.169 |
Neg logit contributions | |
am | -0.327 |
'm | -0.290 |
done | -0.284 |
| -0.273 |
ossible | -0.268 |
Token | ! |
Token ID | 0 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
izing | +0.057 |
yles | +0.056 |
ning | +0.054 |
king | +0.054 |
rily | +0.054 |
Neg logit contributions | |
am | -0.020 |
| -0.018 |
done | -0.017 |
to | -0.017 |
big | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
am | +0.004 |
done | +0.004 |
story | +0.004 |
| +0.003 |
big | +0.003 |
Neg logit contributions | |
izing | -0.012 |
ning | -0.012 |
yles | -0.011 |
rily | -0.011 |
king | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
izing | +0.028 |
yles | +0.027 |
ning | +0.027 |
king | +0.026 |
ellery | +0.026 |
Neg logit contributions | |
am | -0.020 |
| -0.019 |
done | -0.018 |
story | -0.018 |
big | -0.018 |
Token | igator |
Token ID | 23823 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
izing | +0.019 |
yles | +0.018 |
ning | +0.017 |
king | +0.017 |
ellery | +0.017 |
Neg logit contributions | |
am | -0.034 |
done | -0.032 |
| -0.032 |
story | -0.031 |
big | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ning | +0.048 |
izing | +0.047 |
ting | +0.044 |
bing | +0.044 |
ants | +0.043 |
Neg logit contributions | |
am | -0.031 |
done | -0.029 |
story | -0.027 |
own | -0.027 |
bad | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
| +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.004 |
ning | -0.004 |
yles | -0.004 |
king | -0.004 |
rily | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
izing | +0.067 |
yles | +0.065 |
ning | +0.064 |
king | +0.063 |
ellery | +0.063 |
Neg logit contributions | |
am | -0.063 |
| -0.059 |
done | -0.059 |
big | -0.056 |
story | -0.056 |
Token | chocolate |
Token ID | 11311 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
izing | +0.048 |
yles | +0.047 |
ellery | +0.046 |
rily | +0.046 |
ning | +0.046 |
Neg logit contributions | |
am | -0.015 |
| -0.014 |
big | -0.013 |
done | -0.013 |
story | -0.013 |
Token | - |
Token ID | 12 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
izing | +0.085 |
yles | +0.081 |
ning | +0.081 |
king | +0.079 |
ellery | +0.078 |
Neg logit contributions | |
am | -0.064 |
done | -0.060 |
| -0.059 |
story | -0.056 |
big | -0.055 |
Token | col |
Token ID | 4033 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izing | +0.165 |
yles | +0.161 |
rily | +0.154 |
king | +0.152 |
ellery | +0.152 |
Neg logit contributions | |
| -0.207 |
am | -0.200 |
to | -0.197 |
big | -0.187 |
done | -0.185 |
Token | oured |
Token ID | 8167 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
izing | +0.233 |
bly | +0.220 |
bul | +0.219 |
spe | +0.200 |
quet | +0.199 |
Neg logit contributions | |
to | -0.247 |
done | -0.219 |
back | -0.217 |
ossible | -0.217 |
| -0.214 |
Token | whip |
Token ID | 22972 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
izing | +0.058 |
yles | +0.057 |
king | +0.054 |
ellery | +0.054 |
ning | +0.054 |
Neg logit contributions | |
am | -0.053 |
| -0.051 |
done | -0.050 |
big | -0.049 |
story | -0.049 |
Token | named |
Token ID | 3706 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
izing | +0.083 |
yles | +0.081 |
ning | +0.080 |
king | +0.079 |
ellery | +0.079 |
Neg logit contributions | |
am | -0.029 |
done | -0.026 |
| -0.026 |
story | -0.024 |
big | -0.023 |
Token | C |
Token ID | 327 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
izing | +0.136 |
yles | +0.130 |
ellery | +0.126 |
rily | +0.124 |
bul | +0.124 |
Neg logit contributions | |
| -0.118 |
big | -0.104 |
am | -0.104 |
to | -0.103 |
| -0.098 |
Token | heddar |
Token ID | 44937 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
izing | +0.102 |
ning | +0.098 |
king | +0.097 |
yles | +0.097 |
ellery | +0.097 |
Neg logit contributions | |
am | -0.107 |
done | -0.101 |
| -0.096 |
story | -0.096 |
bad | -0.096 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
izing | +0.064 |
yles | +0.061 |
ning | +0.060 |
rily | +0.058 |
king | +0.058 |
Neg logit contributions | |
am | -0.065 |
done | -0.062 |
| -0.061 |
story | -0.059 |
big | -0.058 |
Token | noticed |
Token ID | 6810 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
am | +0.001 |
story | +0.001 |
done | +0.001 |
| +0.001 |
lesson | +0.001 |
Neg logit contributions | |
ning | -0.004 |
yles | -0.004 |
izing | -0.004 |
king | -0.004 |
ellery | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
| +0.006 |
story | +0.006 |
big | +0.005 |
Neg logit contributions | |
izing | -0.022 |
yles | -0.021 |
ning | -0.021 |
ellery | -0.021 |
king | -0.021 |
Token | weather |
Token ID | 6193 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
am | +0.020 |
| +0.018 |
done | +0.018 |
ossible | +0.017 |
learned | +0.015 |
Neg logit contributions | |
izing | -0.035 |
ning | -0.035 |
burn | -0.033 |
bul | -0.033 |
king | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
izing | +0.063 |
yles | +0.061 |
ning | +0.061 |
king | +0.060 |
ellery | +0.060 |
Neg logit contributions | |
am | -0.023 |
done | -0.021 |
| -0.021 |
story | -0.019 |
big | -0.018 |
Token | uncom |
Token ID | 8820 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izing | +0.020 |
ning | +0.019 |
yles | +0.019 |
king | +0.018 |
rily | +0.018 |
Neg logit contributions | |
am | -0.012 |
| -0.011 |
done | -0.011 |
story | -0.010 |
big | -0.010 |
Token | fort |
Token ID | 3319 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
yles | +0.258 |
rily | +0.252 |
ning | +0.230 |
ants | +0.227 |
ries | +0.227 |
Neg logit contributions | |
own | -0.236 |
done | -0.227 |
to | -0.224 |
am | -0.221 |
find | -0.219 |
Token | ably |
Token ID | 1346 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
izing | +0.078 |
yles | +0.073 |
ning | +0.071 |
king | +0.070 |
ellery | +0.070 |
Neg logit contributions | |
am | -0.127 |
done | -0.121 |
| -0.121 |
story | -0.117 |
big | -0.115 |
Token | hot |
Token ID | 3024 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
izing | +0.014 |
ning | +0.014 |
rily | +0.013 |
king | +0.013 |
yles | +0.013 |
Neg logit contributions | |
am | -0.007 |
| -0.007 |
done | -0.006 |
story | -0.006 |
ossible | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
izing | +0.064 |
yles | +0.062 |
ning | +0.061 |
king | +0.061 |
ellery | +0.061 |
Neg logit contributions | |
am | -0.010 |
| -0.008 |
done | -0.008 |
story | -0.006 |
big | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
izing | +0.007 |
yles | +0.007 |
ning | +0.007 |
ellery | +0.006 |
rily | +0.006 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
| -0.002 |
story | -0.002 |
big | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
izing | +0.043 |
yles | +0.042 |
rily | +0.042 |
king | +0.041 |
ellery | +0.040 |
Neg logit contributions | |
am | -0.025 |
done | -0.025 |
| -0.024 |
to | -0.023 |
big | -0.022 |
Token | ! |
Token ID | 0 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
| +0.002 |
story | +0.002 |
big | +0.002 |
Neg logit contributions | |
izing | -0.008 |
yles | -0.007 |
ning | -0.007 |
king | -0.007 |
ellery | -0.007 |
Token | I |
Token ID | 314 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
izing | +0.026 |
ellery | +0.025 |
yles | +0.025 |
king | +0.025 |
bing | +0.024 |
Neg logit contributions | |
| -0.010 |
am | -0.009 |
big | -0.008 |
He | -0.007 |
to | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
izing | +0.025 |
yles | +0.025 |
burn | +0.025 |
ning | +0.025 |
king | +0.025 |
Neg logit contributions | |
done | -0.008 |
| -0.008 |
story | -0.008 |
am | -0.008 |
big | -0.007 |
Token | an |
Token ID | 281 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
izing | +0.060 |
king | +0.058 |
rily | +0.058 |
yles | +0.057 |
ellery | +0.057 |
Neg logit contributions | |
| -0.015 |
big | -0.015 |
to | -0.015 |
am | -0.014 |
done | -0.014 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
yles | +0.092 |
izing | +0.089 |
king | +0.085 |
etti | +0.082 |
rily | +0.081 |
Neg logit contributions | |
big | -0.090 |
bad | -0.088 |
done | -0.087 |
am | -0.086 |
story | -0.084 |
Token | ich |
Token ID | 488 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
rily | +0.184 |
izing | +0.179 |
yles | +0.172 |
ivating | +0.163 |
ellery | +0.157 |
Neg logit contributions | |
am | -0.317 |
| -0.302 |
done | -0.300 |
to | -0.296 |
story | -0.295 |
Token | in |
Token ID | 287 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
yles | +0.093 |
izing | +0.093 |
rily | +0.089 |
ellery | +0.089 |
ants | +0.088 |
Neg logit contributions | |
am | -0.051 |
done | -0.048 |
| -0.047 |
to | -0.047 |
big | -0.046 |
Token | our |
Token ID | 674 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
big | +0.001 |
| +0.001 |
am | +0.001 |
bad | +0.001 |
story | +0.001 |
Neg logit contributions | |
king | -0.004 |
yles | -0.004 |
izing | -0.004 |
ants | -0.003 |
ksh | -0.003 |
Token | backyard |
Token ID | 24296 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
am | +0.018 |
done | +0.015 |
| +0.015 |
story | +0.014 |
'm | +0.013 |
Neg logit contributions | |
ning | -0.032 |
ellery | -0.032 |
izing | -0.030 |
king | -0.029 |
bing | -0.029 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
am | +0.000 |
done | +0.000 |
| +0.000 |
story | +0.000 |
bad | +0.000 |
Neg logit contributions | |
izing | -0.001 |
ning | -0.001 |
yles | -0.001 |
king | -0.001 |
ellery | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ning | +0.027 |
chick | +0.026 |
ellery | +0.026 |
bug | +0.026 |
king | +0.025 |
Neg logit contributions | |
am | -0.012 |
story | -0.011 |
done | -0.011 |
lesson | -0.010 |
bad | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ning | +0.007 |
izing | +0.007 |
yles | +0.007 |
ellery | +0.006 |
ants | +0.006 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
story | -0.002 |
| -0.002 |
own | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
izing | +0.017 |
yles | +0.016 |
ellery | +0.016 |
ning | +0.016 |
rily | +0.016 |
Neg logit contributions | |
am | -0.003 |
| -0.003 |
big | -0.002 |
done | -0.002 |
story | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
yles | +0.119 |
izing | +0.116 |
king | +0.114 |
ants | +0.113 |
ellery | +0.113 |
Neg logit contributions | |
am | -0.044 |
big | -0.043 |
story | -0.040 |
bad | -0.039 |
| -0.039 |
Token | red |
Token ID | 2266 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
izing | +0.167 |
yles | +0.165 |
ning | +0.160 |
ellery | +0.159 |
king | +0.159 |
Neg logit contributions | |
am | -0.079 |
done | -0.072 |
| -0.072 |
big | -0.071 |
story | -0.068 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
yles | +0.076 |
izing | +0.076 |
ellery | +0.071 |
king | +0.071 |
ning | +0.070 |
Neg logit contributions | |
am | -0.074 |
| -0.069 |
big | -0.069 |
story | -0.068 |
to | -0.067 |
Token | ish |
Token ID | 680 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
izing | +0.188 |
yles | +0.178 |
rily | +0.167 |
king | +0.166 |
ivating | +0.163 |
Neg logit contributions | |
am | -0.322 |
| -0.305 |
big | -0.298 |
to | -0.298 |
done | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
izing | +0.116 |
yles | +0.111 |
ning | +0.111 |
king | +0.110 |
ellery | +0.109 |
Neg logit contributions | |
am | -0.043 |
done | -0.039 |
| -0.038 |
story | -0.035 |
big | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
izing | +0.019 |
ning | +0.019 |
rily | +0.019 |
yles | +0.018 |
ants | +0.018 |
Neg logit contributions | |
am | -0.006 |
done | -0.005 |
story | -0.004 |
bad | -0.004 |
time | -0.004 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
am | +0.015 |
done | +0.013 |
story | +0.013 |
| +0.012 |
bad | +0.011 |
Neg logit contributions | |
izing | -0.033 |
yles | -0.032 |
ning | -0.032 |
ellery | -0.032 |
king | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
am | +0.005 |
done | +0.004 |
story | +0.004 |
ossible | +0.003 |
| +0.003 |
Neg logit contributions | |
izing | -0.024 |
ning | -0.024 |
ellery | -0.023 |
yles | -0.023 |
ries | -0.023 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
am | +0.029 |
done | +0.028 |
| +0.026 |
story | +0.025 |
big | +0.024 |
Neg logit contributions | |
yles | -0.053 |
izing | -0.052 |
ellery | -0.050 |
ning | -0.050 |
rily | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
| +0.001 |
story | +0.001 |
own | +0.001 |
Neg logit contributions | |
izing | -0.002 |
yles | -0.002 |
ning | -0.002 |
ellery | -0.002 |
rily | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
izing | +0.053 |
yles | +0.052 |
rily | +0.051 |
ellery | +0.050 |
ning | +0.050 |
Neg logit contributions | |
am | -0.033 |
done | -0.032 |
story | -0.029 |
| -0.028 |
time | -0.027 |
Token | brightly |
Token ID | 35254 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
izing | +0.035 |
ning | +0.034 |
yles | +0.034 |
king | +0.034 |
rily | +0.033 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
| -0.010 |
story | -0.009 |
to | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
izing | +0.054 |
yles | +0.053 |
ellery | +0.051 |
ning | +0.051 |
king | +0.051 |
Neg logit contributions | |
am | -0.054 |
done | -0.052 |
| -0.051 |
story | -0.049 |
big | -0.049 |
Token | col |
Token ID | 4033 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
izing | +0.234 |
yles | +0.219 |
arians | +0.216 |
bing | +0.215 |
ning | +0.214 |
Neg logit contributions | |
| -0.175 |
big | -0.169 |
am | -0.167 |
to | -0.167 |
bad | -0.151 |
Token | oured |
Token ID | 8167 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
izing | +0.215 |
bing | +0.197 |
bly | +0.192 |
rily | +0.187 |
yles | +0.183 |
Neg logit contributions | |
to | -0.254 |
done | -0.250 |
am | -0.235 |
ossible | -0.231 |
back | -0.229 |
Token | belt |
Token ID | 10999 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
izing | +0.054 |
yles | +0.052 |
ning | +0.051 |
king | +0.050 |
ellery | +0.050 |
Neg logit contributions | |
am | -0.043 |
done | -0.040 |
| -0.040 |
story | -0.039 |
big | -0.038 |
Token | caught |
Token ID | 4978 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
izing | +0.106 |
yles | +0.102 |
ning | +0.101 |
king | +0.100 |
ellery | +0.099 |
Neg logit contributions | |
am | -0.050 |
done | -0.046 |
| -0.046 |
story | -0.043 |
big | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
izing | +0.115 |
yles | +0.113 |
shadow | +0.109 |
king | +0.109 |
arians | +0.109 |
Neg logit contributions | |
to | -0.037 |
big | -0.036 |
| -0.035 |
am | -0.035 |
done | -0.034 |
Token | eye |
Token ID | 4151 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
am | +0.038 |
done | +0.035 |
| +0.034 |
story | +0.032 |
bad | +0.029 |
Neg logit contributions | |
izing | -0.071 |
ning | -0.070 |
king | -0.069 |
rily | -0.068 |
ellery | -0.067 |
Token | spotted |
Token ID | 13489 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.038 |
ning | +0.037 |
king | +0.037 |
ellery | +0.037 |
Neg logit contributions | |
am | -0.018 |
story | -0.016 |
done | -0.014 |
| -0.014 |
time | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
izing | +0.020 |
ning | +0.019 |
yles | +0.019 |
ellery | +0.019 |
rily | +0.019 |
Neg logit contributions | |
am | -0.007 |
done | -0.006 |
story | -0.005 |
| -0.005 |
time | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
izing | +0.011 |
yles | +0.011 |
ellery | +0.011 |
ning | +0.011 |
rily | +0.011 |
Neg logit contributions | |
am | -0.002 |
big | -0.002 |
| -0.002 |
story | -0.002 |
done | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
yles | +0.111 |
izing | +0.109 |
ants | +0.105 |
king | +0.105 |
ellery | +0.104 |
Neg logit contributions | |
am | -0.037 |
big | -0.036 |
story | -0.034 |
| -0.033 |
done | -0.032 |
Token | brown |
Token ID | 7586 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
izing | +0.150 |
yles | +0.148 |
ning | +0.144 |
ellery | +0.142 |
king | +0.142 |
Neg logit contributions | |
am | -0.088 |
big | -0.083 |
| -0.082 |
done | -0.082 |
story | -0.079 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
yles | +0.080 |
izing | +0.080 |
ellery | +0.075 |
king | +0.074 |
ants | +0.073 |
Neg logit contributions | |
am | -0.064 |
big | -0.061 |
| -0.061 |
story | -0.061 |
to | -0.059 |
Token | ish |
Token ID | 680 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
izing | +0.192 |
yles | +0.182 |
rily | +0.170 |
king | +0.169 |
ivating | +0.169 |
Neg logit contributions | |
am | -0.315 |
| -0.298 |
big | -0.293 |
to | -0.292 |
done | -0.286 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
izing | +0.122 |
yles | +0.120 |
ellery | +0.116 |
ning | +0.116 |
king | +0.115 |
Neg logit contributions | |
am | -0.033 |
| -0.029 |
done | -0.028 |
to | -0.027 |
story | -0.027 |
Token | Benny |
Token ID | 44275 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
done | +0.006 |
am | +0.006 |
story | +0.005 |
bad | +0.005 |
time | +0.004 |
Neg logit contributions | |
izing | -0.014 |
ning | -0.014 |
rily | -0.013 |
yles | -0.013 |
bing | -0.013 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
izing | +0.034 |
ning | +0.033 |
king | +0.032 |
ellery | +0.032 |
bing | +0.032 |
Neg logit contributions | |
am | -0.015 |
done | -0.013 |
story | -0.012 |
| -0.012 |
time | -0.011 |
Token | rad |
Token ID | 2511 |
Feature activation | -9.53e+00 |
Pos logit contributions | |
am | +0.010 |
done | +0.009 |
| +0.008 |
story | +0.008 |
big | +0.007 |
Neg logit contributions | |
izing | -0.022 |
yles | -0.021 |
ning | -0.021 |
ellery | -0.021 |
king | -0.021 |
Token | sudden |
Token ID | 4802 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
am | +0.008 |
big | +0.008 |
| +0.008 |
story | +0.008 |
bad | +0.008 |
Neg logit contributions | |
izing | -0.009 |
yles | -0.009 |
rily | -0.009 |
ellery | -0.009 |
ning | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
izing | +0.020 |
yles | +0.019 |
ning | +0.019 |
ellery | +0.019 |
king | +0.019 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
| -0.003 |
story | -0.003 |
big | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
izing | +0.082 |
yles | +0.078 |
ning | +0.076 |
ellery | +0.075 |
rily | +0.074 |
Neg logit contributions | |
am | -0.051 |
story | -0.049 |
done | -0.048 |
| -0.044 |
ossible | -0.043 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
am | +0.014 |
story | +0.012 |
| +0.012 |
done | +0.011 |
lesson | +0.011 |
Neg logit contributions | |
yles | -0.033 |
king | -0.032 |
ning | -0.032 |
izing | -0.032 |
ellery | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
am | +0.003 |
done | +0.002 |
story | +0.002 |
| +0.002 |
own | +0.002 |
Neg logit contributions | |
izing | -0.007 |
yles | -0.007 |
ning | -0.007 |
ellery | -0.007 |
ants | -0.007 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
izing | +0.022 |
yles | +0.022 |
ellery | +0.021 |
rily | +0.021 |
ning | +0.021 |
Neg logit contributions | |
am | -0.006 |
big | -0.006 |
story | -0.005 |
| -0.005 |
done | -0.005 |
Token | ish |
Token ID | 680 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
izing | +0.184 |
yles | +0.177 |
king | +0.165 |
rily | +0.164 |
ellery | +0.162 |
Neg logit contributions | |
am | -0.316 |
| -0.300 |
big | -0.296 |
done | -0.294 |
to | -0.292 |
Token | ! |
Token ID | 0 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
izing | +0.116 |
yles | +0.114 |
ning | +0.110 |
ellery | +0.110 |
king | +0.110 |
Neg logit contributions | |
am | -0.042 |
| -0.037 |
done | -0.036 |
story | -0.034 |
big | -0.034 |
Token | She |
Token ID | 1375 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
done | +0.005 |
am | +0.005 |
story | +0.005 |
bad | +0.004 |
own | +0.004 |
Neg logit contributions | |
izing | -0.007 |
yles | -0.007 |
ning | -0.007 |
rily | -0.007 |
ivating | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
am | +0.014 |
done | +0.012 |
| +0.012 |
story | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.047 |
yles | -0.045 |
ning | -0.045 |
king | -0.044 |
ellery | -0.044 |
Token | really |
Token ID | 1107 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
| +0.001 |
big | +0.001 |
to | +0.001 |
Neg logit contributions | |
izing | -0.003 |
yles | -0.002 |
ning | -0.002 |
king | -0.002 |
ellery | -0.002 |
Token | legs |
Token ID | 7405 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
izing | +0.020 |
ning | +0.019 |
king | +0.019 |
yles | +0.018 |
ellery | +0.018 |
Neg logit contributions | |
am | -0.025 |
done | -0.024 |
| -0.023 |
story | -0.023 |
big | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
izing | +0.094 |
yles | +0.091 |
ning | +0.091 |
king | +0.091 |
rily | +0.090 |
Neg logit contributions | |
am | -0.015 |
done | -0.012 |
| -0.011 |
story | -0.010 |
big | -0.009 |
Token | It |
Token ID | 632 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
done | +0.011 |
am | +0.011 |
story | +0.009 |
bad | +0.008 |
big | +0.007 |
Neg logit contributions | |
rily | -0.028 |
yles | -0.027 |
izing | -0.027 |
ning | -0.026 |
ants | -0.026 |
Token | is |
Token ID | 318 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
izing | +0.016 |
yles | +0.016 |
ning | +0.016 |
king | +0.015 |
rily | +0.015 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
| -0.003 |
story | -0.002 |
big | -0.002 |
Token | an |
Token ID | 281 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
izing | +0.014 |
yles | +0.014 |
ellery | +0.013 |
rily | +0.013 |
ants | +0.013 |
Neg logit contributions | |
am | -0.005 |
big | -0.005 |
done | -0.005 |
| -0.005 |
to | -0.004 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
yles | +0.059 |
izing | +0.058 |
king | +0.056 |
ning | +0.054 |
etti | +0.053 |
Neg logit contributions | |
big | -0.047 |
done | -0.046 |
bad | -0.046 |
story | -0.045 |
am | -0.045 |
Token | ich |
Token ID | 488 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
izing | +0.166 |
rily | +0.161 |
yles | +0.159 |
ivating | +0.148 |
ellery | +0.144 |
Neg logit contributions | |
am | -0.326 |
done | -0.310 |
| -0.309 |
story | -0.307 |
big | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
izing | +0.114 |
yles | +0.112 |
rily | +0.109 |
king | +0.109 |
ellery | +0.108 |
Neg logit contributions | |
am | -0.017 |
| -0.014 |
done | -0.012 |
to | -0.011 |
story | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
am | +0.006 |
done | +0.006 |
story | +0.005 |
bad | +0.004 |
big | +0.004 |
Neg logit contributions | |
izing | -0.020 |
yles | -0.020 |
rily | -0.020 |
ning | -0.019 |
king | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
done | +0.001 |
am | +0.001 |
bad | +0.000 |
story | +0.000 |
way | +0.000 |
Neg logit contributions | |
izing | -0.004 |
yles | -0.004 |
rily | -0.004 |
ning | -0.004 |
ivating | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
yles | +0.049 |
ning | +0.048 |
izing | +0.048 |
ellery | +0.048 |
bul | +0.047 |
Neg logit contributions | |
am | -0.032 |
| -0.032 |
big | -0.029 |
done | -0.028 |
time | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
izing | +0.040 |
yles | +0.039 |
rily | +0.038 |
ning | +0.038 |
ellery | +0.038 |
Neg logit contributions | |
am | -0.005 |
| -0.004 |
done | -0.004 |
to | -0.003 |
big | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
izing | +0.090 |
yles | +0.087 |
rily | +0.087 |
ning | +0.087 |
king | +0.086 |
Neg logit contributions | |
am | -0.047 |
| -0.047 |
to | -0.043 |
big | -0.043 |
done | -0.042 |
Token | found |
Token ID | 1043 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
am | +0.015 |
done | +0.014 |
story | +0.014 |
| +0.013 |
bad | +0.012 |
Neg logit contributions | |
yles | -0.041 |
ning | -0.040 |
burn | -0.039 |
king | -0.039 |
izing | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.037 |
ning | +0.037 |
king | +0.036 |
ellery | +0.036 |
Neg logit contributions | |
am | -0.009 |
done | -0.008 |
| -0.008 |
story | -0.007 |
big | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
am | +0.009 |
| +0.008 |
done | +0.008 |
story | +0.008 |
big | +0.008 |
Neg logit contributions | |
izing | -0.033 |
yles | -0.032 |
ning | -0.032 |
ellery | -0.032 |
king | -0.032 |
Token | rad |
Token ID | 2511 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
yles | +0.083 |
izing | +0.082 |
ants | +0.081 |
rily | +0.080 |
king | +0.080 |
Neg logit contributions | |
am | -0.032 |
big | -0.031 |
story | -0.029 |
done | -0.028 |
to | -0.027 |
Token | ish |
Token ID | 680 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
izing | +0.189 |
yles | +0.181 |
rily | +0.170 |
king | +0.169 |
ivating | +0.168 |
Neg logit contributions | |
am | -0.307 |
| -0.289 |
to | -0.285 |
big | -0.284 |
done | -0.281 |
Token | in |
Token ID | 287 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
izing | +0.109 |
yles | +0.107 |
ning | +0.104 |
ellery | +0.103 |
king | +0.103 |
Neg logit contributions | |
am | -0.044 |
| -0.040 |
done | -0.039 |
to | -0.037 |
story | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
izing | +0.013 |
king | +0.013 |
yles | +0.013 |
ning | +0.013 |
ants | +0.013 |
Neg logit contributions | |
am | -0.004 |
| -0.004 |
big | -0.003 |
done | -0.003 |
to | -0.003 |
Token | garden |
Token ID | 11376 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
am | +0.042 |
done | +0.039 |
story | +0.033 |
lesson | +0.033 |
bad | +0.032 |
Neg logit contributions | |
ning | -0.073 |
ellery | -0.073 |
bing | -0.068 |
izing | -0.068 |
yles | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
bad | +0.005 |
story | +0.005 |
| +0.005 |
Neg logit contributions | |
izing | -0.026 |
ning | -0.025 |
king | -0.024 |
ellery | -0.024 |
bing | -0.024 |
Token | Spot |
Token ID | 15899 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
izing | +0.030 |
yles | +0.028 |
ellery | +0.028 |
rily | +0.028 |
king | +0.028 |
Neg logit contributions | |
am | -0.020 |
| -0.020 |
done | -0.018 |
big | -0.018 |
to | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ning | +0.062 |
izing | +0.061 |
bing | +0.061 |
yles | +0.059 |
ellery | +0.059 |
Neg logit contributions | |
done | -0.025 |
am | -0.024 |
story | -0.024 |
lesson | -0.021 |
tum | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
izing | +0.011 |
yles | +0.011 |
ning | +0.010 |
rily | +0.010 |
ellery | +0.010 |
Neg logit contributions | |
am | -0.002 |
| -0.002 |
done | -0.002 |
big | -0.002 |
story | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
izing | +0.062 |
yles | +0.062 |
rily | +0.060 |
ants | +0.060 |
ellery | +0.060 |
Neg logit contributions | |
am | -0.019 |
big | -0.017 |
| -0.017 |
bad | -0.015 |
done | -0.015 |
Token | lovely |
Token ID | 14081 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
izing | +0.027 |
king | +0.025 |
yles | +0.025 |
ning | +0.025 |
ellery | +0.025 |
Neg logit contributions | |
am | -0.015 |
done | -0.013 |
| -0.013 |
story | -0.012 |
to | -0.012 |
Token | po |
Token ID | 745 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
izing | +0.031 |
ning | +0.031 |
king | +0.030 |
yles | +0.029 |
burn | +0.029 |
Neg logit contributions | |
am | -0.020 |
done | -0.019 |
| -0.018 |
story | -0.016 |
bad | -0.016 |
Token | och |
Token ID | 5374 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
rily | +0.214 |
izing | +0.211 |
yles | +0.202 |
ellery | +0.189 |
bul | +0.187 |
Neg logit contributions | |
am | -0.275 |
| -0.272 |
to | -0.251 |
ossible | -0.249 |
story | -0.246 |
Token | and |
Token ID | 290 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
izing | +0.124 |
yles | +0.123 |
rily | +0.118 |
ellery | +0.118 |
ants | +0.118 |
Neg logit contributions | |
am | -0.040 |
| -0.039 |
to | -0.038 |
done | -0.034 |
big | -0.033 |
Token | he |
Token ID | 339 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
izing | +0.101 |
yles | +0.098 |
ning | +0.097 |
king | +0.096 |
ellery | +0.096 |
Neg logit contributions | |
am | -0.029 |
done | -0.025 |
| -0.025 |
story | -0.023 |
big | -0.021 |
Token | always |
Token ID | 1464 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
am | +0.006 |
done | +0.006 |
story | +0.006 |
| +0.006 |
ossible | +0.005 |
Neg logit contributions | |
izing | -0.014 |
yles | -0.013 |
ning | -0.013 |
ellery | -0.013 |
king | -0.013 |
Token | tried |
Token ID | 3088 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
am | +0.006 |
story | +0.006 |
| +0.006 |
done | +0.006 |
big | +0.005 |
Neg logit contributions | |
izing | -0.016 |
yles | -0.015 |
ning | -0.015 |
king | -0.015 |
ellery | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
am | +0.010 |
done | +0.010 |
story | +0.009 |
| +0.009 |
bad | +0.008 |
Neg logit contributions | |
izing | -0.024 |
yles | -0.024 |
ning | -0.024 |
ellery | -0.023 |
rily | -0.023 |
Token | zoo |
Token ID | 26626 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
am | +0.003 |
done | +0.003 |
| +0.003 |
story | +0.003 |
to | +0.003 |
Neg logit contributions | |
izing | -0.004 |
ning | -0.004 |
yles | -0.004 |
ellery | -0.004 |
king | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
izing | +0.023 |
ning | +0.023 |
king | +0.022 |
ellery | +0.021 |
bing | +0.021 |
Neg logit contributions | |
am | -0.018 |
done | -0.016 |
bad | -0.016 |
story | -0.015 |
lesson | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
yles | +0.032 |
ning | +0.031 |
izing | +0.030 |
ting | +0.030 |
king | +0.030 |
Neg logit contributions | |
am | -0.013 |
story | -0.012 |
done | -0.011 |
time | -0.010 |
lesson | -0.010 |
Token | an |
Token ID | 281 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
am | +0.000 |
done | +0.000 |
story | +0.000 |
| +0.000 |
time | +0.000 |
Neg logit contributions | |
izing | -0.001 |
ning | -0.001 |
yles | -0.001 |
ellery | -0.001 |
rily | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
yles | +0.094 |
izing | +0.091 |
king | +0.089 |
burn | +0.088 |
ning | +0.086 |
Neg logit contributions | |
big | -0.053 |
bad | -0.049 |
story | -0.047 |
am | -0.046 |
| -0.046 |
Token | ich |
Token ID | 488 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
rily | +0.190 |
izing | +0.175 |
yles | +0.174 |
ivating | +0.160 |
ellery | +0.159 |
Neg logit contributions | |
am | -0.303 |
| -0.288 |
story | -0.282 |
done | -0.280 |
big | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
izing | +0.092 |
yles | +0.089 |
ning | +0.089 |
king | +0.088 |
ellery | +0.087 |
Neg logit contributions | |
am | -0.023 |
done | -0.020 |
| -0.019 |
story | -0.017 |
big | -0.017 |
Token | It |
Token ID | 632 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
| +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.006 |
yles | -0.006 |
ning | -0.006 |
king | -0.006 |
ellery | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
izing | +0.020 |
yles | +0.019 |
ellery | +0.019 |
king | +0.019 |
ning | +0.019 |
Neg logit contributions | |
am | -0.002 |
| -0.001 |
done | -0.001 |
big | -0.001 |
story | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
izing | +0.035 |
yles | +0.034 |
ning | +0.034 |
king | +0.034 |
ellery | +0.034 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
| -0.009 |
big | -0.009 |
story | -0.009 |
Token | burger |
Token ID | 26593 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
izing | +0.031 |
yles | +0.030 |
ning | +0.030 |
king | +0.029 |
ellery | +0.029 |
Neg logit contributions | |
am | -0.023 |
done | -0.021 |
| -0.021 |
story | -0.020 |
big | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
izing | +0.069 |
ning | +0.067 |
king | +0.066 |
yles | +0.066 |
rily | +0.066 |
Neg logit contributions | |
am | -0.026 |
done | -0.023 |
| -0.022 |
story | -0.021 |
big | -0.020 |
Token | fries |
Token ID | 31757 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
izing | +0.036 |
yles | +0.034 |
ning | +0.034 |
king | +0.034 |
ellery | +0.033 |
Neg logit contributions | |
am | -0.017 |
| -0.016 |
done | -0.016 |
big | -0.016 |
to | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
izing | +0.034 |
ning | +0.033 |
king | +0.033 |
yles | +0.033 |
rily | +0.032 |
Neg logit contributions | |
am | -0.010 |
done | -0.009 |
| -0.008 |
story | -0.008 |
big | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
izing | +0.060 |
yles | +0.058 |
ning | +0.056 |
rily | +0.056 |
ellery | +0.056 |
Neg logit contributions | |
am | -0.061 |
done | -0.057 |
| -0.056 |
story | -0.055 |
big | -0.052 |
Token | mil |
Token ID | 1465 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
am | +0.013 |
done | +0.012 |
| +0.011 |
story | +0.010 |
to | +0.010 |
Neg logit contributions | |
izing | -0.025 |
king | -0.024 |
rily | -0.024 |
yles | -0.024 |
ning | -0.024 |
Token | ksh |
Token ID | 50133 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
izing | +0.130 |
yles | +0.119 |
bul | +0.107 |
ths | +0.096 |
ning | +0.096 |
Neg logit contributions | |
done | -0.341 |
| -0.339 |
to | -0.338 |
am | -0.333 |
whole | -0.327 |
Token | ake |
Token ID | 539 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
izing | +0.094 |
yles | +0.090 |
ning | +0.087 |
ellery | +0.086 |
king | +0.086 |
Neg logit contributions | |
am | -0.116 |
done | -0.110 |
| -0.109 |
story | -0.106 |
big | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
izing | +0.017 |
yles | +0.017 |
ning | +0.017 |
king | +0.017 |
rily | +0.017 |
Neg logit contributions | |
am | -0.005 |
done | -0.004 |
| -0.004 |
story | -0.004 |
big | -0.004 |
Token | But |
Token ID | 887 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
| +0.007 |
am | +0.006 |
to | +0.006 |
done | +0.005 |
big | +0.005 |
Neg logit contributions | |
izing | -0.021 |
yles | -0.020 |
ning | -0.020 |
king | -0.020 |
ellery | -0.020 |
Token | after |
Token ID | 706 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
izing | +0.000 |
yles | +0.000 |
king | +0.000 |
ellery | +0.000 |
ning | +0.000 |
Neg logit contributions | |
am | -0.000 |
| -0.000 |
done | -0.000 |
to | -0.000 |
was | -0.000 |
Token | watched |
Token ID | 7342 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
am | +0.018 |
done | +0.016 |
| +0.016 |
story | +0.016 |
time | +0.015 |
Neg logit contributions | |
izing | -0.038 |
yles | -0.038 |
rily | -0.037 |
ellery | -0.037 |
ning | -0.036 |
Token | as |
Token ID | 355 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
yles | +0.023 |
ellery | +0.023 |
izing | +0.022 |
ning | +0.022 |
burn | +0.022 |
Neg logit contributions | |
to | -0.009 |
| -0.009 |
big | -0.009 |
done | -0.008 |
time | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
izing | +0.007 |
yles | +0.007 |
ning | +0.007 |
king | +0.007 |
ellery | +0.007 |
Neg logit contributions | |
am | -0.003 |
| -0.002 |
done | -0.002 |
big | -0.002 |
to | -0.002 |
Token | baked |
Token ID | 22979 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
am | +0.015 |
done | +0.014 |
| +0.014 |
big | +0.013 |
story | +0.013 |
Neg logit contributions | |
izing | -0.033 |
yles | -0.032 |
ning | -0.031 |
king | -0.031 |
rily | -0.031 |
Token | until |
Token ID | 1566 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
izing | +0.016 |
yles | +0.015 |
ning | +0.015 |
king | +0.015 |
ellery | +0.015 |
Neg logit contributions | |
am | -0.006 |
done | -0.005 |
| -0.005 |
big | -0.005 |
story | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
am | +0.029 |
done | +0.026 |
| +0.026 |
story | +0.025 |
big | +0.024 |
Neg logit contributions | |
izing | -0.061 |
yles | -0.059 |
ning | -0.058 |
rily | -0.057 |
king | -0.057 |
Token | were |
Token ID | 547 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
am | +0.025 |
story | +0.022 |
| +0.021 |
done | +0.019 |
bad | +0.018 |
Neg logit contributions | |
yles | -0.061 |
izing | -0.060 |
rily | -0.059 |
ellery | -0.059 |
king | -0.058 |
Token | golden |
Token ID | 10861 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
am | +0.022 |
| +0.019 |
done | +0.018 |
story | +0.018 |
big | +0.016 |
Neg logit contributions | |
izing | -0.051 |
yles | -0.050 |
ning | -0.049 |
king | -0.049 |
rily | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
izing | +0.047 |
yles | +0.047 |
ning | +0.045 |
ellery | +0.045 |
king | +0.045 |
Neg logit contributions | |
am | -0.018 |
done | -0.016 |
| -0.016 |
big | -0.016 |
to | -0.015 |
Token | When |
Token ID | 1649 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
am | +0.013 |
done | +0.011 |
| +0.011 |
story | +0.010 |
big | +0.009 |
Neg logit contributions | |
izing | -0.057 |
yles | -0.055 |
ning | -0.055 |
king | -0.054 |
ellery | -0.054 |
Token | they |
Token ID | 484 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.021 |
| +0.021 |
story | +0.020 |
big | +0.019 |
Neg logit contributions | |
izing | -0.044 |
yles | -0.043 |
ning | -0.042 |
ellery | -0.041 |
rily | -0.041 |
Token | He |
Token ID | 679 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
done | +0.032 |
am | +0.032 |
bad | +0.029 |
story | +0.028 |
big | +0.026 |
Neg logit contributions | |
izing | -0.048 |
rily | -0.046 |
ning | -0.046 |
ants | -0.046 |
yles | -0.046 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
am | +0.023 |
| +0.021 |
done | +0.021 |
story | +0.019 |
big | +0.019 |
Neg logit contributions | |
izing | -0.060 |
yles | -0.058 |
ning | -0.057 |
king | -0.056 |
ellery | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
am | +0.024 |
done | +0.022 |
| +0.020 |
story | +0.020 |
time | +0.018 |
Neg logit contributions | |
izing | -0.055 |
king | -0.053 |
ning | -0.053 |
rily | -0.053 |
yles | -0.053 |
Token | carefully |
Token ID | 7773 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
izing | +0.019 |
yles | +0.018 |
ning | +0.018 |
king | +0.018 |
ellery | +0.018 |
Neg logit contributions | |
am | -0.010 |
done | -0.009 |
| -0.009 |
story | -0.009 |
big | -0.008 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
am | +0.037 |
done | +0.034 |
| +0.034 |
story | +0.032 |
big | +0.032 |
Neg logit contributions | |
izing | -0.055 |
yles | -0.053 |
ning | -0.052 |
king | -0.051 |
ellery | -0.051 |
Token | it |
Token ID | 340 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
izing | +0.046 |
rily | +0.046 |
ning | +0.045 |
yles | +0.044 |
ellery | +0.044 |
Neg logit contributions | |
am | -0.031 |
done | -0.027 |
story | -0.026 |
| -0.026 |
bad | -0.024 |
Token | down |
Token ID | 866 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
am | +0.023 |
done | +0.018 |
story | +0.018 |
| +0.016 |
bad | +0.015 |
Neg logit contributions | |
ellery | -0.067 |
ning | -0.067 |
rily | -0.067 |
izing | -0.066 |
king | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.018 |
story | +0.017 |
| +0.016 |
bad | +0.015 |
Neg logit contributions | |
izing | -0.059 |
ning | -0.057 |
rily | -0.057 |
king | -0.056 |
bing | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
done | +0.027 |
am | +0.026 |
bad | +0.025 |
story | +0.023 |
big | +0.020 |
Neg logit contributions | |
izing | -0.070 |
yles | -0.069 |
ning | -0.069 |
rily | -0.068 |
ants | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
done | +0.008 |
am | +0.008 |
bad | +0.007 |
way | +0.006 |
story | +0.006 |
Neg logit contributions | |
ants | -0.039 |
izing | -0.038 |
yles | -0.038 |
shadow | -0.038 |
rily | -0.038 |
Token | When |
Token ID | 2215 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
izing | +0.016 |
yles | +0.015 |
ning | +0.015 |
king | +0.015 |
ants | +0.015 |
Neg logit contributions | |
am | -0.019 |
done | -0.018 |
story | -0.018 |
| -0.017 |
big | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
izing | +0.045 |
yles | +0.045 |
ellery | +0.044 |
rily | +0.044 |
king | +0.043 |
Neg logit contributions | |
am | -0.010 |
| -0.010 |
to | -0.009 |
big | -0.009 |
done | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
izing | +0.154 |
yles | +0.150 |
ellery | +0.148 |
king | +0.148 |
ning | +0.148 |
Neg logit contributions | |
am | -0.045 |
| -0.041 |
done | -0.039 |
big | -0.038 |
to | -0.034 |
Token | stripes |
Token ID | 28806 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ning | +0.027 |
izing | +0.027 |
ellery | +0.027 |
yles | +0.027 |
king | +0.027 |
Neg logit contributions | |
am | -0.013 |
done | -0.011 |
story | -0.010 |
| -0.009 |
ossible | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
izing | +0.068 |
ning | +0.067 |
king | +0.066 |
yles | +0.065 |
rily | +0.065 |
Neg logit contributions | |
am | -0.022 |
done | -0.019 |
story | -0.018 |
| -0.017 |
bad | -0.015 |
Token | over |
Token ID | 625 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
am | +0.015 |
story | +0.013 |
done | +0.012 |
| +0.012 |
bad | +0.012 |
Neg logit contributions | |
izing | -0.022 |
ning | -0.022 |
yles | -0.021 |
bing | -0.021 |
ellery | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
am | +0.006 |
done | +0.005 |
story | +0.005 |
| +0.005 |
bad | +0.004 |
Neg logit contributions | |
izing | -0.015 |
yles | -0.014 |
ning | -0.014 |
ellery | -0.014 |
rily | -0.014 |
Token | body |
Token ID | 1767 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
am | +0.056 |
done | +0.051 |
| +0.046 |
story | +0.045 |
lesson | +0.045 |
Neg logit contributions | |
ning | -0.061 |
king | -0.060 |
izing | -0.060 |
bing | -0.059 |
rily | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
am | +0.001 |
done | +0.001 |
story | +0.001 |
| +0.001 |
bad | +0.001 |
Neg logit contributions | |
izing | -0.004 |
ning | -0.004 |
king | -0.004 |
rily | -0.004 |
bing | -0.004 |
Token | Jack |
Token ID | 3619 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
am | +0.017 |
done | +0.016 |
bad | +0.014 |
story | +0.013 |
big | +0.012 |
Neg logit contributions | |
yles | -0.027 |
izing | -0.026 |
ning | -0.025 |
rily | -0.025 |
ivating | -0.024 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
izing | +0.025 |
yles | +0.024 |
ning | +0.024 |
king | +0.024 |
ellery | +0.023 |
Neg logit contributions | |
am | -0.008 |
done | -0.007 |
story | -0.007 |
| -0.007 |
big | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
am | +0.005 |
done | +0.003 |
story | +0.003 |
| +0.003 |
ossible | +0.002 |
Neg logit contributions | |
ning | -0.019 |
yles | -0.019 |
ellery | -0.019 |
izing | -0.018 |
king | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
am | +0.003 |
done | +0.002 |
| +0.002 |
story | +0.002 |
to | +0.002 |
Neg logit contributions | |
izing | -0.008 |
yles | -0.007 |
ning | -0.007 |
king | -0.007 |
ellery | -0.007 |
Token | never |
Token ID | 1239 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
am | +0.000 |
story | +0.000 |
| +0.000 |
ossible | +0.000 |
| +0.000 |
Neg logit contributions | |
ellery | -0.000 |
ning | -0.000 |
izing | -0.000 |
yles | -0.000 |
king | -0.000 |
Token | seen |
Token ID | 1775 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ning | +0.020 |
ellery | +0.020 |
king | +0.020 |
shadow | +0.020 |
yles | +0.020 |
Neg logit contributions | |
am | -0.015 |
story | -0.014 |
| -0.014 |
ossible | -0.014 |
big | -0.012 |
Token | before |
Token ID | 878 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
izing | +0.010 |
yles | +0.009 |
rily | +0.009 |
ants | +0.009 |
king | +0.009 |
Neg logit contributions | |
| -0.006 |
am | -0.006 |
done | -0.006 |
to | -0.006 |
time | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
am | +0.028 |
done | +0.023 |
story | +0.019 |
| +0.018 |
ossible | +0.018 |
Neg logit contributions | |
izing | -0.111 |
ning | -0.107 |
bing | -0.105 |
yles | -0.105 |
rily | -0.104 |
Token | |
Token ID | 220 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
am | +0.004 |
done | +0.003 |
story | +0.003 |
bad | +0.002 |
time | +0.002 |
Neg logit contributions | |
izing | -0.008 |
rily | -0.007 |
ning | -0.007 |
yles | -0.007 |
ivating | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
done | +0.022 |
am | +0.022 |
story | +0.017 |
bad | +0.017 |
learned | +0.014 |
Neg logit contributions | |
yles | -0.101 |
izing | -0.099 |
ants | -0.098 |
ning | -0.098 |
rily | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
am | +0.006 |
done | +0.006 |
bad | +0.004 |
story | +0.004 |
consequences | +0.004 |
Neg logit contributions | |
izing | -0.025 |
yles | -0.025 |
ning | -0.024 |
ants | -0.024 |
shadow | -0.024 |
Token | â |
Token ID | 22940 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
izing | +0.034 |
yles | +0.031 |
king | +0.030 |
ellery | +0.030 |
ning | +0.030 |
Neg logit contributions | |
am | -0.034 |
done | -0.031 |
story | -0.029 |
| -0.029 |
to | -0.028 |
Token | € |
Token ID | 26391 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
izing | +0.102 |
king | +0.093 |
ning | +0.093 |
bing | +0.092 |
yles | +0.091 |
Neg logit contributions | |
am | -0.094 |
big | -0.089 |
| -0.088 |
story | -0.088 |
done | -0.086 |
Token | � |
Token ID | 129 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.038 |
king | +0.037 |
etti | +0.037 |
ning | +0.037 |
Neg logit contributions | |
am | -0.024 |
story | -0.022 |
done | -0.021 |
bad | -0.021 |
lesson | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
izing | +0.062 |
yles | +0.060 |
ning | +0.059 |
king | +0.059 |
rily | +0.058 |
Neg logit contributions | |
am | -0.020 |
done | -0.018 |
| -0.017 |
story | -0.016 |
big | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
| +0.006 |
story | +0.005 |
big | +0.005 |
Neg logit contributions | |
izing | -0.019 |
yles | -0.018 |
ning | -0.018 |
king | -0.018 |
ellery | -0.018 |
Token | town |
Token ID | 3240 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
am | +0.015 |
done | +0.014 |
to | +0.012 |
lesson | +0.011 |
story | +0.011 |
Neg logit contributions | |
izing | -0.023 |
ning | -0.022 |
yles | -0.022 |
king | -0.022 |
ivating | -0.021 |
Token | were |
Token ID | 547 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
am | +0.006 |
story | +0.005 |
done | +0.004 |
| +0.004 |
bad | +0.004 |
Neg logit contributions | |
izing | -0.017 |
yles | -0.016 |
ning | -0.016 |
king | -0.016 |
bing | -0.015 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
izing | +0.001 |
yles | +0.000 |
ning | +0.000 |
king | +0.000 |
ellery | +0.000 |
Neg logit contributions | |
am | -0.000 |
| -0.000 |
done | -0.000 |
story | -0.000 |
big | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
izing | +0.004 |
yles | +0.004 |
ning | +0.004 |
king | +0.004 |
ellery | +0.004 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
story | -0.001 |
big | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
am | +0.042 |
done | +0.040 |
story | +0.037 |
ossible | +0.037 |
| +0.036 |
Neg logit contributions | |
izing | -0.061 |
yles | -0.058 |
ning | -0.056 |
king | -0.055 |
bing | -0.054 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
am | +0.017 |
story | +0.014 |
done | +0.014 |
| +0.013 |
lesson | +0.012 |
Neg logit contributions | |
yles | -0.053 |
izing | -0.052 |
king | -0.052 |
ning | -0.051 |
ting | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
izing | +0.015 |
yles | +0.015 |
ning | +0.014 |
king | +0.014 |
ellery | +0.014 |
Neg logit contributions | |
am | -0.006 |
done | -0.005 |
| -0.005 |
big | -0.005 |
story | -0.005 |
Token | tank |
Token ID | 6873 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
am | +0.017 |
done | +0.015 |
| +0.014 |
ossible | +0.014 |
to | +0.014 |
Neg logit contributions | |
izing | -0.021 |
king | -0.020 |
ning | -0.020 |
yles | -0.019 |
rily | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
izing | +0.003 |
ning | +0.003 |
king | +0.003 |
rily | +0.003 |
bing | +0.003 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
ossible | -0.001 |
story | -0.001 |
Token | ." |
Token ID | 526 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
izing | +0.001 |
yles | +0.001 |
ning | +0.001 |
rily | +0.001 |
king | +0.001 |
Neg logit contributions | |
am | -0.001 |
done | -0.000 |
story | -0.000 |
| -0.000 |
bad | -0.000 |
Token | Mom |
Token ID | 11254 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
done | +0.013 |
am | +0.012 |
story | +0.009 |
whole | +0.008 |
bad | +0.008 |
Neg logit contributions | |
yles | -0.041 |
izing | -0.039 |
rily | -0.039 |
burn | -0.038 |
ants | -0.038 |
Token | said |
Token ID | 531 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
| +0.000 |
am | +0.000 |
done | +0.000 |
to | +0.000 |
was | +0.000 |
Neg logit contributions | |
izing | -0.003 |
yles | -0.003 |
ellery | -0.003 |
king | -0.003 |
ning | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
izing | +0.005 |
rily | +0.005 |
king | +0.005 |
yles | +0.005 |
ning | +0.005 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
story | -0.001 |
| -0.001 |
big | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
done | +0.003 |
am | +0.003 |
story | +0.002 |
bad | +0.002 |
time | +0.001 |
Neg logit contributions | |
izing | -0.017 |
yles | -0.017 |
ning | -0.016 |
king | -0.016 |
rily | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
done | +0.006 |
am | +0.005 |
way | +0.004 |
story | +0.004 |
bad | +0.004 |
Neg logit contributions | |
izing | -0.021 |
yles | -0.021 |
bing | -0.020 |
ang | -0.020 |
ants | -0.020 |
Token | They |
Token ID | 2990 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
izing | +0.029 |
yles | +0.028 |
ning | +0.028 |
king | +0.027 |
rily | +0.027 |
Neg logit contributions | |
am | -0.024 |
| -0.023 |
done | -0.022 |
story | -0.021 |
big | -0.021 |
Token | closed |
Token ID | 4838 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
am | +0.028 |
done | +0.026 |
| +0.025 |
story | +0.023 |
big | +0.023 |
Neg logit contributions | |
izing | -0.064 |
yles | -0.062 |
ning | -0.061 |
king | -0.061 |
ellery | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
izing | +0.068 |
yles | +0.066 |
ning | +0.065 |
king | +0.065 |
ellery | +0.065 |
Neg logit contributions | |
am | -0.023 |
| -0.022 |
done | -0.021 |
big | -0.019 |
to | -0.019 |
Token | book |
Token ID | 1492 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
am | +0.038 |
done | +0.037 |
| +0.036 |
'm | +0.034 |
felt | +0.031 |
Neg logit contributions | |
izing | -0.046 |
ning | -0.046 |
rily | -0.045 |
ries | -0.044 |
bul | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
am | +0.018 |
done | +0.016 |
| +0.015 |
story | +0.014 |
bad | +0.013 |
Neg logit contributions | |
izing | -0.044 |
rily | -0.041 |
ning | -0.041 |
yles | -0.041 |
king | -0.041 |
Token | Annie |
Token ID | 25860 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
izing | +0.067 |
yles | +0.064 |
ning | +0.064 |
king | +0.063 |
rily | +0.062 |
Neg logit contributions | |
am | -0.044 |
| -0.042 |
done | -0.041 |
to | -0.039 |
big | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
izing | +0.005 |
yles | +0.005 |
ning | +0.004 |
king | +0.004 |
ellery | +0.004 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
story | -0.000 |
big | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
am | +0.004 |
done | +0.004 |
bad | +0.003 |
story | +0.003 |
big | +0.003 |
Neg logit contributions | |
izing | -0.007 |
yles | -0.007 |
rily | -0.007 |
ellery | -0.007 |
ning | -0.007 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
am | +0.013 |
done | +0.012 |
story | +0.012 |
ossible | +0.011 |
| +0.011 |
Neg logit contributions | |
izing | -0.022 |
ning | -0.021 |
ellery | -0.021 |
pian | -0.021 |
yles | -0.021 |
Token | going |
Token ID | 1016 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
| +0.002 |
to | +0.002 |
big | +0.001 |
Neg logit contributions | |
izing | -0.019 |
rily | -0.018 |
king | -0.018 |
yles | -0.018 |
ning | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
ning | +0.044 |
burn | +0.041 |
izing | +0.041 |
yles | +0.041 |
king | +0.041 |
Neg logit contributions | |
am | -0.017 |
done | -0.014 |
| -0.013 |
story | -0.013 |
bad | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
am | +0.010 |
| +0.009 |
done | +0.008 |
big | +0.008 |
story | +0.008 |
Neg logit contributions | |
izing | -0.032 |
king | -0.031 |
rily | -0.031 |
yles | -0.031 |
ning | -0.030 |
Token | beach |
Token ID | 10481 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
am | +0.009 |
| +0.009 |
big | +0.008 |
done | +0.008 |
story | +0.008 |
Neg logit contributions | |
izing | -0.026 |
yles | -0.026 |
rily | -0.025 |
king | -0.025 |
ning | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
izing | +0.036 |
ning | +0.035 |
ellery | +0.034 |
yles | +0.034 |
king | +0.034 |
Neg logit contributions | |
am | -0.022 |
done | -0.020 |
| -0.019 |
story | -0.019 |
bad | -0.018 |
Token | playing |
Token ID | 2712 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
izing | +0.084 |
yles | +0.082 |
ning | +0.080 |
king | +0.079 |
ellery | +0.079 |
Neg logit contributions | |
am | -0.064 |
done | -0.060 |
| -0.058 |
story | -0.057 |
big | -0.054 |
Token | with |
Token ID | 351 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
izing | +0.021 |
bing | +0.020 |
ning | +0.020 |
rily | +0.020 |
yles | +0.019 |
Neg logit contributions | |
am | -0.013 |
done | -0.012 |
story | -0.011 |
| -0.011 |
bad | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
yles | +0.030 |
izing | +0.030 |
ning | +0.030 |
ellery | +0.029 |
rily | +0.029 |
Neg logit contributions | |
| -0.017 |
am | -0.017 |
done | -0.015 |
big | -0.015 |
story | -0.014 |
Token | fox |
Token ID | 21831 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
izing | +0.023 |
yles | +0.022 |
ellery | +0.021 |
rily | +0.021 |
ning | +0.021 |
Neg logit contributions | |
am | -0.018 |
| -0.017 |
done | -0.017 |
story | -0.016 |
big | -0.016 |
Token | worked |
Token ID | 3111 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
izing | +0.017 |
yles | +0.016 |
ning | +0.016 |
king | +0.016 |
ellery | +0.016 |
Neg logit contributions | |
am | -0.005 |
done | -0.004 |
| -0.004 |
story | -0.004 |
big | -0.004 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
am | +0.008 |
story | +0.007 |
| +0.007 |
ossible | +0.006 |
'm | +0.006 |
Neg logit contributions | |
izing | -0.015 |
bing | -0.014 |
ning | -0.014 |
rily | -0.014 |
king | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
am | +0.027 |
story | +0.022 |
ossible | +0.020 |
done | +0.020 |
| +0.020 |
Neg logit contributions | |
izing | -0.059 |
ning | -0.055 |
bing | -0.054 |
king | -0.053 |
rily | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
izing | +0.059 |
yles | +0.058 |
ants | +0.057 |
ning | +0.057 |
ellery | +0.057 |
Neg logit contributions | |
am | -0.024 |
done | -0.024 |
| -0.024 |
to | -0.023 |
big | -0.022 |
Token | when |
Token ID | 618 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
izing | +0.031 |
yles | +0.030 |
ants | +0.029 |
king | +0.029 |
ellery | +0.029 |
Neg logit contributions | |
done | -0.017 |
am | -0.017 |
| -0.016 |
to | -0.015 |
big | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
am | +0.025 |
done | +0.023 |
| +0.021 |
story | +0.020 |
ossible | +0.019 |
Neg logit contributions | |
izing | -0.064 |
yles | -0.062 |
ning | -0.061 |
bing | -0.059 |
ellery | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
am | +0.029 |
| +0.025 |
story | +0.024 |
done | +0.024 |
big | +0.022 |
Neg logit contributions | |
izing | -0.088 |
yles | -0.086 |
ning | -0.085 |
ellery | -0.084 |
rily | -0.083 |
Token | done |
Token ID | 1760 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
am | +0.019 |
story | +0.015 |
| +0.014 |
| +0.012 |
ossible | +0.011 |
Neg logit contributions | |
izing | -0.062 |
yles | -0.062 |
ning | -0.061 |
king | -0.061 |
shadow | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
am | +0.033 |
done | +0.027 |
| +0.026 |
story | +0.026 |
ossible | +0.024 |
Neg logit contributions | |
izing | -0.103 |
yles | -0.098 |
ning | -0.098 |
bing | -0.098 |
rily | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
izing | +0.001 |
yles | +0.001 |
bing | +0.001 |
ants | +0.001 |
shadow | +0.001 |
Neg logit contributions | |
done | -0.000 |
am | -0.000 |
story | -0.000 |
way | -0.000 |
time | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.036 |
ning | +0.035 |
king | +0.035 |
ellery | +0.035 |
Neg logit contributions | |
am | -0.035 |
done | -0.033 |
| -0.032 |
story | -0.031 |
big | -0.031 |
Token | L |
Token ID | 43 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
izing | +0.159 |
rily | +0.157 |
ning | +0.154 |
ellery | +0.153 |
yles | +0.152 |
Neg logit contributions | |
am | -0.102 |
| -0.097 |
done | -0.086 |
big | -0.085 |
to | -0.083 |
Token | ila |
Token ID | 10102 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
izing | +0.095 |
yles | +0.091 |
ning | +0.090 |
ellery | +0.089 |
king | +0.089 |
Neg logit contributions | |
am | -0.065 |
done | -0.061 |
| -0.060 |
story | -0.058 |
big | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
am | +0.000 |
story | +0.000 |
done | +0.000 |
| +0.000 |
big | +0.000 |
Neg logit contributions | |
izing | -0.000 |
ning | -0.000 |
king | -0.000 |
rily | -0.000 |
ellery | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
izing | +0.139 |
yles | +0.136 |
ning | +0.132 |
ellery | +0.132 |
king | +0.130 |
Neg logit contributions | |
am | -0.084 |
done | -0.078 |
| -0.078 |
story | -0.073 |
big | -0.071 |
Token | know |
Token ID | 760 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
am | +0.007 |
| +0.007 |
story | +0.007 |
done | +0.007 |
day | +0.006 |
Neg logit contributions | |
yles | -0.023 |
izing | -0.022 |
ellery | -0.022 |
ning | -0.022 |
ants | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
am | +0.014 |
| +0.012 |
done | +0.012 |
story | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.041 |
yles | -0.040 |
ning | -0.039 |
ellery | -0.039 |
king | -0.039 |
Token | are |
Token ID | 389 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
| +0.012 |
story | +0.012 |
am | +0.012 |
done | +0.010 |
big | +0.010 |
Neg logit contributions | |
yles | -0.037 |
izing | -0.036 |
ellery | -0.036 |
ning | -0.035 |
king | -0.035 |
Token | not |
Token ID | 407 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
am | +0.010 |
| +0.009 |
done | +0.008 |
story | +0.008 |
big | +0.007 |
Neg logit contributions | |
izing | -0.026 |
yles | -0.026 |
ning | -0.025 |
king | -0.025 |
ellery | -0.025 |
Token | allowed |
Token ID | 3142 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
am | +0.001 |
| +0.001 |
story | +0.001 |
done | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.001 |
ning | -0.001 |
ellery | -0.001 |
king | -0.001 |
yles | -0.001 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
| +0.006 |
story | +0.006 |
big | +0.005 |
Neg logit contributions | |
izing | -0.016 |
yles | -0.015 |
ning | -0.015 |
king | -0.015 |
ellery | -0.015 |
Token | light |
Token ID | 1657 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
yles | +0.051 |
izing | +0.051 |
ellery | +0.050 |
ants | +0.049 |
king | +0.049 |
Neg logit contributions | |
am | -0.028 |
| -0.026 |
done | -0.026 |
big | -0.026 |
story | -0.025 |
Token | shone |
Token ID | 44193 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
izing | +0.037 |
ning | +0.035 |
yles | +0.035 |
king | +0.034 |
rily | +0.034 |
Neg logit contributions | |
am | -0.027 |
done | -0.025 |
| -0.025 |
story | -0.024 |
big | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
izing | +0.091 |
yles | +0.091 |
ellery | +0.088 |
ants | +0.088 |
ning | +0.086 |
Neg logit contributions | |
am | -0.042 |
| -0.039 |
done | -0.039 |
to | -0.039 |
big | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
am | +0.020 |
done | +0.019 |
story | +0.017 |
bad | +0.017 |
big | +0.016 |
Neg logit contributions | |
izing | -0.033 |
yles | -0.033 |
ning | -0.032 |
ellery | -0.032 |
rily | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
am | +0.022 |
done | +0.019 |
| +0.019 |
story | +0.017 |
big | +0.017 |
Neg logit contributions | |
izing | -0.066 |
yles | -0.064 |
ning | -0.063 |
king | -0.062 |
ellery | -0.062 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
am | +0.004 |
| +0.004 |
done | +0.004 |
story | +0.004 |
big | +0.004 |
Neg logit contributions | |
izing | -0.008 |
yles | -0.008 |
ning | -0.008 |
king | -0.008 |
ellery | -0.007 |
Token | surprised |
Token ID | 6655 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
am | +0.020 |
story | +0.018 |
done | +0.017 |
time | +0.017 |
ossible | +0.017 |
Neg logit contributions | |
izing | -0.028 |
yles | -0.027 |
rily | -0.026 |
king | -0.026 |
bing | -0.026 |
Token | that |
Token ID | 326 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
am | +0.015 |
done | +0.013 |
story | +0.013 |
ossible | +0.012 |
| +0.012 |
Neg logit contributions | |
izing | -0.030 |
ning | -0.028 |
king | -0.028 |
yles | -0.027 |
bing | -0.027 |
Token | she |
Token ID | 673 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
am | +0.008 |
done | +0.007 |
| +0.007 |
story | +0.007 |
big | +0.006 |
Neg logit contributions | |
izing | -0.014 |
yles | -0.013 |
ning | -0.013 |
ellery | -0.013 |
king | -0.013 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
am | +0.018 |
done | +0.016 |
| +0.016 |
story | +0.015 |
big | +0.014 |
Neg logit contributions | |
izing | -0.039 |
yles | -0.038 |
ning | -0.037 |
king | -0.037 |
ellery | -0.037 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
am | +0.014 |
done | +0.013 |
| +0.013 |
story | +0.012 |
big | +0.011 |
Neg logit contributions | |
izing | -0.042 |
yles | -0.040 |
ning | -0.040 |
king | -0.039 |
ellery | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
am | +0.029 |
done | +0.026 |
| +0.024 |
story | +0.024 |
big | +0.022 |
Neg logit contributions | |
izing | -0.066 |
ning | -0.064 |
king | -0.064 |
yles | -0.063 |
rily | -0.063 |
Token | said |
Token ID | 531 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
izing | +0.041 |
yles | +0.039 |
king | +0.039 |
ants | +0.039 |
rily | +0.038 |
Neg logit contributions | |
am | -0.009 |
| -0.009 |
done | -0.008 |
to | -0.007 |
big | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
| +0.002 |
story | +0.002 |
time | +0.001 |
Neg logit contributions | |
izing | -0.009 |
yles | -0.008 |
rily | -0.008 |
ning | -0.008 |
king | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
izing | +0.031 |
ellery | +0.031 |
yles | +0.031 |
ning | +0.030 |
burn | +0.030 |
Neg logit contributions | |
| -0.011 |
to | -0.009 |
am | -0.008 |
big | -0.008 |
was | -0.007 |
Token | L |
Token ID | 43 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
izing | +0.142 |
yles | +0.140 |
rily | +0.139 |
ants | +0.139 |
ellery | +0.137 |
Neg logit contributions | |
| -0.114 |
am | -0.113 |
to | -0.101 |
was | -0.099 |
done | -0.098 |
Token | ily |
Token ID | 813 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
izing | +0.122 |
yles | +0.118 |
ning | +0.117 |
king | +0.116 |
ellery | +0.116 |
Neg logit contributions | |
am | -0.045 |
done | -0.040 |
| -0.040 |
story | -0.036 |
big | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
am | +0.014 |
| +0.012 |
done | +0.012 |
story | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.057 |
ning | -0.056 |
king | -0.054 |
yles | -0.054 |
ellery | -0.054 |
Token | I |
Token ID | 314 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
izing | +0.098 |
yles | +0.097 |
king | +0.095 |
rily | +0.095 |
ning | +0.094 |
Neg logit contributions | |
am | -0.054 |
to | -0.051 |
| -0.050 |
done | -0.050 |
story | -0.048 |
Token | think |
Token ID | 892 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
| +0.009 |
big | +0.009 |
story | +0.009 |
done | +0.009 |
bad | +0.008 |
Neg logit contributions | |
yles | -0.027 |
bul | -0.026 |
burn | -0.026 |
izing | -0.025 |
istent | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
am | +0.007 |
done | +0.007 |
| +0.007 |
to | +0.007 |
big | +0.007 |
Neg logit contributions | |
izing | -0.013 |
king | -0.013 |
rily | -0.012 |
yles | -0.012 |
ning | -0.012 |
Token | magic |
Token ID | 5536 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
am | +0.038 |
done | +0.035 |
| +0.035 |
story | +0.032 |
to | +0.032 |
Neg logit contributions | |
izing | -0.058 |
yles | -0.055 |
ning | -0.055 |
king | -0.055 |
rily | -0.054 |
Token | word |
Token ID | 1573 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
izing | +0.002 |
ning | +0.001 |
rily | +0.001 |
bul | +0.001 |
king | +0.001 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
story | -0.001 |
big | -0.001 |
Token | ." |
Token ID | 526 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
am | +0.014 |
done | +0.013 |
| +0.013 |
story | +0.012 |
big | +0.011 |
Neg logit contributions | |
izing | -0.039 |
yles | -0.037 |
ning | -0.037 |
king | -0.037 |
rily | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
am | +0.011 |
done | +0.010 |
story | +0.008 |
bad | +0.008 |
big | +0.008 |
Neg logit contributions | |
yles | -0.049 |
izing | -0.049 |
rily | -0.048 |
ning | -0.048 |
ants | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
am | +0.002 |
done | +0.002 |
bad | +0.001 |
story | +0.001 |
big | +0.001 |
Neg logit contributions | |
izing | -0.019 |
yles | -0.019 |
ning | -0.018 |
ants | -0.018 |
rily | -0.018 |
Token | " |
Token ID | 1 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
izing | +0.026 |
ning | +0.025 |
yles | +0.025 |
rily | +0.024 |
king | +0.024 |
Neg logit contributions | |
| -0.020 |
am | -0.020 |
story | -0.018 |
done | -0.017 |
big | -0.017 |
Token | Let |
Token ID | 5756 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
rily | +0.156 |
ning | +0.156 |
ellery | +0.154 |
izing | +0.152 |
ants | +0.149 |
Neg logit contributions | |
am | -0.114 |
| -0.113 |
big | -0.093 |
was | -0.089 |
'm | -0.089 |
Token | 's |
Token ID | 338 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.013 |
ning | +0.013 |
king | +0.013 |
ellery | +0.013 |
Neg logit contributions | |
am | -0.006 |
done | -0.005 |
| -0.005 |
story | -0.005 |
big | -0.005 |
Token | try |
Token ID | 1949 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
am | +0.011 |
| +0.010 |
done | +0.010 |
big | +0.009 |
story | +0.009 |
Neg logit contributions | |
izing | -0.029 |
yles | -0.028 |
king | -0.028 |
ning | -0.028 |
rily | -0.028 |
Token | ," |
Token ID | 553 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
am | +0.021 |
| +0.020 |
to | +0.020 |
done | +0.019 |
big | +0.018 |
Neg logit contributions | |
izing | -0.061 |
yles | -0.059 |
king | -0.058 |
rily | -0.058 |
ellery | -0.057 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
izing | +0.029 |
yles | +0.028 |
ning | +0.028 |
rily | +0.027 |
king | +0.027 |
Neg logit contributions | |
am | -0.015 |
done | -0.014 |
| -0.013 |
story | -0.013 |
big | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
am | +0.012 |
done | +0.012 |
own | +0.010 |
| +0.009 |
time | +0.009 |
Neg logit contributions | |
izing | -0.033 |
rily | -0.033 |
ants | -0.032 |
ning | -0.031 |
king | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
izing | +0.056 |
ellery | +0.054 |
yles | +0.054 |
ning | +0.053 |
ants | +0.052 |
Neg logit contributions | |
| -0.020 |
am | -0.018 |
to | -0.016 |
big | -0.016 |
done | -0.015 |
Token | You |
Token ID | 1639 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
izing | +0.137 |
yles | +0.136 |
ning | +0.135 |
ellery | +0.135 |
ants | +0.135 |
Neg logit contributions | |
am | -0.085 |
| -0.084 |
He | -0.068 |
was | -0.067 |
whole | -0.066 |
Token | are |
Token ID | 389 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
am | +0.022 |
| +0.021 |
to | +0.021 |
story | +0.020 |
lesson | +0.018 |
Neg logit contributions | |
yles | -0.044 |
etti | -0.043 |
burn | -0.043 |
izing | -0.043 |
pper | -0.043 |
Token | welcome |
Token ID | 7062 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
am | +0.021 |
done | +0.018 |
| +0.017 |
story | +0.017 |
to | +0.016 |
Neg logit contributions | |
izing | -0.077 |
yles | -0.074 |
ning | -0.074 |
ellery | -0.073 |
king | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
am | +0.016 |
done | +0.014 |
| +0.012 |
story | +0.011 |
big | +0.010 |
Neg logit contributions | |
izing | -0.065 |
ning | -0.063 |
yles | -0.062 |
king | -0.062 |
ellery | -0.062 |
Token | animals |
Token ID | 4695 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
izing | +0.147 |
yles | +0.143 |
ning | +0.141 |
bing | +0.140 |
king | +0.139 |
Neg logit contributions | |
am | -0.073 |
| -0.072 |
big | -0.069 |
done | -0.069 |
story | -0.068 |
Token | ! |
Token ID | 0 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
izing | +0.013 |
king | +0.012 |
ning | +0.012 |
ting | +0.012 |
yles | +0.012 |
Neg logit contributions | |
am | -0.003 |
done | -0.003 |
story | -0.003 |
| -0.003 |
big | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
izing | +0.007 |
yles | +0.007 |
king | +0.007 |
ning | +0.007 |
ellery | +0.007 |
Neg logit contributions | |
am | -0.005 |
| -0.005 |
to | -0.004 |
He | -0.004 |
story | -0.004 |
Token | love |
Token ID | 1842 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
story | +0.006 |
done | +0.006 |
| +0.006 |
big | +0.006 |
to | +0.006 |
Neg logit contributions | |
spe | -0.015 |
burn | -0.015 |
ples | -0.015 |
king | -0.015 |
pper | -0.015 |
Token | you |
Token ID | 345 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
am | +0.016 |
done | +0.014 |
| +0.014 |
story | +0.013 |
big | +0.013 |
Neg logit contributions | |
izing | -0.022 |
yles | -0.021 |
ning | -0.021 |
ellery | -0.020 |
king | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
done | +0.012 |
am | +0.011 |
bad | +0.010 |
story | +0.009 |
whole | +0.008 |
Neg logit contributions | |
ning | -0.038 |
yles | -0.038 |
izing | -0.038 |
bing | -0.036 |
ellery | -0.036 |
Token | got |
Token ID | 1392 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
am | +0.020 |
done | +0.018 |
| +0.018 |
story | +0.017 |
big | +0.016 |
Neg logit contributions | |
izing | -0.049 |
yles | -0.047 |
ning | -0.047 |
king | -0.046 |
ellery | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
izing | +0.059 |
yles | +0.058 |
ning | +0.058 |
king | +0.056 |
ellery | +0.056 |
Neg logit contributions | |
am | -0.027 |
done | -0.025 |
story | -0.024 |
| -0.024 |
time | -0.022 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
am | +0.046 |
| +0.043 |
done | +0.041 |
He | +0.039 |
story | +0.039 |
Neg logit contributions | |
burn | -0.063 |
ning | -0.063 |
izing | -0.063 |
bul | -0.061 |
yles | -0.061 |
Token | coat |
Token ID | 31434 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
izing | +0.047 |
ning | +0.045 |
king | +0.045 |
yles | +0.044 |
burn | +0.044 |
Neg logit contributions | |
am | -0.049 |
| -0.046 |
done | -0.045 |
story | -0.045 |
big | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
izing | +0.106 |
yles | +0.103 |
ellery | +0.101 |
ning | +0.101 |
rily | +0.100 |
Neg logit contributions | |
am | -0.031 |
done | -0.028 |
| -0.027 |
big | -0.025 |
to | -0.024 |
Token | boots |
Token ID | 14412 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
izing | +0.099 |
yles | +0.096 |
ning | +0.095 |
king | +0.094 |
ellery | +0.094 |
Neg logit contributions | |
am | -0.043 |
done | -0.040 |
| -0.039 |
story | -0.036 |
big | -0.036 |
Token | ready |
Token ID | 3492 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
izing | +0.098 |
ning | +0.095 |
king | +0.095 |
yles | +0.093 |
burn | +0.093 |
Neg logit contributions | |
am | -0.036 |
story | -0.032 |
done | -0.030 |
| -0.030 |
big | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
am | +0.020 |
story | +0.015 |
| +0.014 |
done | +0.014 |
ossible | +0.013 |
Neg logit contributions | |
izing | -0.089 |
ning | -0.086 |
king | -0.085 |
rily | -0.085 |
bing | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
am | +0.012 |
done | +0.012 |
story | +0.010 |
bad | +0.009 |
big | +0.007 |
Neg logit contributions | |
yles | -0.051 |
izing | -0.051 |
ning | -0.050 |
bing | -0.049 |
rily | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
done | +0.009 |
am | +0.008 |
consequences | +0.007 |
bad | +0.007 |
grown | +0.006 |
Neg logit contributions | |
yles | -0.032 |
izing | -0.032 |
ning | -0.031 |
ants | -0.031 |
ang | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
| +0.013 |
am | +0.013 |
done | +0.012 |
was | +0.011 |
big | +0.011 |
Neg logit contributions | |
izing | -0.055 |
yles | -0.053 |
rily | -0.052 |
ellery | -0.052 |
king | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
izing | +0.020 |
yles | +0.019 |
ning | +0.019 |
king | +0.019 |
ellery | +0.019 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
| -0.003 |
story | -0.003 |
big | -0.002 |
Token | � |
Token ID | 6184 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
izing | +0.056 |
yles | +0.055 |
ellery | +0.055 |
ning | +0.054 |
rily | +0.053 |
Neg logit contributions | |
| -0.022 |
am | -0.021 |
to | -0.019 |
done | -0.019 |
big | -0.018 |
Token | � |
Token ID | 95 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
yles | +0.101 |
ning | +0.097 |
burn | +0.095 |
rily | +0.094 |
ellery | +0.092 |
Neg logit contributions | |
am | -0.112 |
| -0.103 |
done | -0.097 |
bad | -0.095 |
own | -0.094 |
Token | € |
Token ID | 26391 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
yles | +0.129 |
izing | +0.127 |
rily | +0.122 |
ning | +0.122 |
ants | +0.120 |
Neg logit contributions | |
am | -0.118 |
| -0.112 |
done | -0.109 |
story | -0.101 |
time | -0.099 |
Token | � |
Token ID | 129 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
izing | +0.038 |
yles | +0.036 |
ning | +0.036 |
king | +0.035 |
ellery | +0.035 |
Neg logit contributions | |
am | -0.037 |
done | -0.035 |
| -0.034 |
story | -0.034 |
big | -0.033 |
Token | � |
Token ID | 241 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
yles | +0.140 |
izing | +0.138 |
bul | +0.133 |
ning | +0.132 |
ellery | +0.130 |
Neg logit contributions | |
am | -0.140 |
| -0.139 |
done | -0.138 |
big | -0.130 |
to | -0.129 |
Token | We |
Token ID | 1135 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
izing | +0.028 |
yles | +0.027 |
ning | +0.026 |
king | +0.026 |
ellery | +0.026 |
Neg logit contributions | |
am | -0.024 |
done | -0.023 |
story | -0.022 |
| -0.022 |
big | -0.021 |
Token | need |
Token ID | 761 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
yles | +0.003 |
izing | +0.003 |
bul | +0.003 |
ning | +0.003 |
burn | +0.003 |
Neg logit contributions | |
am | -0.001 |
| -0.001 |
story | -0.001 |
done | -0.001 |
to | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
am | +0.006 |
story | +0.005 |
done | +0.005 |
| +0.005 |
big | +0.003 |
Neg logit contributions | |
izing | -0.036 |
ning | -0.035 |
bul | -0.035 |
yles | -0.034 |
burn | -0.034 |
Token | find |
Token ID | 1064 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
izing | +0.048 |
yles | +0.046 |
ning | +0.046 |
king | +0.045 |
ellery | +0.045 |
Neg logit contributions | |
am | -0.021 |
done | -0.019 |
| -0.018 |
story | -0.017 |
big | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
am | +0.012 |
done | +0.010 |
| +0.009 |
story | +0.009 |
bad | +0.009 |
Neg logit contributions | |
izing | -0.028 |
ning | -0.027 |
rily | -0.026 |
king | -0.026 |
yles | -0.026 |
Token | started |
Token ID | 2067 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
izing | +0.025 |
yles | +0.025 |
ning | +0.024 |
rily | +0.024 |
ellery | +0.024 |
Neg logit contributions | |
am | -0.011 |
done | -0.010 |
| -0.010 |
story | -0.010 |
big | -0.009 |
Token | eating |
Token ID | 6600 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
am | +0.017 |
done | +0.013 |
| +0.013 |
story | +0.012 |
bad | +0.010 |
Neg logit contributions | |
izing | -0.078 |
yles | -0.077 |
ning | -0.077 |
ellery | -0.076 |
king | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
izing | +0.005 |
yles | +0.004 |
rily | +0.004 |
ning | +0.004 |
ellery | +0.004 |
Neg logit contributions | |
am | -0.002 |
done | -0.002 |
| -0.002 |
story | -0.002 |
big | -0.001 |
Token | ch |
Token ID | 442 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
am | +0.021 |
| +0.020 |
done | +0.019 |
ossible | +0.017 |
story | +0.017 |
Neg logit contributions | |
izing | -0.033 |
ning | -0.031 |
rily | -0.031 |
yles | -0.030 |
ellery | -0.030 |
Token | ocol |
Token ID | 4668 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
izing | +0.035 |
yles | +0.032 |
ning | +0.030 |
king | +0.028 |
ellery | +0.028 |
Neg logit contributions | |
am | -0.158 |
done | -0.152 |
| -0.151 |
story | -0.148 |
big | -0.147 |
Token | ates |
Token ID | 689 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
izing | +0.193 |
yles | +0.180 |
ning | +0.174 |
rily | +0.174 |
king | +0.174 |
Neg logit contributions | |
am | -0.210 |
done | -0.202 |
| -0.197 |
story | -0.189 |
to | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
izing | +0.019 |
yles | +0.018 |
ning | +0.018 |
king | +0.018 |
ellery | +0.018 |
Neg logit contributions | |
am | -0.004 |
done | -0.003 |
| -0.003 |
story | -0.003 |
big | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
am | +0.007 |
done | +0.006 |
story | +0.005 |
| +0.005 |
bad | +0.005 |
Neg logit contributions | |
izing | -0.019 |
yles | -0.019 |
rily | -0.019 |
ning | -0.018 |
ellery | -0.018 |
Token | shop |
Token ID | 6128 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
am | +0.011 |
| +0.010 |
done | +0.010 |
to | +0.010 |
story | +0.009 |
Neg logit contributions | |
izing | -0.010 |
ning | -0.010 |
rily | -0.009 |
king | -0.009 |
ender | -0.009 |
Token | keeper |
Token ID | 13884 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
izing | +0.033 |
ning | +0.032 |
yles | +0.032 |
king | +0.031 |
rily | +0.031 |
Neg logit contributions | |
am | -0.022 |
done | -0.020 |
| -0.020 |
story | -0.019 |
big | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
izing | +0.073 |
yles | +0.072 |
ellery | +0.071 |
ning | +0.069 |
ants | +0.069 |
Neg logit contributions | |
am | -0.026 |
done | -0.024 |
| -0.024 |
to | -0.023 |
big | -0.023 |
Token | tw |
Token ID | 665 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
izing | +0.103 |
king | +0.097 |
rily | +0.097 |
yles | +0.096 |
ants | +0.096 |
Neg logit contributions | |
am | -0.031 |
| -0.030 |
big | -0.030 |
done | -0.029 |
to | -0.029 |
Token | inkle |
Token ID | 19894 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
izing | +0.089 |
ning | +0.083 |
king | +0.082 |
yles | +0.081 |
ting | +0.079 |
Neg logit contributions | |
am | -0.125 |
done | -0.120 |
| -0.118 |
big | -0.112 |
to | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
yles | +0.043 |
izing | +0.042 |
ellery | +0.042 |
shadow | +0.041 |
ning | +0.040 |
Neg logit contributions | |
| -0.009 |
big | -0.009 |
am | -0.008 |
to | -0.008 |
done | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
am | +0.004 |
| +0.004 |
done | +0.003 |
story | +0.003 |
big | +0.002 |
Neg logit contributions | |
izing | -0.028 |
yles | -0.027 |
ning | -0.027 |
king | -0.027 |
ellery | -0.027 |
Token | par |
Token ID | 1582 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
izing | +0.023 |
king | +0.022 |
yles | +0.021 |
ning | +0.021 |
ellery | +0.021 |
Neg logit contributions | |
am | -0.029 |
done | -0.027 |
| -0.026 |
to | -0.025 |
story | -0.025 |
Token | rot |
Token ID | 10599 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
izing | +0.142 |
yles | +0.133 |
rily | +0.132 |
ning | +0.131 |
burn | +0.124 |
Neg logit contributions | |
am | -0.254 |
| -0.248 |
story | -0.242 |
done | -0.240 |
big | -0.233 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
izing | +0.040 |
yles | +0.039 |
ning | +0.039 |
ellery | +0.038 |
king | +0.038 |
Neg logit contributions | |
am | -0.012 |
done | -0.010 |
| -0.010 |
story | -0.009 |
big | -0.009 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
izing | +0.035 |
rily | +0.033 |
bly | +0.032 |
ivating | +0.032 |
yles | +0.032 |
Neg logit contributions | |
am | -0.021 |
story | -0.020 |
done | -0.019 |
ossible | -0.019 |
| -0.017 |
Token | while |
Token ID | 981 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
am | +0.019 |
done | +0.016 |
| +0.016 |
story | +0.016 |
big | +0.014 |
Neg logit contributions | |
izing | -0.041 |
ning | -0.039 |
yles | -0.039 |
king | -0.039 |
rily | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
| +0.017 |
am | +0.016 |
big | +0.016 |
to | +0.016 |
done | +0.015 |
Neg logit contributions | |
izing | -0.039 |
ellery | -0.037 |
rily | -0.037 |
yles | -0.037 |
ksh | -0.037 |
Token | But |
Token ID | 1537 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
izing | +0.012 |
yles | +0.012 |
ning | +0.012 |
king | +0.011 |
ellery | +0.011 |
Neg logit contributions | |
am | -0.011 |
done | -0.011 |
| -0.011 |
story | -0.010 |
big | -0.010 |
Token | then |
Token ID | 788 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
am | +0.010 |
| +0.009 |
done | +0.009 |
to | +0.009 |
story | +0.008 |
Neg logit contributions | |
izing | -0.014 |
yles | -0.013 |
ning | -0.013 |
king | -0.013 |
ellery | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
am | +0.017 |
done | +0.016 |
story | +0.015 |
| +0.015 |
big | +0.014 |
Neg logit contributions | |
izing | -0.029 |
yles | -0.028 |
ning | -0.028 |
rily | -0.028 |
ellery | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
am | +0.036 |
| +0.031 |
done | +0.030 |
story | +0.026 |
| +0.024 |
Neg logit contributions | |
izing | -0.096 |
ning | -0.094 |
bul | -0.092 |
king | -0.091 |
rily | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
izing | +0.031 |
yles | +0.030 |
king | +0.029 |
ning | +0.029 |
ellery | +0.029 |
Neg logit contributions | |
am | -0.012 |
| -0.012 |
done | -0.011 |
story | -0.010 |
big | -0.010 |
Token | se |
Token ID | 384 |
Feature activation | -8.39e+00 |
Pos logit contributions | |
am | +0.052 |
| +0.048 |
done | +0.046 |
to | +0.040 |
| +0.039 |
Neg logit contributions | |
izing | -0.082 |
ning | -0.079 |
yles | -0.078 |
king | -0.077 |
bul | -0.076 |
Token | ag |
Token ID | 363 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
izing | +0.223 |
ning | +0.212 |
yles | +0.212 |
king | +0.210 |
rily | +0.208 |
Neg logit contributions | |
am | -0.146 |
| -0.137 |
done | -0.130 |
big | -0.130 |
story | -0.126 |
Token | ull |
Token ID | 724 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
izing | +0.014 |
ning | +0.014 |
rily | +0.013 |
king | +0.013 |
ants | +0.013 |
Neg logit contributions | |
am | -0.021 |
done | -0.020 |
bad | -0.019 |
| -0.019 |
story | -0.019 |
Token | s |
Token ID | 82 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
izing | +0.079 |
yles | +0.076 |
ning | +0.075 |
king | +0.075 |
ellery | +0.075 |
Neg logit contributions | |
am | -0.042 |
done | -0.039 |
| -0.039 |
story | -0.036 |
big | -0.036 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
am | +0.039 |
| +0.034 |
done | +0.033 |
story | +0.033 |
big | +0.030 |
Neg logit contributions | |
izing | -0.064 |
king | -0.063 |
ning | -0.063 |
rily | -0.061 |
yles | -0.060 |
Token | became |
Token ID | 2627 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
am | +0.024 |
story | +0.021 |
| +0.020 |
done | +0.019 |
own | +0.019 |
Neg logit contributions | |
izing | -0.040 |
king | -0.040 |
ning | -0.039 |
rily | -0.038 |
yles | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
izing | +0.020 |
yles | +0.019 |
ning | +0.019 |
king | +0.019 |
ellery | +0.019 |
Neg logit contributions | |
am | -0.003 |
| -0.003 |
done | -0.003 |
story | -0.002 |
big | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
izing | +0.075 |
ellery | +0.073 |
yles | +0.073 |
ning | +0.070 |
burn | +0.069 |
Neg logit contributions | |
| -0.025 |
to | -0.021 |
am | -0.020 |
big | -0.018 |
done | -0.017 |
Token | That |
Token ID | 2504 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
rily | +0.177 |
izing | +0.170 |
ellery | +0.170 |
yles | +0.165 |
arians | +0.163 |
Neg logit contributions | |
| -0.111 |
am | -0.100 |
was | -0.089 |
| -0.086 |
to | -0.086 |
Token | is |
Token ID | 318 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
izing | +0.011 |
yles | +0.010 |
king | +0.010 |
ellery | +0.010 |
ning | +0.010 |
Neg logit contributions | |
am | -0.007 |
| -0.007 |
done | -0.007 |
story | -0.006 |
big | -0.006 |
Token | an |
Token ID | 281 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
yles | +0.002 |
izing | +0.002 |
rily | +0.002 |
king | +0.002 |
ellery | +0.002 |
Neg logit contributions | |
am | -0.001 |
done | -0.001 |
| -0.001 |
big | -0.001 |
to | -0.001 |
Token | aer |
Token ID | 9551 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
yles | +0.050 |
king | +0.049 |
izing | +0.047 |
ning | +0.045 |
ellery | +0.045 |
Neg logit contributions | |
big | -0.047 |
done | -0.046 |
bad | -0.045 |
am | -0.045 |
story | -0.044 |
Token | opl |
Token ID | 20106 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
izing | +0.157 |
yles | +0.155 |
rily | +0.152 |
ning | +0.149 |
king | +0.148 |
Neg logit contributions | |
am | -0.200 |
done | -0.195 |
| -0.193 |
story | -0.189 |
big | -0.182 |
Token | ane |
Token ID | 1531 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
izing | +0.153 |
rily | +0.151 |
ellery | +0.142 |
king | +0.141 |
yles | +0.139 |
Neg logit contributions | |
am | -0.162 |
| -0.152 |
to | -0.144 |
story | -0.141 |
done | -0.137 |
Token | ! |
Token ID | 0 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
yles | +0.104 |
izing | +0.103 |
rily | +0.100 |
ellery | +0.100 |
king | +0.099 |
Neg logit contributions | |
am | -0.025 |
done | -0.021 |
| -0.021 |
to | -0.021 |
story | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
izing | +0.009 |
ellery | +0.009 |
cking | +0.009 |
yles | +0.009 |
rily | +0.008 |
Neg logit contributions | |
| -0.004 |
He | -0.004 |
am | -0.004 |
to | -0.003 |
is | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
izing | +0.046 |
yles | +0.045 |
king | +0.044 |
ellery | +0.044 |
rily | +0.044 |
Neg logit contributions | |
am | -0.012 |
| -0.010 |
done | -0.010 |
story | -0.008 |
big | -0.008 |
Token | an |
Token ID | 281 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
izing | +0.075 |
ning | +0.073 |
yles | +0.073 |
rily | +0.071 |
king | +0.071 |
Neg logit contributions | |
am | -0.027 |
done | -0.025 |
story | -0.023 |
| -0.023 |
big | -0.020 |
Token | orange |
Token ID | 10912 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
yles | +0.048 |
izing | +0.046 |
king | +0.046 |
etti | +0.044 |
ants | +0.044 |
Neg logit contributions | |
big | -0.024 |
am | -0.023 |
done | -0.022 |
bad | -0.022 |
own | -0.022 |
Token | rope |
Token ID | 17182 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
izing | +0.013 |
yles | +0.012 |
ning | +0.012 |
king | +0.012 |
ellery | +0.012 |
Neg logit contributions | |
am | -0.010 |
| -0.009 |
done | -0.009 |
story | -0.009 |
big | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
izing | +0.065 |
ning | +0.064 |
king | +0.063 |
rily | +0.063 |
yles | +0.062 |
Neg logit contributions | |
am | -0.021 |
done | -0.019 |
story | -0.018 |
| -0.017 |
bad | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
izing | +0.022 |
yles | +0.022 |
king | +0.021 |
ellery | +0.021 |
ning | +0.021 |
Neg logit contributions | |
am | -0.010 |
| -0.010 |
big | -0.009 |
done | -0.009 |
to | -0.009 |
Token | kay |
Token ID | 34681 |
Feature activation | -8.72e+00 |
Pos logit contributions | |
am | +0.016 |
big | +0.016 |
| +0.015 |
done | +0.014 |
to | +0.014 |
Neg logit contributions | |
izing | -0.030 |
yles | -0.030 |
ellery | -0.029 |
rily | -0.029 |
king | -0.029 |
Token | ak |
Token ID | 461 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
izing | +0.217 |
yles | +0.206 |
ning | +0.205 |
king | +0.203 |
ellery | +0.200 |
Neg logit contributions | |
am | -0.166 |
done | -0.155 |
| -0.153 |
story | -0.148 |
big | -0.145 |
Token | for |
Token ID | 329 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
am | +0.006 |
done | +0.005 |
story | +0.005 |
| +0.005 |
bad | +0.004 |
Neg logit contributions | |
izing | -0.031 |
ning | -0.030 |
king | -0.030 |
rily | -0.030 |
yles | -0.030 |
Token | him |
Token ID | 683 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
am | +0.016 |
done | +0.015 |
| +0.015 |
big | +0.013 |
to | +0.013 |
Neg logit contributions | |
izing | -0.047 |
yles | -0.046 |
ning | -0.045 |
king | -0.045 |
rily | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
am | +0.020 |
done | +0.017 |
story | +0.016 |
| +0.015 |
bad | +0.013 |
Neg logit contributions | |
izing | -0.099 |
ning | -0.098 |
yles | -0.096 |
king | -0.095 |
ellery | -0.095 |
Token | His |
Token ID | 2399 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
am | +0.004 |
| +0.003 |
done | +0.003 |
story | +0.003 |
big | +0.002 |
Neg logit contributions | |
izing | -0.018 |
yles | -0.017 |
ning | -0.017 |
king | -0.017 |
ellery | -0.017 |