Token | . |
Token ID | 13 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
ursion | +0.041 |
bet | +0.039 |
anna | +0.039 |
Sure | +0.037 |
sur | +0.037 |
Neg logit contributions | |
es | -0.024 |
rats | -0.022 |
ts | -0.021 |
stains | -0.020 |
marks | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
ursion | +0.012 |
anna | +0.011 |
ounded | +0.011 |
bet | +0.011 |
sur | +0.011 |
Neg logit contributions | |
es | -0.008 |
not | -0.008 |
isk | -0.007 |
mice | -0.007 |
rats | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
ursion | +0.009 |
bet | +0.009 |
anna | +0.009 |
pleasure | +0.008 |
sur | +0.008 |
Neg logit contributions | |
es | -0.006 |
not | -0.005 |
rats | -0.005 |
ts | -0.005 |
marks | -0.005 |
Token | On |
Token ID | 2202 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ursion | +0.010 |
anna | +0.010 |
bet | +0.010 |
pleasure | +0.010 |
Sure | +0.009 |
Neg logit contributions | |
es | -0.008 |
rats | -0.007 |
ts | -0.007 |
not | -0.007 |
marks | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
ursion | +0.064 |
bet | +0.062 |
anna | +0.062 |
Sure | +0.060 |
Of | +0.060 |
Neg logit contributions | |
es | -0.028 |
rats | -0.025 |
stains | -0.024 |
ts | -0.024 |
marks | -0.023 |
Token | way |
Token ID | 835 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ursion | +0.062 |
anna | +0.057 |
Sure | +0.056 |
bet | +0.056 |
Of | +0.055 |
Neg logit contributions | |
marks | -0.047 |
rats | -0.047 |
not | -0.046 |
mice | -0.046 |
puzzles | -0.045 |
Token | back |
Token ID | 736 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ursion | +0.268 |
anna | +0.259 |
bet | +0.259 |
Of | +0.251 |
pleasure | +0.241 |
Neg logit contributions | |
es | -0.246 |
rats | -0.218 |
not | -0.216 |
marks | -0.211 |
ts | -0.208 |
Token | he |
Token ID | 339 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
anna | +0.036 |
ursion | +0.035 |
Of | +0.035 |
bet | +0.033 |
ya | +0.032 |
Neg logit contributions | |
es | -0.027 |
ings | -0.024 |
marks | -0.024 |
rats | -0.024 |
not | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
ursion | +0.024 |
anna | +0.022 |
bet | +0.022 |
Of | +0.021 |
pleasure | +0.021 |
Neg logit contributions | |
es | -0.020 |
rats | -0.018 |
ts | -0.018 |
marks | -0.018 |
not | -0.018 |
Token | an |
Token ID | 281 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
es | +0.003 |
stains | +0.003 |
rats | +0.003 |
ts | +0.002 |
bes | +0.002 |
Neg logit contributions | |
bet | -0.006 |
ursion | -0.006 |
Of | -0.006 |
anna | -0.006 |
pleasure | -0.006 |
Token | old |
Token ID | 1468 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
ursion | +0.056 |
Sure | +0.053 |
anna | +0.053 |
Of | +0.053 |
bet | +0.052 |
Neg logit contributions | |
rats | -0.032 |
es | -0.031 |
marks | -0.030 |
mice | -0.030 |
ts | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
ursion | +0.050 |
bet | +0.049 |
anna | +0.047 |
Of | +0.047 |
sur | +0.047 |
Neg logit contributions | |
es | -0.022 |
marks | -0.018 |
not | -0.017 |
stains | -0.017 |
rats | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
adventurer | +0.036 |
sur | +0.034 |
ursion | +0.034 |
ya | +0.034 |
anna | +0.034 |
Neg logit contributions | |
es | -0.014 |
ings | -0.013 |
not | -0.012 |
't | -0.012 |
all | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +8.18e-03 |
Pos logit contributions | |
ursion | +0.016 |
bet | +0.015 |
adventurer | +0.015 |
pleasure | +0.015 |
sur | +0.015 |
Neg logit contributions | |
es | -0.008 |
not | -0.007 |
ings | -0.006 |
marks | -0.006 |
bes | -0.006 |
Token | On |
Token ID | 2202 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ursion | +0.014 |
bet | +0.014 |
pleasure | +0.014 |
anna | +0.014 |
Sure | +0.013 |
Neg logit contributions | |
es | -0.010 |
not | -0.009 |
marks | -0.009 |
stains | -0.009 |
bes | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
ursion | +0.065 |
bet | +0.063 |
anna | +0.063 |
Of | +0.061 |
Sure | +0.061 |
Neg logit contributions | |
es | -0.026 |
rats | -0.023 |
ts | -0.022 |
stains | -0.022 |
marks | -0.021 |
Token | way |
Token ID | 835 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ursion | +0.065 |
bet | +0.061 |
sur | +0.058 |
uster | +0.056 |
Sure | +0.056 |
Neg logit contributions | |
pictures | -0.051 |
marks | -0.050 |
cookies | -0.048 |
puzzles | -0.048 |
all | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
ursion | +0.279 |
bet | +0.272 |
anna | +0.271 |
Of | +0.260 |
pleasure | +0.254 |
Neg logit contributions | |
es | -0.233 |
not | -0.206 |
marks | -0.198 |
rats | -0.197 |
stains | -0.196 |
Token | Jenny |
Token ID | 28437 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ursion | +0.005 |
anna | +0.005 |
bet | +0.005 |
Sure | +0.004 |
Of | +0.004 |
Neg logit contributions | |
es | -0.008 |
marks | -0.008 |
stains | -0.008 |
rats | -0.008 |
not | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
ursion | +0.046 |
pleasure | +0.044 |
Of | +0.043 |
bet | +0.043 |
Sure | +0.042 |
Neg logit contributions | |
es | -0.041 |
marks | -0.035 |
not | -0.034 |
stains | -0.034 |
ts | -0.034 |
Token | so |
Token ID | 523 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
ursion | +0.016 |
bet | +0.015 |
anna | +0.015 |
Of | +0.015 |
Sure | +0.015 |
Neg logit contributions | |
es | -0.013 |
rats | -0.011 |
not | -0.011 |
ts | -0.011 |
marks | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
ursion | +0.055 |
anna | +0.053 |
bet | +0.050 |
Sure | +0.049 |
Of | +0.049 |
Neg logit contributions | |
es | -0.055 |
not | -0.053 |
rats | -0.050 |
marks | -0.050 |
ts | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
es | +0.005 |
rats | +0.004 |
ts | +0.004 |
stains | +0.004 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.012 |
bet | -0.012 |
anna | -0.012 |
Sure | -0.011 |
Of | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
ursion | +0.016 |
sur | +0.016 |
adventurer | +0.015 |
uster | +0.014 |
anna | +0.014 |
Neg logit contributions | |
es | -0.007 |
not | -0.007 |
mice | -0.006 |
stains | -0.006 |
rats | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
ursion | +0.005 |
bet | +0.004 |
anna | +0.004 |
Of | +0.004 |
sur | +0.004 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
ts | -0.004 |
stains | -0.004 |
marks | -0.004 |
Token | On |
Token ID | 2202 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.004 |
anna | +0.004 |
Of | +0.004 |
Sure | +0.004 |
Neg logit contributions | |
es | -0.005 |
rats | -0.005 |
ts | -0.005 |
stains | -0.005 |
marks | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ursion | +0.060 |
bet | +0.058 |
anna | +0.057 |
Sure | +0.055 |
pleasure | +0.055 |
Neg logit contributions | |
es | -0.030 |
rats | -0.026 |
ts | -0.025 |
stains | -0.025 |
marks | -0.024 |
Token | way |
Token ID | 835 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ursion | +0.043 |
bet | +0.039 |
anna | +0.039 |
sur | +0.038 |
Of | +0.036 |
Neg logit contributions | |
rats | -0.054 |
es | -0.053 |
puzzles | -0.052 |
cookies | -0.051 |
not | -0.051 |
Token | home |
Token ID | 1363 |
Feature activation | -6.50e-05 |
Pos logit contributions | |
ursion | +0.257 |
bet | +0.247 |
anna | +0.246 |
Of | +0.235 |
sur | +0.230 |
Neg logit contributions | |
es | -0.254 |
rats | -0.231 |
not | -0.226 |
stains | -0.225 |
marks | -0.222 |
Token | something |
Token ID | 1223 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
es | +0.000 |
rats | +0.000 |
ts | +0.000 |
stains | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Sure | -0.000 |
Of | -0.000 |
Token | amazing |
Token ID | 4998 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
es | +0.034 |
not | +0.032 |
stains | +0.032 |
rats | +0.032 |
marks | +0.031 |
Neg logit contributions | |
ursion | -0.050 |
anna | -0.047 |
bet | -0.046 |
Sure | -0.044 |
Of | -0.043 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ursion | +0.007 |
bet | +0.007 |
anna | +0.007 |
Of | +0.006 |
Sure | +0.006 |
Neg logit contributions | |
es | -0.004 |
rats | -0.003 |
ts | -0.003 |
stains | -0.003 |
marks | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
ursion | +0.025 |
bet | +0.024 |
anna | +0.024 |
Sure | +0.023 |
Of | +0.023 |
Neg logit contributions | |
es | -0.014 |
rats | -0.013 |
ts | -0.013 |
stains | -0.013 |
marks | -0.013 |
Token | |
Token ID | 220 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
ursion | +0.016 |
bet | +0.014 |
anna | +0.014 |
ounded | +0.014 |
sur | +0.013 |
Neg logit contributions | |
es | -0.011 |
not | -0.010 |
mice | -0.010 |
rats | -0.009 |
bones | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
ursion | +0.054 |
bet | +0.051 |
anna | +0.051 |
Sure | +0.048 |
Of | +0.048 |
Neg logit contributions | |
es | -0.056 |
rats | -0.052 |
ts | -0.050 |
stains | -0.050 |
marks | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +4.77e-03 |
Pos logit contributions | |
ursion | +0.006 |
bet | +0.006 |
anna | +0.006 |
pleasure | +0.006 |
sur | +0.006 |
Neg logit contributions | |
es | -0.005 |
not | -0.004 |
ts | -0.004 |
rats | -0.004 |
marks | -0.004 |
Token | On |
Token ID | 2202 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
ursion | +0.007 |
bet | +0.006 |
anna | +0.006 |
Sure | +0.006 |
Of | +0.006 |
Neg logit contributions | |
es | -0.008 |
rats | -0.007 |
ts | -0.007 |
stains | -0.007 |
marks | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
ursion | +0.066 |
bet | +0.064 |
anna | +0.064 |
Of | +0.061 |
Sure | +0.061 |
Neg logit contributions | |
es | -0.026 |
rats | -0.023 |
ts | -0.022 |
stains | -0.021 |
marks | -0.021 |
Token | way |
Token ID | 835 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ursion | +0.063 |
anna | +0.060 |
uster | +0.058 |
Of | +0.058 |
Sure | +0.058 |
Neg logit contributions | |
not | -0.051 |
pictures | -0.050 |
marks | -0.049 |
puzzles | -0.046 |
things | -0.045 |
Token | home |
Token ID | 1363 |
Feature activation | +7.34e-04 |
Pos logit contributions | |
ursion | +0.280 |
anna | +0.273 |
bet | +0.272 |
Of | +0.266 |
pleasure | +0.251 |
Neg logit contributions | |
es | -0.231 |
not | -0.205 |
rats | -0.202 |
marks | -0.197 |
stains | -0.192 |
Token | from |
Token ID | 422 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
ursion | +0.001 |
bet | +0.001 |
anna | +0.001 |
Of | +0.001 |
Sure | +0.001 |
Neg logit contributions | |
es | -0.001 |
rats | -0.001 |
ts | -0.001 |
stains | -0.001 |
marks | -0.001 |
Token | school |
Token ID | 1524 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
stains | +0.006 |
ts | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.012 |
bet | -0.012 |
anna | -0.012 |
Sure | -0.011 |
sur | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
ursion | +0.027 |
bet | +0.026 |
anna | +0.025 |
Of | +0.025 |
pleasure | +0.024 |
Neg logit contributions | |
es | -0.017 |
rats | -0.014 |
ts | -0.014 |
marks | -0.014 |
not | -0.014 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
es | +0.015 |
rats | +0.014 |
ts | +0.014 |
stains | +0.014 |
marks | +0.013 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.007 |
anna | -0.007 |
Sure | -0.007 |
Of | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
es | +0.025 |
rats | +0.022 |
ts | +0.021 |
stains | +0.021 |
marks | +0.021 |
Neg logit contributions | |
ursion | -0.048 |
bet | -0.047 |
anna | -0.046 |
Of | -0.045 |
Sure | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
ursion | +0.016 |
anna | +0.016 |
adventurer | +0.015 |
sur | +0.015 |
ya | +0.015 |
Neg logit contributions | |
es | -0.008 |
not | -0.008 |
mice | -0.007 |
ings | -0.007 |
isk | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.004 |
anna | +0.003 |
Of | +0.003 |
Sure | +0.003 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
ts | -0.002 |
stains | -0.002 |
marks | -0.002 |
Token | On |
Token ID | 2202 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
ursion | +0.005 |
bet | +0.004 |
anna | +0.004 |
Of | +0.004 |
Sure | +0.004 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
stains | -0.004 |
ts | -0.004 |
marks | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ursion | +0.065 |
bet | +0.063 |
anna | +0.063 |
Sure | +0.060 |
Of | +0.060 |
Neg logit contributions | |
es | -0.027 |
rats | -0.023 |
ts | -0.022 |
stains | -0.022 |
marks | -0.022 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
bet | +0.049 |
ursion | +0.048 |
uster | +0.045 |
anna | +0.045 |
sur | +0.045 |
Neg logit contributions | |
cookies | -0.047 |
sandwiches | -0.046 |
not | -0.045 |
puzzles | -0.045 |
pictures | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
ursion | +0.276 |
bet | +0.269 |
anna | +0.266 |
Of | +0.260 |
sur | +0.250 |
Neg logit contributions | |
es | -0.229 |
not | -0.208 |
rats | -0.200 |
marks | -0.193 |
stains | -0.191 |
Token | A |
Token ID | 317 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
ursion | +0.007 |
anna | +0.007 |
bet | +0.007 |
Of | +0.006 |
Sure | +0.006 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
ts | -0.004 |
stains | -0.004 |
marks | -0.004 |
Token | str |
Token ID | 2536 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ursion | +0.090 |
anna | +0.087 |
bet | +0.083 |
Sure | +0.079 |
ounded | +0.077 |
Neg logit contributions | |
rats | -0.043 |
mice | -0.041 |
cookies | -0.041 |
not | -0.040 |
marks | -0.039 |
Token | id |
Token ID | 312 |
Feature activation | -4.53e-04 |
Pos logit contributions | |
ursion | +0.036 |
anna | +0.035 |
bet | +0.033 |
Sure | +0.032 |
sur | +0.032 |
Neg logit contributions | |
es | -0.029 |
stains | -0.028 |
rats | -0.028 |
ts | -0.028 |
sandwiches | -0.027 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
bet | -0.001 |
anna | -0.001 |
Of | -0.001 |
Sure | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-03 |
Pos logit contributions | |
es | +0.026 |
rats | +0.024 |
stains | +0.023 |
ts | +0.023 |
marks | +0.022 |
Neg logit contributions | |
ursion | -0.040 |
bet | -0.039 |
anna | -0.038 |
Sure | -0.037 |
sur | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -9.21e-04 |
Pos logit contributions | |
ursion | +0.004 |
anna | +0.004 |
sur | +0.004 |
bet | +0.004 |
ya | +0.004 |
Neg logit contributions | |
es | -0.004 |
not | -0.003 |
rats | -0.003 |
isk | -0.003 |
marks | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-04 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.002 |
bet | -0.001 |
anna | -0.001 |
pleasure | -0.001 |
Of | -0.001 |
Token | On |
Token ID | 2202 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
es | +0.000 |
rats | +0.000 |
ts | +0.000 |
stains | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Of | -0.000 |
Sure | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ursion | +0.062 |
bet | +0.060 |
anna | +0.059 |
Sure | +0.058 |
Of | +0.057 |
Neg logit contributions | |
es | -0.029 |
rats | -0.025 |
stains | -0.024 |
ts | -0.024 |
marks | -0.024 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.064 |
anna | +0.063 |
bet | +0.061 |
sur | +0.060 |
pleasure | +0.059 |
Neg logit contributions | |
rats | -0.051 |
mice | -0.049 |
not | -0.049 |
marks | -0.048 |
monsters | -0.048 |
Token | home |
Token ID | 1363 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
ursion | +0.283 |
anna | +0.278 |
bet | +0.276 |
Of | +0.266 |
sur | +0.261 |
Neg logit contributions | |
es | -0.221 |
rats | -0.200 |
not | -0.198 |
marks | -0.187 |
stains | -0.186 |
Token | , |
Token ID | 11 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
es | +0.002 |
rats | +0.002 |
ts | +0.002 |
stains | +0.002 |
marks | +0.002 |
Neg logit contributions | |
ursion | -0.003 |
bet | -0.002 |
anna | -0.002 |
Sure | -0.002 |
Of | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
es | +0.010 |
stains | +0.010 |
ts | +0.009 |
rats | +0.009 |
bes | +0.009 |
Neg logit contributions | |
ursion | -0.013 |
bet | -0.013 |
Sure | -0.012 |
Of | -0.012 |
pleasure | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | -8.64e-03 |
Pos logit contributions | |
ursion | +0.030 |
bet | +0.029 |
anna | +0.029 |
Of | +0.027 |
Sure | +0.027 |
Neg logit contributions | |
es | -0.028 |
rats | -0.026 |
ts | -0.025 |
stains | -0.025 |
marks | -0.025 |
Token | something |
Token ID | 1223 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
es | +0.008 |
ts | +0.008 |
rats | +0.007 |
stains | +0.007 |
bes | +0.007 |
Neg logit contributions | |
ursion | -0.017 |
bet | -0.017 |
anna | -0.017 |
Of | -0.017 |
Sure | -0.016 |
Token | continued |
Token ID | 3767 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
ursion | +0.016 |
bet | +0.015 |
anna | +0.015 |
Of | +0.014 |
Sure | +0.014 |
Neg logit contributions | |
es | -0.015 |
rats | -0.014 |
ts | -0.014 |
stains | -0.014 |
marks | -0.014 |
Token | walking |
Token ID | 6155 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
ursion | +0.105 |
bet | +0.101 |
anna | +0.099 |
Of | +0.096 |
Sure | +0.095 |
Neg logit contributions | |
es | -0.070 |
rats | -0.062 |
ts | -0.060 |
stains | -0.060 |
marks | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
ursion | +0.125 |
Shall | +0.119 |
anna | +0.119 |
pleasure | +0.114 |
Of | +0.114 |
Neg logit contributions | |
es | -0.056 |
all | -0.049 |
not | -0.042 |
ts | -0.041 |
mice | -0.040 |
Token | Along |
Token ID | 17159 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
ursion | +0.008 |
sur | +0.007 |
bet | +0.007 |
anna | +0.007 |
ounded | +0.007 |
Neg logit contributions | |
es | -0.009 |
rats | -0.008 |
stains | -0.008 |
not | -0.008 |
mice | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ursion | +0.221 |
anna | +0.214 |
bet | +0.214 |
Of | +0.208 |
Sure | +0.205 |
Neg logit contributions | |
es | -0.055 |
rats | -0.045 |
ts | -0.041 |
stains | -0.041 |
not | -0.040 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.051 |
Sure | +0.048 |
Of | +0.048 |
anna | +0.048 |
bet | +0.046 |
Neg logit contributions | |
not | -0.051 |
marks | -0.051 |
all | -0.050 |
rats | -0.050 |
pictures | -0.049 |
Token | they |
Token ID | 484 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ursion | +0.326 |
bet | +0.314 |
anna | +0.308 |
Of | +0.305 |
sur | +0.297 |
Neg logit contributions | |
es | -0.189 |
rats | -0.166 |
not | -0.160 |
stains | -0.154 |
marks | -0.151 |
Token | found |
Token ID | 1043 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
ursion | +0.029 |
anna | +0.028 |
bet | +0.027 |
pleasure | +0.026 |
Sure | +0.026 |
Neg logit contributions | |
es | -0.027 |
rats | -0.024 |
ts | -0.024 |
stains | -0.023 |
marks | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
es | +0.003 |
ts | +0.003 |
rats | +0.003 |
stains | +0.003 |
bes | +0.003 |
Neg logit contributions | |
bet | -0.006 |
ursion | -0.006 |
pleasure | -0.006 |
Of | -0.006 |
Sure | -0.006 |
Token | post |
Token ID | 1281 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ursion | +0.020 |
anna | +0.019 |
bet | +0.018 |
Sure | +0.017 |
Of | +0.017 |
Neg logit contributions | |
rats | -0.009 |
not | -0.008 |
marks | -0.008 |
stains | -0.008 |
es | -0.008 |
Token | standing |
Token ID | 5055 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ursion | +0.029 |
bet | +0.028 |
anna | +0.028 |
Of | +0.027 |
Sure | +0.027 |
Neg logit contributions | |
es | -0.017 |
rats | -0.016 |
ts | -0.015 |
stains | -0.015 |
marks | -0.015 |
Token | |
Token ID | 220 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
sur | +0.011 |
ursion | +0.010 |
adventurer | +0.010 |
den | +0.010 |
ya | +0.010 |
Neg logit contributions | |
es | -0.007 |
not | -0.006 |
isk | -0.005 |
mice | -0.005 |
't | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
ursion | +0.060 |
bet | +0.058 |
anna | +0.056 |
sur | +0.055 |
Of | +0.054 |
Neg logit contributions | |
es | -0.048 |
not | -0.041 |
rats | -0.040 |
marks | -0.039 |
stains | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.003 |
anna | +0.003 |
pleasure | +0.003 |
sur | +0.003 |
Neg logit contributions | |
es | -0.002 |
not | -0.002 |
ts | -0.002 |
rats | -0.002 |
marks | -0.002 |
Token | On |
Token ID | 2202 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.003 |
anna | +0.003 |
Of | +0.003 |
Sure | +0.003 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
ts | -0.003 |
stains | -0.003 |
marks | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ursion | +0.063 |
bet | +0.061 |
anna | +0.060 |
Sure | +0.058 |
Of | +0.058 |
Neg logit contributions | |
es | -0.025 |
rats | -0.022 |
ts | -0.021 |
stains | -0.021 |
marks | -0.020 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.061 |
bet | +0.057 |
Sure | +0.054 |
sur | +0.053 |
anna | +0.053 |
Neg logit contributions | |
cookies | -0.050 |
rats | -0.050 |
not | -0.049 |
ow | -0.049 |
marks | -0.049 |
Token | home |
Token ID | 1363 |
Feature activation | -5.94e-04 |
Pos logit contributions | |
ursion | +0.268 |
bet | +0.261 |
anna | +0.259 |
Of | +0.249 |
sur | +0.243 |
Neg logit contributions | |
es | -0.236 |
rats | -0.212 |
not | -0.211 |
stains | -0.203 |
marks | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
bet | -0.001 |
anna | -0.001 |
Sure | -0.001 |
Of | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
stains | +0.006 |
ts | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.013 |
bet | -0.013 |
anna | -0.013 |
Sure | -0.012 |
Of | -0.012 |
Token | made |
Token ID | 925 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ursion | +0.029 |
bet | +0.027 |
anna | +0.027 |
Of | +0.026 |
Sure | +0.026 |
Neg logit contributions | |
es | -0.026 |
rats | -0.024 |
ts | -0.024 |
stains | -0.024 |
marks | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
es | +0.037 |
rats | +0.034 |
ts | +0.033 |
adoes | +0.031 |
stains | +0.031 |
Neg logit contributions | |
anna | -0.059 |
bet | -0.058 |
pleasure | -0.057 |
ursion | -0.057 |
Of | -0.056 |
Token | so |
Token ID | 523 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
ursion | +0.024 |
bet | +0.023 |
anna | +0.023 |
Sure | +0.022 |
Of | +0.022 |
Neg logit contributions | |
es | -0.020 |
not | -0.018 |
rats | -0.018 |
ts | -0.018 |
marks | -0.017 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
ursion | +0.057 |
anna | +0.053 |
bet | +0.053 |
Sure | +0.052 |
Of | +0.051 |
Neg logit contributions | |
es | -0.061 |
not | -0.056 |
ts | -0.055 |
rats | -0.054 |
marks | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
es | +0.009 |
rats | +0.008 |
ts | +0.008 |
stains | +0.008 |
marks | +0.008 |
Neg logit contributions | |
ursion | -0.013 |
bet | -0.013 |
anna | -0.013 |
Sure | -0.012 |
Of | -0.012 |
Token | On |
Token ID | 1550 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ursion | +0.018 |
anna | +0.018 |
ounded | +0.017 |
sur | +0.017 |
ya | +0.017 |
Neg logit contributions | |
es | -0.008 |
not | -0.007 |
marks | -0.007 |
bones | -0.007 |
mice | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
ursion | +0.078 |
bet | +0.076 |
anna | +0.076 |
Of | +0.073 |
Sure | +0.073 |
Neg logit contributions | |
es | -0.034 |
rats | -0.030 |
ts | -0.029 |
stains | -0.029 |
marks | -0.028 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.058 |
bet | +0.054 |
Of | +0.053 |
Sure | +0.053 |
Shall | +0.051 |
Neg logit contributions | |
not | -0.044 |
marks | -0.044 |
pictures | -0.044 |
es | -0.043 |
puzzles | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
ursion | +0.294 |
anna | +0.289 |
bet | +0.283 |
Of | +0.282 |
sur | +0.266 |
Neg logit contributions | |
es | -0.215 |
not | -0.189 |
marks | -0.180 |
rats | -0.179 |
stains | -0.172 |
Token | they |
Token ID | 484 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.004 |
anna | +0.004 |
Sure | +0.004 |
Of | +0.004 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
ts | -0.004 |
stains | -0.004 |
marks | -0.003 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
ursion | +0.025 |
anna | +0.023 |
bet | +0.023 |
Sure | +0.022 |
Of | +0.022 |
Neg logit contributions | |
es | -0.024 |
ts | -0.022 |
rats | -0.022 |
stains | -0.021 |
marks | -0.021 |
Token | at |
Token ID | 379 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
ursion | +0.040 |
bet | +0.038 |
anna | +0.038 |
Sure | +0.036 |
Of | +0.036 |
Neg logit contributions | |
es | -0.028 |
rats | -0.026 |
ts | -0.025 |
stains | -0.025 |
marks | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
es | +0.003 |
rats | +0.003 |
stains | +0.003 |
ts | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
bet | -0.006 |
ursion | -0.006 |
Sure | -0.006 |
pleasure | -0.006 |
anna | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ursion | +0.030 |
anna | +0.029 |
Of | +0.028 |
ounded | +0.027 |
bet | +0.027 |
Neg logit contributions | |
es | -0.013 |
marks | -0.011 |
not | -0.011 |
ts | -0.010 |
stains | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
ursion | +0.022 |
ounded | +0.021 |
sur | +0.021 |
anna | +0.021 |
ya | +0.020 |
Neg logit contributions | |
es | -0.013 |
mice | -0.011 |
not | -0.011 |
isk | -0.010 |
rats | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.004 |
anna | +0.004 |
Of | +0.004 |
Sure | +0.004 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
ts | -0.003 |
stains | -0.002 |
marks | -0.002 |
Token | On |
Token ID | 2202 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ursion | +0.004 |
anna | +0.004 |
bet | +0.004 |
Sure | +0.004 |
Of | +0.004 |
Neg logit contributions | |
es | -0.004 |
rats | -0.003 |
ts | -0.003 |
stains | -0.003 |
marks | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ursion | +0.070 |
bet | +0.068 |
anna | +0.067 |
Sure | +0.065 |
Of | +0.065 |
Neg logit contributions | |
es | -0.030 |
rats | -0.026 |
ts | -0.025 |
stains | -0.025 |
marks | -0.024 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.051 |
anna | +0.046 |
bet | +0.045 |
Sure | +0.044 |
Of | +0.044 |
Neg logit contributions | |
puzzles | -0.048 |
marks | -0.048 |
not | -0.048 |
pictures | -0.047 |
cookies | -0.046 |
Token | back |
Token ID | 736 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ursion | +0.303 |
anna | +0.296 |
Of | +0.294 |
bet | +0.291 |
sur | +0.274 |
Neg logit contributions | |
es | -0.207 |
not | -0.185 |
marks | -0.175 |
rats | -0.171 |
stains | -0.167 |
Token | home |
Token ID | 1363 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
anna | +0.038 |
Of | +0.037 |
ursion | +0.036 |
bet | +0.034 |
Shall | +0.034 |
Neg logit contributions | |
es | -0.025 |
marks | -0.023 |
ings | -0.023 |
not | -0.021 |
rats | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
es | +0.003 |
rats | +0.003 |
ts | +0.003 |
stains | +0.003 |
marks | +0.003 |
Neg logit contributions | |
ursion | -0.005 |
bet | -0.004 |
anna | -0.004 |
Sure | -0.004 |
Of | -0.004 |
Token | car |
Token ID | 1097 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ursion | +0.053 |
anna | +0.050 |
bet | +0.050 |
Sure | +0.047 |
Of | +0.047 |
Neg logit contributions | |
es | -0.037 |
rats | -0.037 |
marks | -0.035 |
stains | -0.035 |
ts | -0.035 |
Token | had |
Token ID | 550 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ursion | +0.041 |
bet | +0.039 |
anna | +0.039 |
Of | +0.038 |
pleasure | +0.037 |
Neg logit contributions | |
es | -0.027 |
rats | -0.023 |
marks | -0.023 |
ts | -0.023 |
not | -0.022 |
Token | walking |
Token ID | 6155 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
ursion | +0.056 |
bet | +0.054 |
anna | +0.054 |
Sure | +0.051 |
Of | +0.051 |
Neg logit contributions | |
es | -0.048 |
rats | -0.044 |
ts | -0.043 |
stains | -0.043 |
marks | -0.042 |
Token | home |
Token ID | 1363 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ursion | +0.094 |
anna | +0.089 |
bet | +0.089 |
Of | +0.086 |
pleasure | +0.085 |
Neg logit contributions | |
es | -0.044 |
rats | -0.036 |
ts | -0.036 |
not | -0.036 |
marks | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
es | +0.039 |
rats | +0.037 |
stains | +0.036 |
ts | +0.035 |
marks | +0.035 |
Neg logit contributions | |
ursion | -0.066 |
bet | -0.065 |
anna | -0.064 |
Sure | -0.062 |
sur | -0.061 |
Token | Along |
Token ID | 17159 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
es | +0.003 |
not | +0.002 |
mice | +0.002 |
rats | +0.002 |
isk | +0.002 |
Neg logit contributions | |
sur | -0.004 |
ursion | -0.004 |
anna | -0.004 |
bet | -0.004 |
ounded | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
ursion | +0.210 |
bet | +0.204 |
anna | +0.204 |
Of | +0.198 |
Sure | +0.195 |
Neg logit contributions | |
es | -0.062 |
rats | -0.051 |
ts | -0.048 |
stains | -0.047 |
marks | -0.046 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.052 |
anna | +0.049 |
uster | +0.049 |
sur | +0.048 |
bet | +0.048 |
Neg logit contributions | |
not | -0.053 |
pictures | -0.051 |
rats | -0.050 |
animals | -0.049 |
marks | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
ursion | +0.325 |
bet | +0.316 |
anna | +0.312 |
Of | +0.308 |
sur | +0.299 |
Neg logit contributions | |
es | -0.185 |
rats | -0.159 |
not | -0.158 |
marks | -0.147 |
stains | -0.147 |
Token | she |
Token ID | 673 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
es | +0.004 |
stains | +0.004 |
rats | +0.004 |
marks | +0.004 |
ts | +0.004 |
Neg logit contributions | |
ursion | -0.004 |
bet | -0.004 |
anna | -0.003 |
Sure | -0.003 |
Of | -0.003 |
Token | played |
Token ID | 2826 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
ursion | +0.037 |
bet | +0.034 |
anna | +0.034 |
Of | +0.033 |
pleasure | +0.033 |
Neg logit contributions | |
es | -0.030 |
ts | -0.026 |
rats | -0.026 |
not | -0.026 |
marks | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
stains | +0.033 |
rats | +0.032 |
es | +0.032 |
oni | +0.031 |
burns | +0.031 |
Neg logit contributions | |
bet | -0.046 |
ursion | -0.043 |
Sure | -0.043 |
Of | -0.042 |
anna | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
es | +0.007 |
stains | +0.006 |
bes | +0.006 |
ts | +0.006 |
oni | +0.006 |
Neg logit contributions | |
bet | -0.009 |
pleasure | -0.009 |
ursion | -0.009 |
Sure | -0.009 |
Of | -0.009 |
Token | way |
Token ID | 835 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
es | +0.040 |
rats | +0.040 |
marks | +0.039 |
not | +0.038 |
stains | +0.038 |
Neg logit contributions | |
ursion | -0.052 |
anna | -0.049 |
bet | -0.048 |
Of | -0.047 |
Sure | -0.046 |
Token | home |
Token ID | 1363 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ursion | +0.217 |
anna | +0.211 |
bet | +0.208 |
Of | +0.202 |
Sure | +0.198 |
Neg logit contributions | |
not | -0.150 |
es | -0.149 |
marks | -0.139 |
stains | -0.136 |
rats | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
es | +0.036 |
rats | +0.034 |
stains | +0.032 |
ts | +0.031 |
mice | +0.031 |
Neg logit contributions | |
ursion | -0.053 |
bet | -0.052 |
anna | -0.052 |
Sure | -0.050 |
pleasure | -0.049 |
Token | Along |
Token ID | 17159 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
ursion | +0.007 |
anna | +0.006 |
bet | +0.006 |
sur | +0.006 |
Of | +0.006 |
Neg logit contributions | |
es | -0.006 |
not | -0.005 |
rats | -0.005 |
marks | -0.005 |
isk | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ursion | +0.213 |
bet | +0.206 |
anna | +0.206 |
Of | +0.199 |
Sure | +0.197 |
Neg logit contributions | |
es | -0.068 |
rats | -0.058 |
ts | -0.055 |
stains | -0.054 |
marks | -0.053 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.049 |
Of | +0.046 |
sur | +0.044 |
bet | +0.043 |
Sure | +0.043 |
Neg logit contributions | |
marks | -0.060 |
rats | -0.059 |
not | -0.058 |
es | -0.057 |
monsters | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
ursion | +0.323 |
bet | +0.314 |
anna | +0.313 |
Of | +0.303 |
pleasure | +0.294 |
Neg logit contributions | |
es | -0.187 |
rats | -0.166 |
not | -0.160 |
marks | -0.152 |
stains | -0.149 |
Token | he |
Token ID | 339 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
es | +0.004 |
rats | +0.004 |
ts | +0.004 |
not | +0.004 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.004 |
anna | -0.004 |
bet | -0.004 |
Of | -0.004 |
Sure | -0.004 |
Token | met |
Token ID | 1138 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ursion | +0.013 |
bet | +0.013 |
anna | +0.013 |
Sure | +0.012 |
sur | +0.012 |
Neg logit contributions | |
es | -0.014 |
rats | -0.013 |
stains | -0.013 |
ts | -0.013 |
marks | -0.012 |
Token | some |
Token ID | 617 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
bet | +0.040 |
Of | +0.039 |
ursion | +0.039 |
anna | +0.039 |
pleasure | +0.039 |
Neg logit contributions | |
es | -0.021 |
stains | -0.020 |
ts | -0.020 |
rats | -0.019 |
bes | -0.019 |
Token | other |
Token ID | 584 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
es | +0.015 |
rats | +0.013 |
ts | +0.013 |
stains | +0.013 |
marks | +0.013 |
Neg logit contributions | |
ursion | -0.025 |
bet | -0.024 |
anna | -0.024 |
Sure | -0.023 |
Of | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -6.48e-04 |
Pos logit contributions | |
es | +0.037 |
rats | +0.034 |
ts | +0.033 |
stains | +0.032 |
marks | +0.032 |
Neg logit contributions | |
ursion | -0.052 |
bet | -0.050 |
anna | -0.049 |
Of | -0.048 |
pleasure | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
es | +0.001 |
not | +0.001 |
stains | +0.001 |
marks | +0.001 |
adoes | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
sur | -0.001 |
bet | -0.001 |
anna | -0.001 |
pleasure | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
es | +0.004 |
not | +0.004 |
rats | +0.004 |
marks | +0.004 |
stains | +0.003 |
Neg logit contributions | |
ursion | -0.005 |
bet | -0.005 |
anna | -0.005 |
pleasure | -0.005 |
sur | -0.005 |
Token | On |
Token ID | 2202 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
es | +0.003 |
rats | +0.003 |
ts | +0.003 |
stains | +0.003 |
marks | +0.003 |
Neg logit contributions | |
ursion | -0.003 |
anna | -0.003 |
bet | -0.003 |
Of | -0.003 |
Sure | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ursion | +0.049 |
bet | +0.047 |
anna | +0.046 |
Sure | +0.046 |
Of | +0.045 |
Neg logit contributions | |
es | -0.026 |
rats | -0.023 |
ts | -0.021 |
stains | -0.021 |
marks | -0.021 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.034 |
bet | +0.032 |
anna | +0.031 |
sur | +0.030 |
pleasure | +0.028 |
Neg logit contributions | |
es | -0.061 |
rats | -0.060 |
not | -0.060 |
puzzles | -0.059 |
stains | -0.059 |
Token | home |
Token ID | 1363 |
Feature activation | -9.56e-04 |
Pos logit contributions | |
ursion | +0.230 |
bet | +0.217 |
anna | +0.215 |
Sure | +0.204 |
Of | +0.202 |
Neg logit contributions | |
es | -0.278 |
rats | -0.260 |
ts | -0.257 |
stains | -0.254 |
marks | -0.251 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.002 |
bet | -0.002 |
anna | -0.001 |
Sure | -0.001 |
Of | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
es | +0.019 |
ts | +0.017 |
rats | +0.017 |
marks | +0.017 |
stains | +0.017 |
Neg logit contributions | |
ursion | -0.016 |
bet | -0.016 |
Sure | -0.016 |
Of | -0.015 |
anna | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ursion | +0.020 |
bet | +0.019 |
anna | +0.019 |
Sure | +0.018 |
Of | +0.018 |
Neg logit contributions | |
es | -0.020 |
rats | -0.019 |
ts | -0.018 |
stains | -0.018 |
marks | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
es | +0.016 |
bes | +0.015 |
ts | +0.015 |
icer | +0.015 |
ink | +0.014 |
Neg logit contributions | |
Of | -0.021 |
ursion | -0.019 |
bet | -0.019 |
Sure | -0.019 |
pleasure | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
es | +0.021 |
not | +0.018 |
marks | +0.017 |
rats | +0.017 |
stains | +0.017 |
Neg logit contributions | |
ursion | -0.045 |
bet | -0.043 |
anna | -0.042 |
Of | -0.041 |
Sure | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
ursion | +0.009 |
bet | +0.009 |
sur | +0.009 |
anna | +0.009 |
den | +0.009 |
Neg logit contributions | |
es | -0.007 |
not | -0.007 |
stains | -0.007 |
accidents | -0.006 |
ings | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.003 |
anna | +0.003 |
Sure | +0.002 |
Of | +0.002 |
Neg logit contributions | |
es | -0.001 |
rats | -0.001 |
stains | -0.001 |
ts | -0.001 |
marks | -0.001 |
Token | On |
Token ID | 2202 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.003 |
anna | +0.003 |
Sure | +0.002 |
pleasure | +0.002 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
stains | -0.003 |
ts | -0.003 |
marks | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ursion | +0.063 |
bet | +0.061 |
anna | +0.061 |
Of | +0.059 |
Sure | +0.059 |
Neg logit contributions | |
es | -0.024 |
rats | -0.021 |
ts | -0.020 |
stains | -0.020 |
marks | -0.019 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.064 |
bet | +0.062 |
anna | +0.060 |
uster | +0.059 |
Sure | +0.057 |
Neg logit contributions | |
not | -0.044 |
sandwiches | -0.043 |
marks | -0.042 |
pictures | -0.041 |
cookies | -0.040 |
Token | home |
Token ID | 1363 |
Feature activation | -7.87e-04 |
Pos logit contributions | |
ursion | +0.277 |
bet | +0.275 |
anna | +0.266 |
Of | +0.261 |
sur | +0.255 |
Neg logit contributions | |
es | -0.223 |
not | -0.202 |
rats | -0.189 |
stains | -0.188 |
marks | -0.186 |
Token | , |
Token ID | 11 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
stains | +0.001 |
ts | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
bet | -0.001 |
anna | -0.001 |
Of | -0.001 |
Sure | -0.001 |
Token | Hannah |
Token ID | 26013 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
es | +0.013 |
rats | +0.012 |
stains | +0.012 |
ts | +0.012 |
marks | +0.012 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.008 |
anna | -0.008 |
Sure | -0.007 |
Of | -0.007 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ursion | +0.055 |
bet | +0.052 |
pleasure | +0.051 |
Of | +0.050 |
Sure | +0.050 |
Neg logit contributions | |
es | -0.045 |
not | -0.039 |
ts | -0.038 |
rats | -0.038 |
marks | -0.038 |
Token | out |
Token ID | 503 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ursion | +0.033 |
bet | +0.031 |
anna | +0.031 |
Of | +0.030 |
Sure | +0.030 |
Neg logit contributions | |
es | -0.018 |
not | -0.016 |
stains | -0.015 |
rats | -0.015 |
marks | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
es | +0.032 |
rats | +0.028 |
stains | +0.027 |
ts | +0.027 |
not | +0.027 |
Neg logit contributions | |
ursion | -0.066 |
bet | -0.063 |
anna | -0.062 |
Of | -0.060 |
Sure | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
ursion | +0.020 |
anna | +0.020 |
bet | +0.019 |
sur | +0.019 |
fy | +0.018 |
Neg logit contributions | |
not | -0.010 |
es | -0.009 |
mice | -0.008 |
oni | -0.008 |
marks | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.40e-03 |
Pos logit contributions | |
ursion | +0.007 |
pleasure | +0.007 |
bet | +0.007 |
anna | +0.007 |
adventurer | +0.007 |
Neg logit contributions | |
es | -0.004 |
not | -0.003 |
oni | -0.003 |
marks | -0.003 |
ings | -0.003 |
Token | On |
Token ID | 2202 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ursion | +0.008 |
pleasure | +0.008 |
anna | +0.008 |
bet | +0.008 |
sur | +0.007 |
Neg logit contributions | |
es | -0.005 |
not | -0.005 |
marks | -0.004 |
mice | -0.004 |
ts | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ursion | +0.062 |
bet | +0.060 |
anna | +0.060 |
Sure | +0.058 |
Of | +0.058 |
Neg logit contributions | |
es | -0.027 |
rats | -0.024 |
stains | -0.023 |
ts | -0.023 |
marks | -0.022 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.053 |
uster | +0.050 |
anna | +0.050 |
Sure | +0.048 |
bet | +0.048 |
Neg logit contributions | |
not | -0.051 |
pictures | -0.051 |
marks | -0.050 |
puzzles | -0.050 |
cookies | -0.049 |
Token | home |
Token ID | 1363 |
Feature activation | -2.29e-04 |
Pos logit contributions | |
ursion | +0.269 |
anna | +0.263 |
bet | +0.261 |
Of | +0.252 |
pleasure | +0.243 |
Neg logit contributions | |
es | -0.236 |
not | -0.209 |
rats | -0.209 |
marks | -0.204 |
stains | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
es | +0.000 |
rats | +0.000 |
ts | +0.000 |
stains | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Of | -0.000 |
Sure | -0.000 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
ts | +0.005 |
marks | +0.005 |
stains | +0.005 |
Neg logit contributions | |
ursion | -0.005 |
anna | -0.004 |
bet | -0.004 |
Of | -0.004 |
Sure | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
ursion | +0.027 |
bet | +0.025 |
anna | +0.025 |
Of | +0.025 |
pleasure | +0.025 |
Neg logit contributions | |
es | -0.027 |
rats | -0.024 |
marks | -0.023 |
ts | -0.023 |
not | -0.023 |
Token | feeling |
Token ID | 4203 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ursion | +0.014 |
bet | +0.014 |
anna | +0.014 |
Of | +0.013 |
Sure | +0.013 |
Neg logit contributions | |
es | -0.011 |
rats | -0.010 |
ts | -0.010 |
stains | -0.010 |
marks | -0.010 |
Token | |
Token ID | 220 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
den | +0.008 |
ursion | +0.008 |
anna | +0.008 |
sur | +0.008 |
adventurer | +0.007 |
Neg logit contributions | |
not | -0.005 |
es | -0.005 |
ings | -0.005 |
mice | -0.005 |
isk | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
ursion | +0.050 |
bet | +0.048 |
anna | +0.047 |
sur | +0.045 |
Of | +0.045 |
Neg logit contributions | |
es | -0.043 |
rats | -0.037 |
not | -0.037 |
marks | -0.037 |
stains | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-04 |
Pos logit contributions | |
es | +0.003 |
not | +0.003 |
stains | +0.003 |
marks | +0.003 |
rats | +0.003 |
Neg logit contributions | |
ursion | -0.004 |
anna | -0.004 |
bet | -0.004 |
pleasure | -0.004 |
Sure | -0.004 |
Token | Along |
Token ID | 24035 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
es | +0.000 |
rats | +0.000 |
ts | +0.000 |
stains | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Sure | -0.000 |
Of | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
ursion | +0.263 |
anna | +0.258 |
Of | +0.257 |
bet | +0.256 |
Sure | +0.252 |
Neg logit contributions | |
es | -0.074 |
marks | -0.052 |
not | -0.052 |
stains | -0.051 |
rats | -0.050 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.050 |
Sure | +0.049 |
Of | +0.049 |
bet | +0.048 |
anna | +0.048 |
Neg logit contributions | |
pictures | -0.059 |
marks | -0.058 |
not | -0.056 |
puzzles | -0.055 |
all | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -9.60e-04 |
Pos logit contributions | |
ursion | +0.337 |
Of | +0.324 |
bet | +0.323 |
anna | +0.319 |
sur | +0.311 |
Neg logit contributions | |
es | -0.173 |
not | -0.153 |
rats | -0.136 |
ings | -0.135 |
marks | -0.131 |
Token | Sally |
Token ID | 25737 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
es | +0.002 |
rats | +0.001 |
not | +0.001 |
stains | +0.001 |
mice | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
anna | -0.001 |
bet | -0.001 |
Sure | -0.001 |
sur | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ursion | +0.043 |
bet | +0.040 |
Of | +0.039 |
pleasure | +0.039 |
Sure | +0.039 |
Neg logit contributions | |
es | -0.034 |
marks | -0.029 |
not | -0.029 |
rats | -0.029 |
stains | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ursion | +0.040 |
bet | +0.039 |
anna | +0.039 |
Of | +0.037 |
Sure | +0.037 |
Neg logit contributions | |
es | -0.022 |
rats | -0.020 |
ts | -0.020 |
stains | -0.019 |
marks | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.003 |
anna | +0.003 |
Of | +0.003 |
Sure | +0.003 |
Neg logit contributions | |
es | -0.002 |
rats | -0.001 |
ts | -0.001 |
stains | -0.001 |
marks | -0.001 |
Token | |
Token ID | 220 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ursion | +0.025 |
ya | +0.025 |
anna | +0.025 |
ounded | +0.025 |
sur | +0.024 |
Neg logit contributions | |
es | -0.011 |
not | -0.010 |
isk | -0.009 |
mice | -0.009 |
bones | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
ursion | +0.059 |
bet | +0.056 |
anna | +0.056 |
Of | +0.053 |
sur | +0.053 |
Neg logit contributions | |
es | -0.055 |
rats | -0.049 |
ts | -0.048 |
marks | -0.047 |
stains | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
ursion | +0.013 |
anna | +0.012 |
bet | +0.012 |
pleasure | +0.012 |
ounded | +0.011 |
Neg logit contributions | |
es | -0.008 |
not | -0.007 |
bes | -0.006 |
ts | -0.006 |
isk | -0.006 |
Token | Along |
Token ID | 24035 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ursion | +0.015 |
anna | +0.014 |
bet | +0.014 |
pleasure | +0.014 |
Sure | +0.013 |
Neg logit contributions | |
es | -0.013 |
rats | -0.011 |
not | -0.011 |
ts | -0.011 |
marks | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
ursion | +0.242 |
anna | +0.239 |
bet | +0.237 |
Of | +0.236 |
pleasure | +0.230 |
Neg logit contributions | |
es | -0.094 |
ts | -0.073 |
rats | -0.072 |
marks | -0.071 |
stains | -0.068 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Of | +0.056 |
ursion | +0.055 |
anna | +0.053 |
Sure | +0.052 |
bet | +0.052 |
Neg logit contributions | |
pictures | -0.061 |
puzzles | -0.058 |
marks | -0.058 |
not | -0.058 |
rats | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
ursion | +0.323 |
anna | +0.314 |
bet | +0.314 |
Of | +0.314 |
pleasure | +0.297 |
Neg logit contributions | |
es | -0.190 |
not | -0.158 |
rats | -0.155 |
marks | -0.150 |
ts | -0.145 |
Token | Mark |
Token ID | 2940 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ursion | +0.007 |
bet | +0.007 |
anna | +0.007 |
Of | +0.006 |
Sure | +0.006 |
Neg logit contributions | |
es | -0.006 |
rats | -0.005 |
ts | -0.005 |
stains | -0.005 |
marks | -0.005 |
Token | met |
Token ID | 1138 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
ursion | +0.039 |
bet | +0.036 |
Of | +0.036 |
pleasure | +0.035 |
Sure | +0.035 |
Neg logit contributions | |
es | -0.032 |
rats | -0.028 |
ts | -0.028 |
marks | -0.027 |
stains | -0.027 |
Token | some |
Token ID | 617 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ursion | +0.036 |
bet | +0.036 |
anna | +0.035 |
Of | +0.034 |
Sure | +0.034 |
Neg logit contributions | |
es | -0.017 |
stains | -0.015 |
rats | -0.015 |
ts | -0.015 |
marks | -0.014 |
Token | new |
Token ID | 649 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
es | +0.018 |
rats | +0.017 |
ts | +0.016 |
marks | +0.016 |
mice | +0.015 |
Neg logit contributions | |
ursion | -0.030 |
anna | -0.028 |
bet | -0.028 |
Sure | -0.027 |
Of | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
es | +0.030 |
rats | +0.026 |
ts | +0.025 |
stains | +0.025 |
marks | +0.025 |
Neg logit contributions | |
ursion | -0.059 |
bet | -0.057 |
anna | -0.057 |
Of | -0.055 |
Sure | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
ursion | +0.008 |
bet | +0.007 |
ounded | +0.007 |
anna | +0.007 |
sur | +0.007 |
Neg logit contributions | |
es | -0.005 |
not | -0.005 |
mice | -0.005 |
rats | -0.004 |
bones | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.002 |
anna | +0.002 |
pleasure | +0.002 |
sur | +0.002 |
Neg logit contributions | |
es | -0.002 |
rats | -0.002 |
not | -0.002 |
ts | -0.002 |
marks | -0.002 |
Token | On |
Token ID | 2202 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ursion | +0.004 |
bet | +0.004 |
anna | +0.004 |
Sure | +0.004 |
Of | +0.004 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
ts | -0.004 |
stains | -0.004 |
marks | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ursion | +0.060 |
bet | +0.058 |
anna | +0.057 |
Sure | +0.056 |
pleasure | +0.055 |
Neg logit contributions | |
es | -0.028 |
rats | -0.025 |
stains | -0.023 |
ts | -0.023 |
marks | -0.023 |
Token | way |
Token ID | 835 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ursion | +0.047 |
bet | +0.043 |
anna | +0.042 |
Of | +0.041 |
sur | +0.040 |
Neg logit contributions | |
puzzles | -0.049 |
not | -0.049 |
marks | -0.049 |
cookies | -0.048 |
pictures | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
ursion | +0.285 |
anna | +0.277 |
bet | +0.276 |
Of | +0.272 |
pleasure | +0.257 |
Neg logit contributions | |
es | -0.224 |
not | -0.195 |
rats | -0.195 |
marks | -0.189 |
stains | -0.183 |
Token | school |
Token ID | 1524 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
marks | +0.001 |
stains | +0.001 |
Neg logit contributions | |
ursion | -0.004 |
anna | -0.004 |
bet | -0.004 |
Of | -0.003 |
Sure | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
ursion | +0.031 |
bet | +0.030 |
anna | +0.029 |
Of | +0.029 |
pleasure | +0.028 |
Neg logit contributions | |
es | -0.019 |
rats | -0.016 |
ts | -0.016 |
not | -0.016 |
marks | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
es | +0.009 |
rats | +0.008 |
stains | +0.008 |
ts | +0.008 |
marks | +0.008 |
Neg logit contributions | |
ursion | -0.010 |
bet | -0.010 |
anna | -0.009 |
Sure | -0.009 |
Of | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
ursion | +0.010 |
bet | +0.010 |
anna | +0.010 |
Sure | +0.009 |
sur | +0.009 |
Neg logit contributions | |
es | -0.010 |
rats | -0.010 |
stains | -0.009 |
ts | -0.009 |
marks | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
ursion | +0.045 |
bet | +0.042 |
anna | +0.042 |
Of | +0.041 |
Sure | +0.040 |
Neg logit contributions | |
es | -0.023 |
rats | -0.020 |
marks | -0.019 |
stains | -0.019 |
not | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-04 |
Pos logit contributions | |
sur | +0.008 |
ursion | +0.008 |
ounded | +0.007 |
bet | +0.007 |
anna | +0.007 |
Neg logit contributions | |
es | -0.005 |
mice | -0.004 |
isk | -0.004 |
not | -0.004 |
rats | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
es | +0.000 |
not | +0.000 |
rats | +0.000 |
ts | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
pleasure | -0.000 |
sur | -0.000 |
Token | On |
Token ID | 2202 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
ursion | +0.002 |
anna | +0.002 |
bet | +0.002 |
pleasure | +0.002 |
Sure | +0.002 |
Neg logit contributions | |
es | -0.002 |
rats | -0.002 |
ts | -0.002 |
stains | -0.001 |
marks | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ursion | +0.063 |
bet | +0.061 |
anna | +0.060 |
Sure | +0.058 |
pleasure | +0.058 |
Neg logit contributions | |
es | -0.030 |
rats | -0.028 |
ts | -0.026 |
stains | -0.026 |
mice | -0.025 |
Token | way |
Token ID | 835 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ursion | +0.052 |
bet | +0.047 |
anna | +0.047 |
sur | +0.045 |
Sure | +0.044 |
Neg logit contributions | |
marks | -0.049 |
cookies | -0.048 |
puzzles | -0.048 |
pictures | -0.048 |
stains | -0.046 |
Token | back |
Token ID | 736 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ursion | +0.281 |
bet | +0.271 |
anna | +0.270 |
Of | +0.261 |
sur | +0.254 |
Neg logit contributions | |
es | -0.227 |
rats | -0.201 |
marks | -0.196 |
stains | -0.195 |
not | -0.195 |
Token | home |
Token ID | 1363 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
anna | +0.035 |
ursion | +0.034 |
Of | +0.034 |
bet | +0.032 |
Shall | +0.031 |
Neg logit contributions | |
es | -0.024 |
ings | -0.021 |
marks | -0.021 |
puzzles | -0.020 |
rats | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
es | +0.007 |
rats | +0.007 |
ts | +0.007 |
stains | +0.007 |
marks | +0.007 |
Neg logit contributions | |
ursion | -0.009 |
bet | -0.009 |
anna | -0.009 |
Sure | -0.008 |
Of | -0.008 |
Token | Betsy |
Token ID | 45775 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
es | +0.011 |
stains | +0.010 |
rats | +0.010 |
ts | +0.010 |
marks | +0.010 |
Neg logit contributions | |
ursion | -0.013 |
bet | -0.012 |
anna | -0.012 |
Sure | -0.012 |
Of | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
es | +0.013 |
rats | +0.012 |
ts | +0.012 |
stains | +0.012 |
marks | +0.012 |
Neg logit contributions | |
ursion | -0.012 |
anna | -0.012 |
bet | -0.012 |
Sure | -0.011 |
sur | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
ursion | +0.049 |
anna | +0.048 |
bet | +0.047 |
Of | +0.046 |
Sure | +0.045 |
Neg logit contributions | |
es | -0.015 |
not | -0.013 |
marks | -0.012 |
stains | -0.011 |
rats | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
ursion | +0.013 |
anna | +0.013 |
bet | +0.013 |
ya | +0.013 |
sur | +0.013 |
Neg logit contributions | |
es | -0.007 |
not | -0.007 |
isk | -0.006 |
marks | -0.006 |
bones | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
ursion | +0.006 |
bet | +0.006 |
anna | +0.006 |
Of | +0.006 |
Sure | +0.006 |
Neg logit contributions | |
es | -0.005 |
rats | -0.004 |
ts | -0.004 |
stains | -0.004 |
marks | -0.004 |
Token | On |
Token ID | 2202 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ursion | +0.009 |
bet | +0.008 |
anna | +0.008 |
Of | +0.008 |
Sure | +0.008 |
Neg logit contributions | |
es | -0.007 |
rats | -0.007 |
ts | -0.006 |
stains | -0.006 |
marks | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
ursion | +0.059 |
bet | +0.057 |
anna | +0.057 |
Sure | +0.055 |
pleasure | +0.055 |
Neg logit contributions | |
es | -0.027 |
rats | -0.024 |
stains | -0.022 |
ts | -0.022 |
marks | -0.022 |
Token | way |
Token ID | 835 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ursion | +0.043 |
bet | +0.040 |
anna | +0.039 |
sur | +0.037 |
Of | +0.036 |
Neg logit contributions | |
es | -0.054 |
rats | -0.053 |
puzzles | -0.053 |
marks | -0.052 |
stains | -0.052 |
Token | home |
Token ID | 1363 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
ursion | +0.268 |
anna | +0.261 |
bet | +0.261 |
Of | +0.252 |
pleasure | +0.240 |
Neg logit contributions | |
es | -0.237 |
rats | -0.211 |
not | -0.209 |
marks | -0.206 |
stains | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
es | +0.004 |
rats | +0.004 |
ts | +0.004 |
stains | +0.004 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.005 |
bet | -0.005 |
anna | -0.005 |
Sure | -0.005 |
Of | -0.005 |
Token | Tim |
Token ID | 5045 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
es | +0.006 |
rats | +0.006 |
ts | +0.006 |
stains | +0.006 |
marks | +0.005 |
Neg logit contributions | |
ursion | -0.010 |
anna | -0.009 |
bet | -0.009 |
Of | -0.009 |
Sure | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | -8.33e-04 |
Pos logit contributions | |
ursion | +0.008 |
bet | +0.007 |
Of | +0.007 |
Sure | +0.007 |
pleasure | +0.007 |
Neg logit contributions | |
es | -0.005 |
marks | -0.005 |
rats | -0.004 |
isk | -0.004 |
stains | -0.004 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
marks | +0.001 |
stains | +0.001 |
ts | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
bet | -0.001 |
Of | -0.001 |
pleasure | -0.001 |
anna | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
es | +0.041 |
rats | +0.039 |
stains | +0.037 |
ts | +0.037 |
marks | +0.036 |
Neg logit contributions | |
ursion | -0.072 |
bet | -0.070 |
anna | -0.069 |
Sure | -0.066 |
Of | -0.066 |
Token | filled |
Token ID | 5901 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
stains | +0.005 |
ts | +0.005 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.007 |
anna | -0.007 |
pleasure | -0.007 |
Sure | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
rats | +0.094 |
stains | +0.089 |
ow | +0.085 |
blood | +0.084 |
es | +0.084 |
Neg logit contributions | |
bet | -0.130 |
ursion | -0.129 |
Sure | -0.126 |
anna | -0.125 |
sur | -0.125 |
Token | delicious |
Token ID | 12625 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
es | +0.025 |
rats | +0.023 |
ts | +0.022 |
stains | +0.022 |
marks | +0.022 |
Neg logit contributions | |
ursion | -0.027 |
bet | -0.026 |
anna | -0.025 |
pleasure | -0.025 |
Of | -0.024 |
Token | ch |
Token ID | 442 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
es | +0.050 |
isk | +0.044 |
not | +0.044 |
ts | +0.043 |
rats | +0.042 |
Neg logit contributions | |
anna | -0.081 |
pleasure | -0.080 |
bet | -0.079 |
ursion | -0.079 |
sur | -0.077 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ursion | +0.010 |
anna | +0.010 |
bet | +0.009 |
pleasure | +0.009 |
sur | +0.009 |
Neg logit contributions | |
es | -0.008 |
rats | -0.007 |
not | -0.007 |
stains | -0.007 |
ts | -0.007 |
Token | ates |
Token ID | 689 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
rats | +0.138 |
stains | +0.133 |
not | +0.131 |
accidents | +0.124 |
blood | +0.119 |
Neg logit contributions | |
anna | -0.295 |
ursion | -0.286 |
pad | -0.262 |
bet | -0.262 |
pleasure | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
es | +0.015 |
rats | +0.015 |
ts | +0.014 |
stains | +0.014 |
adoes | +0.013 |
Neg logit contributions | |
ursion | -0.024 |
anna | -0.024 |
bet | -0.023 |
sur | -0.022 |
Sure | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ursion | +0.008 |
anna | +0.008 |
bet | +0.007 |
ounded | +0.007 |
den | +0.007 |
Neg logit contributions | |
es | -0.004 |
not | -0.003 |
mice | -0.003 |
isk | -0.003 |
all | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
es | +0.022 |
ts | +0.019 |
not | +0.019 |
rats | +0.019 |
marks | +0.019 |
Neg logit contributions | |
ursion | -0.025 |
bet | -0.023 |
anna | -0.023 |
Sure | -0.022 |
pleasure | -0.021 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ursion | +0.011 |
bet | +0.011 |
anna | +0.011 |
Sure | +0.010 |
Of | +0.010 |
Neg logit contributions | |
es | -0.011 |
not | -0.011 |
rats | -0.010 |
ts | -0.010 |
stains | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
es | +0.007 |
isk | +0.007 |
bes | +0.007 |
adoes | +0.006 |
stains | +0.006 |
Neg logit contributions | |
bet | -0.012 |
pleasure | -0.011 |
Sure | -0.011 |
anna | -0.011 |
ursion | -0.011 |
Token | soup |
Token ID | 17141 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
bet | +0.037 |
ursion | +0.036 |
pleasure | +0.035 |
anna | +0.035 |
Sure | +0.034 |
Neg logit contributions | |
es | -0.038 |
isk | -0.033 |
ts | -0.032 |
adoes | -0.031 |
rats | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
rats | +0.044 |
es | +0.043 |
adoes | +0.043 |
ts | +0.042 |
isk | +0.042 |
Neg logit contributions | |
ursion | -0.050 |
bet | -0.049 |
anna | -0.047 |
Sure | -0.047 |
Shall | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
es | +0.025 |
isk | +0.024 |
ts | +0.023 |
bes | +0.022 |
stains | +0.022 |
Neg logit contributions | |
bet | -0.023 |
ursion | -0.022 |
Sure | -0.022 |
Of | -0.021 |
anna | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -2.97e-04 |
Pos logit contributions | |
adoes | +0.037 |
rats | +0.036 |
isk | +0.035 |
ings | +0.035 |
es | +0.035 |
Neg logit contributions | |
bet | -0.026 |
ursion | -0.024 |
Shall | -0.023 |
Sure | -0.023 |
anna | -0.023 |
Token | ste |
Token ID | 2876 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
es | +0.000 |
isk | +0.000 |
rats | +0.000 |
ts | +0.000 |
adoes | +0.000 |
Neg logit contributions | |
pleasure | -0.000 |
bet | -0.000 |
ursion | -0.000 |
Shall | -0.000 |
pad | -0.000 |
Token | aming |
Token ID | 3723 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
rats | +0.235 |
es | +0.222 |
stains | +0.218 |
adoes | +0.215 |
snakes | +0.213 |
Neg logit contributions | |
ursion | -0.207 |
anna | -0.182 |
bet | -0.182 |
sur | -0.161 |
Sure | -0.161 |
Token | hot |
Token ID | 3024 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
es | +0.031 |
rats | +0.029 |
ts | +0.029 |
isk | +0.027 |
blood | +0.025 |
Neg logit contributions | |
ursion | -0.041 |
anna | -0.040 |
bet | -0.039 |
sur | -0.037 |
Sure | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
es | +0.054 |
rats | +0.049 |
ts | +0.048 |
stains | +0.046 |
marks | +0.046 |
Neg logit contributions | |
ursion | -0.090 |
bet | -0.087 |
anna | -0.087 |
Sure | -0.083 |
Of | -0.082 |
Token | She |
Token ID | 1375 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
es | +0.006 |
rats | +0.005 |
marks | +0.005 |
not | +0.005 |
stains | +0.005 |
Neg logit contributions | |
ursion | -0.004 |
bet | -0.004 |
anna | -0.004 |
sur | -0.004 |
Of | -0.004 |
Token | pretended |
Token ID | 36766 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
es | +0.025 |
rats | +0.024 |
stains | +0.023 |
adoes | +0.023 |
ts | +0.023 |
Neg logit contributions | |
ursion | -0.024 |
bet | -0.024 |
anna | -0.024 |
Sure | -0.022 |
Of | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
anna | +0.056 |
bet | +0.055 |
Sure | +0.054 |
ursion | +0.054 |
Of | +0.053 |
Neg logit contributions | |
es | -0.035 |
stains | -0.033 |
rats | -0.033 |
bes | -0.031 |
ts | -0.031 |
Token | laughed |
Token ID | 13818 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
es | +0.014 |
ts | +0.013 |
rats | +0.013 |
stains | +0.013 |
not | +0.013 |
Neg logit contributions | |
ursion | -0.014 |
anna | -0.013 |
bet | -0.013 |
pleasure | -0.012 |
Of | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
rats | +0.043 |
es | +0.042 |
ts | +0.042 |
stains | +0.041 |
isk | +0.041 |
Neg logit contributions | |
bet | -0.048 |
ursion | -0.047 |
anna | -0.046 |
Of | -0.046 |
Sure | -0.046 |
Token | ate |
Token ID | 15063 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
es | +0.022 |
ts | +0.020 |
rats | +0.020 |
stains | +0.020 |
not | +0.020 |
Neg logit contributions | |
ursion | -0.023 |
anna | -0.022 |
bet | -0.021 |
Sure | -0.020 |
Of | -0.020 |
Token | ch |
Token ID | 442 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
es | +0.093 |
isk | +0.087 |
rats | +0.086 |
stains | +0.084 |
adoes | +0.083 |
Neg logit contributions | |
bet | -0.128 |
pleasure | -0.125 |
anna | -0.125 |
Sure | -0.124 |
ursion | -0.122 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
not | +0.006 |
rats | +0.005 |
stains | +0.005 |
es | +0.005 |
isk | +0.005 |
Neg logit contributions | |
anna | -0.006 |
ursion | -0.005 |
bet | -0.005 |
sur | -0.005 |
pleasure | -0.005 |
Token | ates |
Token ID | 689 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
not | +0.128 |
rats | +0.125 |
accidents | +0.123 |
stains | +0.123 |
mess | +0.116 |
Neg logit contributions | |
anna | -0.277 |
ursion | -0.264 |
den | -0.250 |
pad | -0.245 |
bet | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
rats | +0.007 |
adoes | +0.007 |
isk | +0.007 |
stains | +0.007 |
ts | +0.007 |
Neg logit contributions | |
anna | -0.008 |
bet | -0.008 |
ursion | -0.007 |
sur | -0.007 |
Of | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
es | +0.019 |
mice | +0.018 |
stains | +0.018 |
not | +0.017 |
rats | +0.017 |
Neg logit contributions | |
ursion | -0.030 |
anna | -0.028 |
bet | -0.027 |
sur | -0.027 |
ounded | -0.027 |
Token | had |
Token ID | 550 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
es | +0.038 |
rats | +0.037 |
adoes | +0.037 |
ings | +0.036 |
accidents | +0.035 |
Neg logit contributions | |
bet | -0.034 |
ursion | -0.032 |
Of | -0.031 |
sur | -0.031 |
anna | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
es | +0.020 |
rats | +0.018 |
adoes | +0.018 |
ts | +0.017 |
stains | +0.017 |
Neg logit contributions | |
bet | -0.031 |
ursion | -0.030 |
anna | -0.030 |
pleasure | -0.030 |
Of | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
anna | +0.001 |
ursion | +0.001 |
ounded | +0.001 |
sur | +0.001 |
bet | +0.001 |
Neg logit contributions | |
es | -0.000 |
mice | -0.000 |
pictures | -0.000 |
ings | -0.000 |
ados | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +2.24e-04 |
Pos logit contributions | |
rats | +0.032 |
es | +0.031 |
ts | +0.030 |
stains | +0.029 |
adoes | +0.029 |
Neg logit contributions | |
ursion | -0.043 |
bet | -0.043 |
anna | -0.042 |
Sure | -0.041 |
Of | -0.040 |
Token | filled |
Token ID | 5901 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
pleasure | +0.000 |
bet | +0.000 |
Katie | +0.000 |
Sure | +0.000 |
sur | +0.000 |
Neg logit contributions | |
es | -0.000 |
ts | -0.000 |
rats | -0.000 |
bes | -0.000 |
adoes | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
rats | +0.102 |
blood | +0.094 |
ow | +0.093 |
stains | +0.091 |
burns | +0.089 |
Neg logit contributions | |
ya | -0.107 |
Katie | -0.105 |
bet | -0.105 |
very | -0.104 |
Sure | -0.103 |
Token | ch |
Token ID | 442 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
es | +0.018 |
rats | +0.016 |
ts | +0.016 |
isk | +0.015 |
bes | +0.015 |
Neg logit contributions | |
bet | -0.021 |
pleasure | -0.021 |
ursion | -0.020 |
Of | -0.020 |
anna | -0.019 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ursion | +0.010 |
bet | +0.010 |
anna | +0.010 |
pleasure | +0.009 |
sur | +0.009 |
Neg logit contributions | |
es | -0.010 |
not | -0.009 |
rats | -0.009 |
stains | -0.009 |
isk | -0.009 |
Token | ates |
Token ID | 689 |
Feature activation | -7.24e-04 |
Pos logit contributions | |
rats | +0.141 |
not | +0.140 |
stains | +0.133 |
accidents | +0.123 |
mess | +0.121 |
Neg logit contributions | |
anna | -0.263 |
ursion | -0.257 |
pad | -0.240 |
bet | -0.233 |
enna | -0.232 |
Token | and |
Token ID | 290 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
rats | +0.001 |
ts | +0.001 |
isk | +0.001 |
es | +0.001 |
adoes | +0.001 |
Neg logit contributions | |
anna | -0.001 |
ursion | -0.001 |
bet | -0.001 |
pleasure | -0.001 |
ya | -0.001 |
Token | coins |
Token ID | 10796 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
es | +0.003 |
rats | +0.002 |
ts | +0.002 |
stains | +0.002 |
marks | +0.002 |
Neg logit contributions | |
ursion | -0.004 |
bet | -0.004 |
anna | -0.003 |
Sure | -0.003 |
Of | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
rats | +0.003 |
es | +0.002 |
mice | +0.002 |
ts | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ursion | -0.003 |
anna | -0.003 |
bet | -0.003 |
sur | -0.003 |
pleasure | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -7.84e-03 |
Pos logit contributions | |
ursion | +0.009 |
anna | +0.009 |
den | +0.009 |
sur | +0.009 |
fy | +0.009 |
Neg logit contributions | |
es | -0.006 |
pictures | -0.005 |
marks | -0.005 |
mice | -0.005 |
not | -0.005 |
Token | room |
Token ID | 2119 |
Feature activation | -9.07e-03 |
Pos logit contributions | |
es | +0.064 |
rats | +0.059 |
ts | +0.057 |
stains | +0.056 |
marks | +0.055 |
Neg logit contributions | |
ursion | -0.102 |
anna | -0.099 |
bet | -0.099 |
Sure | -0.094 |
Of | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
es | +0.009 |
rats | +0.008 |
ts | +0.008 |
stains | +0.008 |
marks | +0.008 |
Neg logit contributions | |
ursion | -0.018 |
bet | -0.018 |
anna | -0.018 |
Of | -0.017 |
Sure | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | -9.76e-06 |
Pos logit contributions | |
mice | +0.010 |
rats | +0.009 |
not | +0.009 |
es | +0.009 |
puzzles | +0.009 |
Neg logit contributions | |
ursion | -0.019 |
anna | -0.019 |
sur | -0.018 |
ounded | -0.018 |
Of | -0.018 |
Token | dish |
Token ID | 9433 |
Feature activation | -3.66e-02 |
Token | was |
Token ID | 373 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
rats | +0.058 |
ts | +0.056 |
es | +0.056 |
adoes | +0.055 |
isk | +0.055 |
Neg logit contributions | |
ursion | -0.050 |
bet | -0.048 |
Sure | -0.046 |
anna | -0.046 |
Of | -0.043 |
Token | ste |
Token ID | 2876 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
es | +0.009 |
rats | +0.008 |
adoes | +0.007 |
ts | +0.007 |
isk | +0.007 |
Neg logit contributions | |
pleasure | -0.006 |
bet | -0.006 |
ursion | -0.006 |
anna | -0.006 |
sur | -0.006 |
Token | aming |
Token ID | 3723 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
rats | +0.217 |
es | +0.209 |
stains | +0.204 |
snakes | +0.197 |
blood | +0.196 |
Neg logit contributions | |
ursion | -0.204 |
anna | -0.188 |
bet | -0.183 |
Of | -0.170 |
sur | -0.166 |
Token | hot |
Token ID | 3024 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
es | +0.030 |
rats | +0.027 |
ts | +0.026 |
stains | +0.026 |
marks | +0.025 |
Neg logit contributions | |
ursion | -0.046 |
anna | -0.044 |
bet | -0.044 |
Sure | -0.042 |
Of | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
es | +0.049 |
rats | +0.045 |
stains | +0.043 |
marks | +0.043 |
ts | +0.042 |
Neg logit contributions | |
ursion | -0.085 |
bet | -0.082 |
anna | -0.081 |
Of | -0.078 |
Sure | -0.078 |
Token | It |
Token ID | 632 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
not | +0.004 |
es | +0.004 |
mice | +0.004 |
rats | +0.004 |
marks | +0.003 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.009 |
sur | -0.008 |
ounded | -0.008 |
Of | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
es | +0.041 |
rats | +0.037 |
ts | +0.037 |
adoes | +0.036 |
stains | +0.036 |
Neg logit contributions | |
bet | -0.050 |
ursion | -0.049 |
anna | -0.048 |
Sure | -0.046 |
Of | -0.046 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
es | +0.024 |
ts | +0.023 |
rats | +0.023 |
stains | +0.022 |
adoes | +0.022 |
Neg logit contributions | |
ursion | -0.035 |
anna | -0.034 |
bet | -0.034 |
Sure | -0.032 |
Of | -0.032 |
Token | ! |
Token ID | 0 |
Feature activation | -1.82e-03 |
Pos logit contributions | |
ursion | +0.025 |
bet | +0.025 |
anna | +0.025 |
pleasure | +0.024 |
Sure | +0.024 |
Neg logit contributions | |
es | -0.018 |
rats | -0.017 |
ts | -0.017 |
stains | -0.016 |
adoes | -0.016 |
Token | There |
Token ID | 1318 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
es | +0.002 |
mice | +0.002 |
rats | +0.002 |
stains | +0.002 |
puzzles | +0.002 |
Neg logit contributions | |
ursion | -0.003 |
sur | -0.003 |
anna | -0.003 |
bet | -0.003 |
ounded | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
bet | +0.075 |
ursion | +0.074 |
Sure | +0.071 |
Katie | +0.070 |
pleasure | +0.068 |
Neg logit contributions | |
bes | -0.077 |
rats | -0.076 |
adoes | -0.075 |
isk | -0.075 |
ts | -0.075 |
Token | ch |
Token ID | 442 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
es | +0.025 |
adoes | +0.023 |
bes | +0.022 |
ts | +0.022 |
isk | +0.022 |
Neg logit contributions | |
pleasure | -0.033 |
bet | -0.032 |
Of | -0.032 |
anna | -0.032 |
ya | -0.031 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anna | +0.003 |
uster | +0.003 |
ursion | +0.002 |
bet | +0.002 |
ya | +0.002 |
Neg logit contributions | |
not | -0.005 |
es | -0.004 |
stains | -0.004 |
bes | -0.004 |
rats | -0.004 |
Token | ates |
Token ID | 689 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
rats | +0.134 |
not | +0.133 |
stains | +0.129 |
accidents | +0.125 |
mess | +0.120 |
Neg logit contributions | |
anna | -0.248 |
ursion | -0.245 |
pad | -0.231 |
bet | -0.225 |
Sure | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
anna | +0.003 |
pad | +0.003 |
ya | +0.003 |
bet | +0.003 |
Katie | +0.003 |
Neg logit contributions | |
rats | -0.004 |
adoes | -0.004 |
ts | -0.004 |
isk | -0.004 |
blood | -0.004 |
Token | cookies |
Token ID | 14746 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
es | +0.016 |
ts | +0.014 |
ings | +0.014 |
rats | +0.014 |
adoes | +0.013 |
Neg logit contributions | |
bet | -0.026 |
Of | -0.026 |
anna | -0.026 |
Sure | -0.026 |
pleasure | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
rats | +0.069 |
adoes | +0.068 |
ts | +0.067 |
es | +0.065 |
blood | +0.064 |
Neg logit contributions | |
ursion | -0.059 |
anna | -0.058 |
bet | -0.057 |
pad | -0.056 |
Sure | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
es | +0.018 |
ts | +0.017 |
ings | +0.016 |
rats | +0.016 |
adoes | +0.016 |
Neg logit contributions | |
anna | -0.021 |
Of | -0.021 |
bet | -0.021 |
Sure | -0.020 |
pleasure | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
es | +0.030 |
ts | +0.027 |
stains | +0.027 |
rats | +0.026 |
marks | +0.026 |
Neg logit contributions | |
ursion | -0.039 |
bet | -0.038 |
anna | -0.037 |
sur | -0.037 |
Sure | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-04 |
Pos logit contributions | |
es | +0.047 |
ts | +0.043 |
rats | +0.042 |
marks | +0.042 |
stains | +0.042 |
Neg logit contributions | |
ursion | -0.042 |
bet | -0.041 |
anna | -0.040 |
Sure | -0.039 |
Of | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
es | +0.000 |
marks | +0.000 |
stains | +0.000 |
rats | +0.000 |
ings | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Of | -0.000 |
Sure | -0.000 |
Token | skin |
Token ID | 4168 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
es | +0.031 |
ts | +0.027 |
stains | +0.026 |
rats | +0.026 |
adoes | +0.025 |
Neg logit contributions | |
bet | -0.034 |
pleasure | -0.033 |
ursion | -0.033 |
anna | -0.031 |
sur | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
rats | +0.038 |
mice | +0.037 |
injuries | +0.037 |
adoes | +0.036 |
es | +0.036 |
Neg logit contributions | |
anna | -0.027 |
ursion | -0.023 |
bet | -0.023 |
So | -0.022 |
shirt | -0.021 |
Token | wrink |
Token ID | 34866 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
es | +0.018 |
rats | +0.016 |
adoes | +0.016 |
ts | +0.015 |
marks | +0.015 |
Neg logit contributions | |
anna | -0.014 |
ursion | -0.013 |
pleasure | -0.013 |
bet | -0.013 |
sur | -0.012 |
Token | ly |
Token ID | 306 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
es | +0.222 |
rats | +0.221 |
bes | +0.209 |
snakes | +0.208 |
ts | +0.207 |
Neg logit contributions | |
anna | -0.168 |
ursion | -0.162 |
bet | -0.146 |
ya | -0.141 |
sur | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
anna | +0.038 |
bet | +0.037 |
pad | +0.037 |
ursion | +0.036 |
pleasure | +0.035 |
Neg logit contributions | |
ts | -0.035 |
isk | -0.034 |
es | -0.033 |
rats | -0.032 |
bes | -0.030 |
Token | The |
Token ID | 383 |
Feature activation | -4.01e-04 |
Pos logit contributions | |
es | +0.022 |
rats | +0.021 |
stains | +0.020 |
ts | +0.020 |
mice | +0.020 |
Neg logit contributions | |
ursion | -0.021 |
bet | -0.020 |
anna | -0.019 |
sur | -0.018 |
Of | -0.018 |
Token | frog |
Token ID | 21264 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
es | +0.001 |
ts | +0.001 |
bes | +0.001 |
rats | +0.001 |
isk | +0.001 |
Neg logit contributions | |
bet | -0.001 |
ursion | -0.001 |
sur | -0.001 |
Of | -0.001 |
pleasure | -0.001 |
Token | lived |
Token ID | 5615 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
adoes | +0.009 |
rats | +0.009 |
es | +0.009 |
accidents | +0.009 |
stains | +0.009 |
Neg logit contributions | |
anna | -0.007 |
bet | -0.007 |
ursion | -0.007 |
Of | -0.006 |
Sure | -0.006 |
Token | not |
Token ID | 407 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
es | +0.006 |
rats | +0.006 |
ts | +0.005 |
stains | +0.005 |
mice | +0.005 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.008 |
anna | -0.008 |
Of | -0.007 |
pleasure | -0.007 |
Token | eat |
Token ID | 4483 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
es | +0.113 |
ts | +0.102 |
rats | +0.101 |
stains | +0.097 |
marks | +0.095 |
Neg logit contributions | |
ursion | -0.100 |
bet | -0.098 |
anna | -0.096 |
Of | -0.091 |
sur | -0.088 |
Token | too |
Token ID | 1165 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
es | +0.081 |
bes | +0.068 |
isk | +0.067 |
stains | +0.067 |
adoes | +0.066 |
Neg logit contributions | |
bet | -0.126 |
anna | -0.126 |
pleasure | -0.123 |
sur | -0.118 |
Of | -0.118 |
Token | many |
Token ID | 867 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
es | +0.075 |
ts | +0.069 |
bes | +0.069 |
adoes | +0.069 |
isk | +0.069 |
Neg logit contributions | |
ursion | -0.053 |
bet | -0.050 |
anna | -0.048 |
Sure | -0.045 |
pleasure | -0.045 |
Token | ch |
Token ID | 442 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
ts | +0.004 |
stains | +0.004 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.013 |
bet | -0.013 |
anna | -0.013 |
Of | -0.012 |
Sure | -0.012 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
anna | +0.006 |
bet | +0.006 |
ursion | +0.006 |
sur | +0.005 |
pleasure | +0.005 |
Neg logit contributions | |
es | -0.005 |
stains | -0.005 |
not | -0.005 |
rats | -0.005 |
bes | -0.005 |
Token | ates |
Token ID | 689 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
stains | +0.118 |
rats | +0.116 |
not | +0.109 |
accidents | +0.109 |
mice | +0.104 |
Neg logit contributions | |
anna | -0.268 |
ursion | -0.267 |
bet | -0.249 |
pad | -0.242 |
Sure | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
es | +0.004 |
rats | +0.004 |
ts | +0.004 |
stains | +0.004 |
adoes | +0.004 |
Neg logit contributions | |
ursion | -0.007 |
anna | -0.006 |
bet | -0.006 |
pleasure | -0.006 |
Of | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
es | +0.023 |
rats | +0.021 |
ts | +0.020 |
stains | +0.020 |
marks | +0.020 |
Neg logit contributions | |
ursion | -0.034 |
bet | -0.033 |
anna | -0.033 |
Sure | -0.031 |
Of | -0.031 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
es | +0.045 |
rats | +0.038 |
ts | +0.038 |
stains | +0.038 |
adoes | +0.036 |
Neg logit contributions | |
bet | -0.058 |
ursion | -0.058 |
anna | -0.058 |
pleasure | -0.056 |
Sure | -0.055 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
ursion | +0.033 |
bet | +0.032 |
anna | +0.032 |
Of | +0.030 |
Sure | +0.030 |
Neg logit contributions | |
es | -0.031 |
rats | -0.029 |
ts | -0.028 |
stains | -0.028 |
marks | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
anna | +0.033 |
Of | +0.031 |
pleasure | +0.030 |
� | +0.030 |
bet | +0.029 |
Neg logit contributions | |
es | -0.040 |
ts | -0.040 |
isk | -0.040 |
icer | -0.040 |
bes | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
es | +0.047 |
ts | +0.045 |
bes | +0.045 |
ings | +0.044 |
arts | +0.044 |
Neg logit contributions | |
Of | -0.035 |
bet | -0.035 |
ursion | -0.034 |
Sure | -0.033 |
anna | -0.033 |
Token | injury |
Token ID | 5095 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
es | +0.003 |
ts | +0.002 |
rats | +0.002 |
mice | +0.002 |
isk | +0.002 |
Neg logit contributions | |
anna | -0.003 |
ursion | -0.003 |
bet | -0.003 |
pleasure | -0.003 |
Of | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
es | +0.030 |
rats | +0.030 |
ts | +0.029 |
mice | +0.028 |
stains | +0.027 |
Neg logit contributions | |
ursion | -0.041 |
anna | -0.040 |
bet | -0.040 |
Of | -0.038 |
Sure | -0.037 |
Token | too |
Token ID | 1165 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
es | +0.006 |
ts | +0.005 |
rats | +0.005 |
marks | +0.005 |
bes | +0.005 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.009 |
bet | -0.008 |
Of | -0.008 |
pleasure | -0.008 |
Token | severe |
Token ID | 6049 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
es | +0.056 |
ts | +0.051 |
rats | +0.049 |
stains | +0.047 |
marks | +0.046 |
Neg logit contributions | |
ursion | -0.076 |
anna | -0.072 |
bet | -0.070 |
Of | -0.068 |
Sure | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ts | +0.189 |
stains | +0.189 |
es | +0.186 |
adoes | +0.184 |
icer | +0.180 |
Neg logit contributions | |
anna | -0.182 |
bet | -0.173 |
ursion | -0.172 |
Sure | -0.163 |
pleasure | -0.154 |
Token | she |
Token ID | 673 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
es | +0.016 |
rats | +0.014 |
ts | +0.014 |
stains | +0.014 |
marks | +0.014 |
Neg logit contributions | |
ursion | -0.024 |
bet | -0.023 |
anna | -0.023 |
Of | -0.022 |
Sure | -0.022 |
Token | would |
Token ID | 561 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ursion | +0.013 |
anna | +0.012 |
bet | +0.012 |
Of | +0.011 |
Sure | +0.011 |
Neg logit contributions | |
es | -0.016 |
rats | -0.015 |
ts | -0.015 |
adoes | -0.015 |
stains | -0.014 |
Token | never |
Token ID | 1239 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
bet | +0.039 |
ursion | +0.039 |
anna | +0.038 |
Of | +0.037 |
pleasure | +0.036 |
Neg logit contributions | |
es | -0.036 |
rats | -0.032 |
ts | -0.031 |
mice | -0.030 |
puzzles | -0.029 |
Token | be |
Token ID | 307 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
ursion | +0.005 |
anna | +0.005 |
bet | +0.005 |
Sure | +0.005 |
Of | +0.005 |
Neg logit contributions | |
es | -0.004 |
rats | -0.004 |
marks | -0.004 |
stains | -0.004 |
not | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
anna | +0.008 |
den | +0.008 |
sur | +0.008 |
ursion | +0.008 |
bet | +0.007 |
Neg logit contributions | |
not | -0.005 |
adoes | -0.005 |
es | -0.005 |
mice | -0.004 |
pictures | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -5.58e-04 |
Pos logit contributions | |
es | +0.039 |
rats | +0.038 |
ts | +0.037 |
adoes | +0.037 |
puzzles | +0.036 |
Neg logit contributions | |
bet | -0.043 |
anna | -0.041 |
Of | -0.040 |
ursion | -0.040 |
Sure | -0.039 |
Token | sweet |
Token ID | 6029 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
adoes | +0.001 |
bes | +0.001 |
Neg logit contributions | |
pleasure | -0.001 |
bet | -0.001 |
anna | -0.001 |
Shall | -0.001 |
ursion | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
es | +0.048 |
rats | +0.043 |
ts | +0.042 |
stains | +0.042 |
marks | +0.041 |
Neg logit contributions | |
ursion | -0.080 |
bet | -0.078 |
anna | -0.078 |
Of | -0.074 |
Sure | -0.074 |
Token | ch |
Token ID | 442 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
es | +0.016 |
rats | +0.015 |
ts | +0.015 |
stains | +0.014 |
marks | +0.014 |
Neg logit contributions | |
ursion | -0.020 |
bet | -0.020 |
anna | -0.019 |
Of | -0.019 |
Sure | -0.019 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
anna | +0.015 |
ursion | +0.015 |
bet | +0.014 |
pleasure | +0.013 |
sur | +0.013 |
Neg logit contributions | |
es | -0.016 |
puzzles | -0.015 |
rats | -0.015 |
not | -0.015 |
ts | -0.014 |
Token | at |
Token ID | 265 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
rats | +0.125 |
not | +0.119 |
stains | +0.115 |
puzzles | +0.114 |
mice | +0.114 |
Neg logit contributions | |
anna | -0.258 |
ursion | -0.256 |
bet | -0.240 |
pad | -0.234 |
Sure | -0.234 |
Token | y |
Token ID | 88 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
rats | +0.057 |
es | +0.055 |
adoes | +0.054 |
ts | +0.054 |
puzzles | +0.052 |
Neg logit contributions | |
anna | -0.071 |
ursion | -0.067 |
bet | -0.066 |
pleasure | -0.065 |
Sure | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +7.36e-04 |
Pos logit contributions | |
es | +0.026 |
rats | +0.025 |
ts | +0.024 |
stains | +0.023 |
marks | +0.023 |
Neg logit contributions | |
ursion | -0.037 |
anna | -0.037 |
bet | -0.036 |
pleasure | -0.035 |
Sure | -0.035 |
Token | warm |
Token ID | 5814 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ursion | +0.001 |
bet | +0.001 |
anna | +0.001 |
Of | +0.001 |
Sure | +0.001 |
Neg logit contributions | |
es | -0.001 |
rats | -0.001 |
ts | -0.001 |
stains | -0.001 |
marks | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
es | +0.016 |
rats | +0.015 |
ts | +0.015 |
stains | +0.014 |
marks | +0.014 |
Neg logit contributions | |
ursion | -0.026 |
anna | -0.025 |
bet | -0.025 |
Sure | -0.024 |
Of | -0.024 |
Token | nice |
Token ID | 3621 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
es | +0.012 |
rats | +0.011 |
stains | +0.011 |
ts | +0.010 |
marks | +0.010 |
Neg logit contributions | |
ursion | -0.016 |
anna | -0.015 |
bet | -0.015 |
Sure | -0.015 |
Of | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
es | +0.035 |
rats | +0.033 |
ts | +0.033 |
stains | +0.031 |
mice | +0.030 |
Neg logit contributions | |
ursion | -0.055 |
bet | -0.054 |
anna | -0.053 |
Sure | -0.051 |
pleasure | -0.050 |
Token | but |
Token ID | 475 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
es | +0.049 |
not | +0.049 |
rats | +0.048 |
stains | +0.048 |
marks | +0.047 |
Neg logit contributions | |
ursion | -0.038 |
anna | -0.035 |
bet | -0.033 |
sur | -0.031 |
Sure | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ursion | +0.086 |
bet | +0.085 |
Of | +0.082 |
Sure | +0.081 |
anna | +0.080 |
Neg logit contributions | |
es | -0.077 |
rats | -0.070 |
ts | -0.069 |
stains | -0.068 |
mice | -0.068 |
Token | was |
Token ID | 373 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
es | +0.048 |
adoes | +0.047 |
mice | +0.046 |
rats | +0.046 |
ados | +0.045 |
Neg logit contributions | |
bet | -0.043 |
ursion | -0.039 |
Of | -0.039 |
Sure | -0.038 |
sur | -0.037 |
Token | wrink |
Token ID | 34866 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
es | +0.017 |
ts | +0.014 |
adoes | +0.014 |
bes | +0.014 |
ops | +0.014 |
Neg logit contributions | |
bet | -0.018 |
ursion | -0.018 |
pleasure | -0.018 |
pad | -0.017 |
Of | -0.017 |
Token | led |
Token ID | 992 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
rats | +0.191 |
es | +0.191 |
puzzles | +0.185 |
isk | +0.183 |
ts | +0.181 |
Neg logit contributions | |
anna | -0.187 |
ursion | -0.184 |
bet | -0.171 |
ya | -0.160 |
ounded | -0.159 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
es | +0.019 |
ts | +0.019 |
bes | +0.018 |
rats | +0.017 |
ics | +0.017 |
Neg logit contributions | |
bet | -0.020 |
ursion | -0.019 |
anna | -0.019 |
Of | -0.019 |
pad | -0.019 |
Token | dirty |
Token ID | 11841 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
es | +0.021 |
rats | +0.019 |
ts | +0.018 |
marks | +0.018 |
adoes | +0.017 |
Neg logit contributions | |
ursion | -0.029 |
bet | -0.028 |
anna | -0.027 |
Of | -0.027 |
Sure | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
es | +0.067 |
ts | +0.066 |
isk | +0.065 |
rats | +0.064 |
lich | +0.061 |
Neg logit contributions | |
bet | -0.074 |
anna | -0.074 |
ursion | -0.074 |
sur | -0.068 |
pad | -0.068 |
Token | She |
Token ID | 1375 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
es | +0.016 |
rats | +0.015 |
stains | +0.015 |
marks | +0.015 |
not | +0.014 |
Neg logit contributions | |
ursion | -0.021 |
anna | -0.020 |
bet | -0.019 |
sur | -0.019 |
ya | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e-03 |
Pos logit contributions | |
es | +0.022 |
stains | +0.018 |
marks | +0.017 |
not | +0.017 |
rats | +0.017 |
Neg logit contributions | |
ursion | -0.053 |
bet | -0.051 |
anna | -0.051 |
pleasure | -0.049 |
Of | -0.049 |
Token | dream |
Token ID | 4320 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
es | +0.008 |
rats | +0.007 |
stains | +0.007 |
ts | +0.007 |
marks | +0.007 |
Neg logit contributions | |
ursion | -0.006 |
bet | -0.006 |
anna | -0.006 |
Sure | -0.005 |
Of | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
es | +0.039 |
rats | +0.036 |
ts | +0.035 |
stains | +0.035 |
marks | +0.034 |
Neg logit contributions | |
ursion | -0.056 |
bet | -0.054 |
anna | -0.054 |
Of | -0.051 |
Sure | -0.051 |
Token | horses |
Token ID | 14260 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
es | +0.040 |
adoes | +0.033 |
stains | +0.033 |
bes | +0.033 |
isk | +0.033 |
Neg logit contributions | |
bet | -0.057 |
pleasure | -0.056 |
sur | -0.054 |
ursion | -0.053 |
Sure | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -7.10e-03 |
Pos logit contributions | |
ursion | +0.018 |
bet | +0.018 |
anna | +0.018 |
sur | +0.017 |
Sure | +0.017 |
Neg logit contributions | |
es | -0.012 |
rats | -0.012 |
stains | -0.012 |
ts | -0.011 |
adoes | -0.011 |
Token | ste |
Token ID | 2876 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
es | +0.007 |
stains | +0.006 |
rats | +0.006 |
ts | +0.006 |
marks | +0.006 |
Neg logit contributions | |
bet | -0.013 |
ursion | -0.013 |
anna | -0.013 |
pleasure | -0.013 |
Sure | -0.013 |
Token | aks |
Token ID | 4730 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
rats | +0.198 |
stains | +0.193 |
not | +0.192 |
accidents | +0.185 |
es | +0.184 |
Neg logit contributions | |
anna | -0.182 |
ursion | -0.181 |
bet | -0.168 |
sur | -0.154 |
ya | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
rats | +0.017 |
es | +0.017 |
stains | +0.017 |
ts | +0.017 |
not | +0.016 |
Neg logit contributions | |
anna | -0.024 |
bet | -0.023 |
ursion | -0.022 |
sur | -0.022 |
Sure | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
es | +0.011 |
mice | +0.011 |
rats | +0.011 |
not | +0.010 |
stains | +0.010 |
Neg logit contributions | |
ursion | -0.026 |
anna | -0.025 |
ounded | -0.024 |
sur | -0.024 |
ya | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
es | +0.021 |
adoes | +0.020 |
rats | +0.020 |
accidents | +0.020 |
stains | +0.019 |
Neg logit contributions | |
bet | -0.020 |
ursion | -0.019 |
anna | -0.018 |
sur | -0.017 |
pleasure | -0.017 |
Token | good |
Token ID | 922 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
es | +0.058 |
stains | +0.053 |
rats | +0.052 |
marks | +0.051 |
ts | +0.051 |
Neg logit contributions | |
pleasure | -0.046 |
bet | -0.045 |
anna | -0.045 |
ursion | -0.045 |
sur | -0.042 |
Token | pride |
Token ID | 11293 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
es | +0.012 |
rats | +0.011 |
stains | +0.011 |
ts | +0.011 |
marks | +0.011 |
Neg logit contributions | |
ursion | -0.007 |
bet | -0.007 |
pleasure | -0.007 |
anna | -0.007 |
Of | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ursion | +0.030 |
anna | +0.029 |
bet | +0.029 |
Of | +0.027 |
Sure | +0.027 |
Neg logit contributions | |
es | -0.019 |
rats | -0.017 |
ts | -0.017 |
stains | -0.017 |
marks | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ursion | +0.067 |
anna | +0.065 |
bet | +0.064 |
Of | +0.061 |
Sure | +0.060 |
Neg logit contributions | |
es | -0.044 |
rats | -0.040 |
ts | -0.039 |
marks | -0.038 |
not | -0.038 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ursion | +0.028 |
anna | +0.026 |
bet | +0.026 |
Sure | +0.025 |
Of | +0.025 |
Neg logit contributions | |
es | -0.031 |
rats | -0.029 |
ts | -0.029 |
stains | -0.028 |
marks | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ursion | +0.069 |
bet | +0.068 |
anna | +0.068 |
Sure | +0.066 |
pleasure | +0.066 |
Neg logit contributions | |
es | -0.035 |
rats | -0.032 |
stains | -0.030 |
ts | -0.030 |
marks | -0.029 |
Token | ste |
Token ID | 2876 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
es | +0.043 |
rats | +0.041 |
ts | +0.039 |
stains | +0.039 |
mice | +0.037 |
Neg logit contributions | |
ursion | -0.050 |
bet | -0.049 |
anna | -0.048 |
Sure | -0.045 |
Of | -0.045 |
Token | aming |
Token ID | 3723 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
rats | +0.191 |
es | +0.185 |
stains | +0.179 |
not | +0.171 |
snakes | +0.169 |
Neg logit contributions | |
ursion | -0.208 |
anna | -0.196 |
bet | -0.196 |
Of | -0.180 |
sur | -0.179 |
Token | away |
Token ID | 1497 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
es | +0.019 |
marks | +0.017 |
rats | +0.017 |
stains | +0.017 |
ts | +0.017 |
Neg logit contributions | |
ursion | -0.033 |
bet | -0.031 |
anna | -0.031 |
Of | -0.030 |
Sure | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
es | +0.021 |
rats | +0.020 |
ts | +0.019 |
stains | +0.019 |
isk | +0.018 |
Neg logit contributions | |
bet | -0.031 |
ursion | -0.030 |
anna | -0.030 |
pleasure | -0.029 |
sur | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
es | +0.017 |
rats | +0.015 |
isk | +0.015 |
ts | +0.014 |
stains | +0.014 |
Neg logit contributions | |
bet | -0.025 |
pleasure | -0.025 |
Sure | -0.024 |
ursion | -0.024 |
anna | -0.023 |
Token | stove |
Token ID | 27635 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ursion | +0.031 |
bet | +0.030 |
anna | +0.029 |
Of | +0.029 |
Sure | +0.028 |
Neg logit contributions | |
es | -0.019 |
rats | -0.018 |
stains | -0.018 |
marks | -0.017 |
ts | -0.017 |
Token | king |
Token ID | 5822 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
stains | +0.001 |
ts | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.002 |
bet | -0.002 |
anna | -0.002 |
Of | -0.002 |
Sure | -0.002 |
Token | ate |
Token ID | 15063 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
rats | +0.045 |
stains | +0.044 |
adoes | +0.043 |
ts | +0.043 |
es | +0.043 |
Neg logit contributions | |
anna | -0.050 |
ursion | -0.050 |
bet | -0.049 |
Of | -0.046 |
sur | -0.045 |
Token | too |
Token ID | 1165 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
es | +0.082 |
bes | +0.076 |
adoes | +0.074 |
isk | +0.073 |
iders | +0.071 |
Neg logit contributions | |
bet | -0.109 |
pleasure | -0.104 |
Of | -0.104 |
Sure | -0.104 |
sur | -0.100 |
Token | many |
Token ID | 867 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
es | +0.048 |
adoes | +0.047 |
stains | +0.046 |
rats | +0.045 |
ts | +0.044 |
Neg logit contributions | |
ursion | -0.039 |
bet | -0.038 |
anna | -0.037 |
Sure | -0.037 |
pleasure | -0.037 |
Token | ch |
Token ID | 442 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
anna | +0.007 |
bet | +0.007 |
ursion | +0.007 |
Of | +0.007 |
pleasure | +0.007 |
Neg logit contributions | |
es | -0.004 |
adoes | -0.004 |
stains | -0.004 |
rats | -0.003 |
not | -0.003 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
anna | +0.015 |
ursion | +0.014 |
bet | +0.014 |
sur | +0.013 |
uster | +0.012 |
Neg logit contributions | |
not | -0.015 |
es | -0.014 |
stains | -0.014 |
bes | -0.014 |
rats | -0.014 |
Token | ates |
Token ID | 689 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
rats | +0.127 |
not | +0.122 |
stains | +0.121 |
accidents | +0.120 |
mess | +0.112 |
Neg logit contributions | |
anna | -0.255 |
ursion | -0.252 |
pad | -0.231 |
bet | -0.229 |
Sure | -0.228 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ursion | +0.007 |
anna | +0.007 |
bet | +0.007 |
pleasure | +0.007 |
Sure | +0.007 |
Neg logit contributions | |
rats | -0.007 |
adoes | -0.007 |
ts | -0.007 |
stains | -0.007 |
isk | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
es | +0.017 |
rats | +0.016 |
stains | +0.016 |
ts | +0.016 |
marks | +0.015 |
Neg logit contributions | |
ursion | -0.018 |
bet | -0.018 |
anna | -0.017 |
Sure | -0.017 |
Of | -0.017 |
Token | tum |
Token ID | 11814 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
es | +0.035 |
stains | +0.030 |
rats | +0.029 |
adoes | +0.029 |
ts | +0.029 |
Neg logit contributions | |
anna | -0.048 |
pleasure | -0.048 |
bet | -0.048 |
ursion | -0.046 |
Sure | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
es | +0.167 |
rats | +0.165 |
ts | +0.161 |
mice | +0.158 |
stains | +0.156 |
Neg logit contributions | |
ursion | -0.118 |
anna | -0.113 |
bet | -0.103 |
Of | -0.101 |
Sure | -0.100 |
Token | so |
Token ID | 523 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
ursion | +0.000 |
anna | +0.000 |
bet | +0.000 |
Sure | +0.000 |
pleasure | +0.000 |
Neg logit contributions | |
es | -0.000 |
ts | -0.000 |
not | -0.000 |
rats | -0.000 |
stains | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ursion | +0.091 |
Sure | +0.084 |
anna | +0.084 |
bet | +0.084 |
uster | +0.083 |
Neg logit contributions | |
not | -0.069 |
es | -0.057 |
rats | -0.054 |
ts | -0.053 |
all | -0.053 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
es | +0.046 |
rats | +0.041 |
stains | +0.041 |
ts | +0.041 |
marks | +0.041 |
Neg logit contributions | |
ursion | -0.051 |
bet | -0.048 |
anna | -0.048 |
Sure | -0.046 |
Of | -0.046 |
Token | 't |
Token ID | 470 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
ursion | +0.062 |
bet | +0.060 |
anna | +0.060 |
Sure | +0.057 |
Of | +0.057 |
Neg logit contributions | |
es | -0.018 |
rats | -0.016 |
ts | -0.015 |
stains | -0.014 |
mice | -0.013 |
Token | get |
Token ID | 651 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
es | +0.041 |
not | +0.039 |
rats | +0.038 |
marks | +0.038 |
stains | +0.038 |
Neg logit contributions | |
ursion | -0.065 |
anna | -0.061 |
bet | -0.061 |
Sure | -0.061 |
Of | -0.059 |
Token | wrink |
Token ID | 34866 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
es | +0.003 |
rats | +0.003 |
stains | +0.003 |
ts | +0.003 |
marks | +0.003 |
Neg logit contributions | |
ursion | -0.005 |
bet | -0.005 |
anna | -0.005 |
Sure | -0.005 |
Of | -0.005 |
Token | led |
Token ID | 992 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
es | +0.227 |
rats | +0.216 |
not | +0.206 |
ts | +0.204 |
isk | +0.204 |
Neg logit contributions | |
anna | -0.165 |
ursion | -0.160 |
bet | -0.153 |
sur | -0.142 |
ya | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
es | +0.023 |
ts | +0.020 |
rats | +0.020 |
stains | +0.019 |
marks | +0.019 |
Neg logit contributions | |
bet | -0.033 |
ursion | -0.033 |
anna | -0.032 |
pleasure | -0.031 |
Of | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
ursion | +0.036 |
ounded | +0.034 |
bet | +0.034 |
anna | +0.033 |
sur | +0.032 |
Neg logit contributions | |
es | -0.025 |
not | -0.024 |
mice | -0.023 |
rats | -0.022 |
adoes | -0.021 |
Token | took |
Token ID | 1718 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ursion | +0.003 |
bet | +0.003 |
anna | +0.003 |
Sure | +0.003 |
Of | +0.003 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
stains | -0.002 |
ts | -0.002 |
marks | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
ursion | +0.044 |
anna | +0.043 |
bet | +0.043 |
Of | +0.041 |
Sure | +0.041 |
Neg logit contributions | |
es | -0.018 |
rats | -0.016 |
ts | -0.015 |
stains | -0.015 |
marks | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
es | +0.051 |
rats | +0.048 |
ts | +0.046 |
stains | +0.045 |
marks | +0.044 |
Neg logit contributions | |
ursion | -0.086 |
anna | -0.083 |
bet | -0.083 |
Sure | -0.079 |
Of | -0.079 |
Token | cup |
Token ID | 6508 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
es | +0.032 |
rats | +0.029 |
ts | +0.028 |
stains | +0.028 |
marks | +0.028 |
Neg logit contributions | |
ursion | -0.043 |
bet | -0.042 |
anna | -0.041 |
Of | -0.039 |
Sure | -0.039 |
Token | cakes |
Token ID | 37263 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
es | +0.086 |
rats | +0.085 |
ts | +0.083 |
mice | +0.078 |
adoes | +0.078 |
Neg logit contributions | |
ursion | -0.111 |
anna | -0.109 |
bet | -0.104 |
Sure | -0.103 |
Of | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
es | +0.064 |
rats | +0.060 |
ts | +0.057 |
stains | +0.056 |
marks | +0.055 |
Neg logit contributions | |
ursion | -0.093 |
anna | -0.090 |
bet | -0.090 |
Of | -0.086 |
Sure | -0.086 |
Token | ch |
Token ID | 442 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
es | +0.004 |
rats | +0.003 |
ts | +0.003 |
stains | +0.003 |
not | +0.003 |
Neg logit contributions | |
ursion | -0.006 |
bet | -0.005 |
anna | -0.005 |
Sure | -0.005 |
ounded | -0.005 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ursion | +0.014 |
anna | +0.013 |
bet | +0.013 |
sur | +0.012 |
Of | +0.012 |
Neg logit contributions | |
es | -0.010 |
rats | -0.009 |
stains | -0.009 |
marks | -0.009 |
ts | -0.009 |
Token | ates |
Token ID | 689 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
rats | +0.111 |
not | +0.107 |
stains | +0.107 |
es | +0.101 |
accidents | +0.101 |
Neg logit contributions | |
anna | -0.267 |
ursion | -0.262 |
bet | -0.247 |
Sure | -0.240 |
pad | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-04 |
Pos logit contributions | |
es | +0.006 |
rats | +0.006 |
ts | +0.005 |
stains | +0.005 |
mice | +0.005 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.009 |
bet | -0.009 |
Sure | -0.008 |
Of | -0.008 |
Token | |
Token ID | 220 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
not | +0.000 |
es | +0.000 |
rats | +0.000 |
bones | +0.000 |
mice | +0.000 |
Neg logit contributions | |
ursion | -0.001 |
anna | -0.001 |
bet | -0.001 |
ounded | -0.001 |
ya | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.49e-05 |
Pos logit contributions | |
ursion | +0.045 |
bet | +0.043 |
anna | +0.042 |
Of | +0.040 |
Sure | +0.040 |
Neg logit contributions | |
es | -0.045 |
rats | -0.041 |
ts | -0.040 |
stains | -0.040 |
marks | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
ursion | +0.000 |
bet | +0.000 |
anna | +0.000 |
pleasure | +0.000 |
ounded | +0.000 |
Neg logit contributions | |
es | -0.000 |
not | -0.000 |
isk | -0.000 |
oni | -0.000 |
rats | -0.000 |
Token | unes |
Token ID | 4015 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
ts | +0.048 |
rats | +0.047 |
mice | +0.046 |
bes | +0.046 |
es | +0.046 |
Neg logit contributions | |
ursion | -0.052 |
anna | -0.051 |
bet | -0.050 |
pleasure | -0.047 |
Sure | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
es | +0.067 |
rats | +0.064 |
ts | +0.062 |
mice | +0.061 |
adoes | +0.060 |
Neg logit contributions | |
ursion | -0.102 |
anna | -0.098 |
bet | -0.097 |
Of | -0.091 |
sur | -0.090 |
Token | They |
Token ID | 1119 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
es | +0.010 |
rats | +0.010 |
mice | +0.009 |
not | +0.009 |
stains | +0.009 |
Neg logit contributions | |
ursion | -0.010 |
anna | -0.009 |
bet | -0.009 |
sur | -0.009 |
ounded | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
es | +0.031 |
adoes | +0.029 |
rats | +0.029 |
bes | +0.028 |
ts | +0.028 |
Neg logit contributions | |
bet | -0.033 |
ursion | -0.032 |
anna | -0.030 |
Of | -0.029 |
pleasure | -0.029 |
Token | too |
Token ID | 1165 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
es | +0.052 |
bes | +0.042 |
adoes | +0.041 |
ts | +0.041 |
isk | +0.040 |
Neg logit contributions | |
bet | -0.068 |
pleasure | -0.067 |
anna | -0.065 |
ursion | -0.064 |
Of | -0.063 |
Token | wrink |
Token ID | 34866 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
es | +0.045 |
isk | +0.040 |
ts | +0.039 |
bes | +0.038 |
adoes | +0.038 |
Neg logit contributions | |
anna | -0.045 |
ursion | -0.044 |
bet | -0.044 |
pleasure | -0.041 |
Of | -0.040 |
Token | ly |
Token ID | 306 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
rats | +0.177 |
es | +0.174 |
ts | +0.167 |
bes | +0.164 |
isk | +0.164 |
Neg logit contributions | |
anna | -0.199 |
ursion | -0.195 |
bet | -0.187 |
ounded | -0.173 |
ya | -0.172 |
Token | and |
Token ID | 290 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
anna | +0.073 |
bet | +0.071 |
ursion | +0.069 |
pad | +0.064 |
pleasure | +0.063 |
Neg logit contributions | |
es | -0.057 |
ts | -0.055 |
isk | -0.055 |
rats | -0.053 |
bes | -0.050 |
Token | sour |
Token ID | 11348 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
es | +0.010 |
rats | +0.009 |
ts | +0.008 |
adoes | +0.008 |
marks | +0.008 |
Neg logit contributions | |
ursion | -0.014 |
bet | -0.014 |
anna | -0.014 |
Of | -0.013 |
pleasure | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
es | +0.089 |
ts | +0.087 |
rats | +0.083 |
isk | +0.082 |
bes | +0.078 |
Neg logit contributions | |
anna | -0.119 |
ursion | -0.118 |
bet | -0.117 |
Of | -0.109 |
sur | -0.108 |
Token | cakes |
Token ID | 30849 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
es | +0.105 |
rats | +0.091 |
stains | +0.087 |
ts | +0.086 |
adoes | +0.086 |
Neg logit contributions | |
ursion | -0.140 |
anna | -0.139 |
bet | -0.139 |
pleasure | -0.135 |
Of | -0.132 |
Token | iled |
Token ID | 3902 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
bet | +0.028 |
anna | +0.027 |
ursion | +0.026 |
pleasure | +0.025 |
Sure | +0.025 |
Neg logit contributions | |
es | -0.026 |
ts | -0.023 |
stains | -0.022 |
oni | -0.022 |
arts | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -8.15e-04 |
Pos logit contributions | |
es | +0.067 |
rats | +0.063 |
ts | +0.060 |
bes | +0.058 |
isk | +0.058 |
Neg logit contributions | |
anna | -0.090 |
bet | -0.089 |
ursion | -0.087 |
sur | -0.081 |
pleasure | -0.081 |
Token | po |
Token ID | 745 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.001 |
bet | -0.001 |
anna | -0.001 |
Sure | -0.001 |
Of | -0.001 |
Token | ached |
Token ID | 2317 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
es | +0.019 |
rats | +0.017 |
stains | +0.017 |
ts | +0.017 |
marks | +0.017 |
Neg logit contributions | |
ursion | -0.016 |
bet | -0.016 |
anna | -0.015 |
Sure | -0.014 |
Of | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
anna | +0.079 |
ursion | +0.078 |
bet | +0.077 |
pleasure | +0.072 |
Sure | +0.072 |
Neg logit contributions | |
es | -0.058 |
rats | -0.056 |
ts | -0.055 |
stains | -0.052 |
bes | -0.051 |
Token | ste |
Token ID | 2876 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ursion | +0.002 |
bet | +0.002 |
anna | +0.002 |
Sure | +0.002 |
Of | +0.002 |
Neg logit contributions | |
es | -0.002 |
rats | -0.001 |
ts | -0.001 |
stains | -0.001 |
marks | -0.001 |
Token | amed |
Token ID | 2434 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
rats | +0.172 |
es | +0.167 |
stains | +0.162 |
not | +0.155 |
puzzles | +0.154 |
Neg logit contributions | |
ursion | -0.214 |
anna | -0.207 |
bet | -0.202 |
Of | -0.187 |
pleasure | -0.186 |
Token | and |
Token ID | 290 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
es | +0.009 |
rats | +0.008 |
stains | +0.008 |
ts | +0.008 |
marks | +0.007 |
Neg logit contributions | |
anna | -0.013 |
ursion | -0.013 |
bet | -0.013 |
Of | -0.012 |
pleasure | -0.012 |
Token | microw |
Token ID | 23479 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ursion | +0.009 |
anna | +0.008 |
bet | +0.008 |
ounded | +0.008 |
Of | +0.008 |
Neg logit contributions | |
es | -0.007 |
not | -0.006 |
rats | -0.006 |
ts | -0.006 |
stains | -0.006 |
Token | aved |
Token ID | 9586 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ursion | +0.027 |
Of | +0.027 |
adventurer | +0.026 |
ya | +0.026 |
pleasure | +0.026 |
Neg logit contributions | |
es | -0.027 |
isk | -0.023 |
stains | -0.022 |
marks | -0.021 |
arts | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
ursion | +0.058 |
bet | +0.056 |
anna | +0.056 |
Of | +0.054 |
Sure | +0.054 |
Neg logit contributions | |
es | -0.035 |
rats | -0.032 |
ts | -0.031 |
stains | -0.030 |
marks | -0.030 |
Token | cakes |
Token ID | 30849 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
es | +0.033 |
isk | +0.030 |
adoes | +0.029 |
bes | +0.028 |
ings | +0.028 |
Neg logit contributions | |
bet | -0.039 |
pleasure | -0.039 |
anna | -0.036 |
Of | -0.036 |
ursion | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
rats | +0.032 |
ts | +0.031 |
adoes | +0.030 |
mice | +0.030 |
es | +0.029 |
Neg logit contributions | |
ursion | -0.022 |
anna | -0.022 |
bet | -0.022 |
pad | -0.022 |
Sure | -0.021 |
Token | cookies |
Token ID | 14746 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
es | +0.002 |
ings | +0.002 |
isk | +0.002 |
adoes | +0.001 |
iders | +0.001 |
Neg logit contributions | |
anna | -0.003 |
bet | -0.003 |
Of | -0.003 |
pleasure | -0.002 |
piping | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +6.71e-04 |
Pos logit contributions | |
rats | +0.057 |
es | +0.056 |
ts | +0.054 |
adoes | +0.053 |
mice | +0.051 |
Neg logit contributions | |
ursion | -0.074 |
bet | -0.072 |
anna | -0.071 |
Sure | -0.068 |
sur | -0.068 |
Token | ch |
Token ID | 442 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
bet | +0.001 |
ursion | +0.001 |
anna | +0.001 |
Of | +0.001 |
pleasure | +0.001 |
Neg logit contributions | |
es | -0.001 |
ts | -0.001 |
isk | -0.001 |
ings | -0.001 |
rats | -0.000 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
anna | +0.013 |
ursion | +0.013 |
bet | +0.012 |
pleasure | +0.011 |
sur | +0.011 |
Neg logit contributions | |
es | -0.011 |
not | -0.010 |
rats | -0.010 |
puzzles | -0.010 |
stains | -0.010 |
Token | ates |
Token ID | 689 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
not | +0.134 |
accidents | +0.125 |
rats | +0.123 |
stains | +0.123 |
blood | +0.115 |
Neg logit contributions | |
anna | -0.236 |
ursion | -0.226 |
pad | -0.216 |
bet | -0.211 |
pleasure | -0.204 |
Token | and |
Token ID | 290 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
anna | +0.006 |
bet | +0.006 |
ursion | +0.006 |
pad | +0.006 |
sur | +0.005 |
Neg logit contributions | |
rats | -0.006 |
adoes | -0.005 |
ts | -0.005 |
isk | -0.005 |
mice | -0.005 |
Token | ice |
Token ID | 4771 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
es | +0.004 |
rats | +0.003 |
ts | +0.003 |
stains | +0.003 |
marks | +0.003 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.008 |
anna | -0.008 |
Of | -0.008 |
Sure | -0.008 |
Token | cream |
Token ID | 8566 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
rats | +0.081 |
adoes | +0.078 |
es | +0.077 |
mice | +0.077 |
accidents | +0.075 |
Neg logit contributions | |
anna | -0.104 |
round | -0.089 |
ursion | -0.089 |
ya | -0.089 |
bet | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
es | +0.022 |
rats | +0.022 |
ts | +0.021 |
adoes | +0.021 |
stains | +0.020 |
Neg logit contributions | |
ursion | -0.031 |
bet | -0.030 |
anna | -0.030 |
Sure | -0.029 |
sur | -0.029 |
Token | oll |
Token ID | 692 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
es | +0.082 |
rats | +0.079 |
ts | +0.078 |
stains | +0.076 |
adoes | +0.076 |
Neg logit contributions | |
ursion | -0.083 |
anna | -0.078 |
bet | -0.078 |
Of | -0.073 |
Sure | -0.072 |
Token | ip |
Token ID | 541 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
es | +0.066 |
rats | +0.066 |
stains | +0.065 |
adoes | +0.065 |
mice | +0.064 |
Neg logit contributions | |
anna | -0.050 |
ursion | -0.050 |
bet | -0.045 |
Sure | -0.042 |
Of | -0.042 |
Token | ops |
Token ID | 2840 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
adoes | +0.029 |
rats | +0.028 |
mice | +0.024 |
snakes | +0.024 |
stains | +0.024 |
Neg logit contributions | |
anna | -0.072 |
ursion | -0.067 |
pad | -0.065 |
ya | -0.063 |
bet | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
rats | +0.060 |
es | +0.060 |
ts | +0.058 |
adoes | +0.057 |
stains | +0.055 |
Neg logit contributions | |
ursion | -0.093 |
anna | -0.091 |
bet | -0.087 |
pad | -0.084 |
sur | -0.082 |
Token | ch |
Token ID | 442 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
es | +0.024 |
ts | +0.022 |
rats | +0.022 |
stains | +0.022 |
marks | +0.021 |
Neg logit contributions | |
ursion | -0.030 |
bet | -0.030 |
anna | -0.030 |
Of | -0.029 |
Sure | -0.029 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
anna | +0.014 |
ursion | +0.013 |
bet | +0.013 |
sur | +0.012 |
ya | +0.012 |
Neg logit contributions | |
es | -0.012 |
not | -0.012 |
rats | -0.012 |
adoes | -0.012 |
puzzles | -0.012 |
Token | ates |
Token ID | 689 |
Feature activation | -3.30e-04 |
Pos logit contributions | |
rats | +0.121 |
stains | +0.120 |
not | +0.118 |
accidents | +0.117 |
mice | +0.112 |
Neg logit contributions | |
anna | -0.250 |
ursion | -0.240 |
pad | -0.232 |
bet | -0.223 |
sur | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
rats | +0.000 |
adoes | +0.000 |
ts | +0.000 |
mice | +0.000 |
es | +0.000 |
Neg logit contributions | |
anna | -0.000 |
ursion | -0.000 |
bet | -0.000 |
pad | -0.000 |
sur | -0.000 |
Token | g |
Token ID | 308 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
es | +0.022 |
rats | +0.020 |
ts | +0.020 |
stains | +0.019 |
marks | +0.019 |
Neg logit contributions | |
ursion | -0.031 |
bet | -0.031 |
anna | -0.030 |
Of | -0.029 |
Sure | -0.029 |
Token | ummies |
Token ID | 39578 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
es | +0.045 |
rats | +0.044 |
ts | +0.042 |
stains | +0.041 |
puzzles | +0.041 |
Neg logit contributions | |
anna | -0.054 |
ursion | -0.047 |
ya | -0.045 |
bet | -0.044 |
sur | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ts | +0.069 |
rats | +0.068 |
es | +0.067 |
adoes | +0.066 |
stains | +0.064 |
Neg logit contributions | |
anna | -0.084 |
ursion | -0.081 |
bet | -0.078 |
pad | -0.075 |
sur | -0.075 |
Token | park |
Token ID | 3952 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
ursion | +0.016 |
bet | +0.015 |
anna | +0.015 |
Of | +0.014 |
Sure | +0.014 |
Neg logit contributions | |
es | -0.017 |
rats | -0.015 |
ts | -0.015 |
stains | -0.015 |
marks | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ursion | +0.109 |
anna | +0.107 |
bet | +0.105 |
pleasure | +0.101 |
Of | +0.100 |
Neg logit contributions | |
es | -0.039 |
not | -0.033 |
rats | -0.030 |
marks | -0.029 |
stains | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -5.86e-03 |
Pos logit contributions | |
anna | +0.020 |
ursion | +0.020 |
sur | +0.019 |
Of | +0.018 |
lifetime | +0.018 |
Neg logit contributions | |
es | -0.009 |
mice | -0.009 |
not | -0.009 |
puzzles | -0.008 |
adoes | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
es | +0.008 |
ts | +0.007 |
rats | +0.007 |
stains | +0.007 |
not | +0.007 |
Neg logit contributions | |
ursion | -0.010 |
anna | -0.010 |
bet | -0.009 |
pleasure | -0.009 |
Sure | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +7.91e-04 |
Pos logit contributions | |
es | +0.017 |
rats | +0.015 |
ts | +0.014 |
stains | +0.014 |
marks | +0.014 |
Neg logit contributions | |
ursion | -0.030 |
bet | -0.029 |
anna | -0.029 |
Of | -0.028 |
Sure | -0.027 |
Token | best |
Token ID | 1266 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
anna | +0.001 |
ursion | +0.001 |
bet | +0.001 |
Sure | +0.001 |
ounded | +0.001 |
Neg logit contributions | |
marks | -0.001 |
rats | -0.001 |
stains | -0.001 |
not | -0.001 |
cookies | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ursion | +0.178 |
anna | +0.163 |
Of | +0.160 |
ounded | +0.160 |
bet | +0.160 |
Neg logit contributions | |
marks | -0.153 |
rats | -0.149 |
stains | -0.148 |
sandwiches | -0.148 |
es | -0.147 |
Token | playing |
Token ID | 2712 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
ursion | +0.146 |
bet | +0.139 |
anna | +0.136 |
Of | +0.136 |
Sure | +0.132 |
Neg logit contributions | |
es | -0.072 |
rats | -0.059 |
not | -0.058 |
marks | -0.057 |
ts | -0.056 |
Token | together |
Token ID | 1978 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
es | +0.039 |
rats | +0.037 |
stains | +0.037 |
marks | +0.035 |
ts | +0.034 |
Neg logit contributions | |
bet | -0.066 |
ursion | -0.066 |
anna | -0.062 |
Sure | -0.061 |
sur | -0.061 |
Token | on |
Token ID | 319 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ursion | +0.098 |
bet | +0.094 |
anna | +0.094 |
Of | +0.090 |
Sure | +0.090 |
Neg logit contributions | |
es | -0.048 |
rats | -0.042 |
ts | -0.040 |
stains | -0.040 |
marks | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
es | +0.016 |
rats | +0.014 |
stains | +0.013 |
isk | +0.013 |
ts | +0.013 |
Neg logit contributions | |
ursion | -0.026 |
bet | -0.026 |
Sure | -0.025 |
pleasure | -0.025 |
sur | -0.025 |
Token | then |
Token ID | 788 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
ursion | +0.021 |
anna | +0.020 |
bet | +0.019 |
Of | +0.019 |
Sure | +0.019 |
Neg logit contributions | |
es | -0.016 |
rats | -0.014 |
not | -0.014 |
ts | -0.014 |
stains | -0.014 |
Token | Jack |
Token ID | 3619 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
ursion | +0.100 |
anna | +0.095 |
bet | +0.095 |
Of | +0.091 |
Sure | +0.090 |
Neg logit contributions | |
es | -0.087 |
rats | -0.079 |
ts | -0.077 |
stains | -0.077 |
marks | -0.077 |
Token | said |
Token ID | 531 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
ursion | +0.053 |
bet | +0.049 |
anna | +0.049 |
Of | +0.048 |
Sure | +0.047 |
Neg logit contributions | |
es | -0.053 |
rats | -0.047 |
marks | -0.047 |
stains | -0.046 |
ts | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ursion | +0.071 |
bet | +0.067 |
anna | +0.067 |
Sure | +0.064 |
Of | +0.063 |
Neg logit contributions | |
es | -0.053 |
rats | -0.047 |
ts | -0.046 |
not | -0.045 |
stains | -0.045 |
Token | " |
Token ID | 366 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ursion | +0.025 |
anna | +0.023 |
bet | +0.023 |
ounded | +0.022 |
pleasure | +0.021 |
Neg logit contributions | |
es | -0.015 |
not | -0.015 |
rats | -0.012 |
mice | -0.012 |
marks | -0.012 |
Token | Let |
Token ID | 5756 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
anna | +0.042 |
ursion | +0.042 |
ounded | +0.040 |
pleasure | +0.040 |
bet | +0.039 |
Neg logit contributions | |
es | -0.030 |
marks | -0.024 |
isk | -0.024 |
not | -0.024 |
mice | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
ursion | +0.173 |
bet | +0.162 |
Sure | +0.161 |
anna | +0.161 |
Of | +0.157 |
Neg logit contributions | |
es | -0.112 |
marks | -0.102 |
not | -0.101 |
rats | -0.098 |
stains | -0.096 |
Token | race |
Token ID | 3234 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
ursion | +0.013 |
anna | +0.013 |
bet | +0.012 |
Of | +0.012 |
Sure | +0.012 |
Neg logit contributions | |
es | -0.013 |
rats | -0.012 |
marks | -0.012 |
not | -0.012 |
ts | -0.011 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
ursion | +0.112 |
anna | +0.109 |
bet | +0.106 |
Of | +0.103 |
Sure | +0.103 |
Neg logit contributions | |
es | -0.067 |
ts | -0.058 |
rats | -0.057 |
marks | -0.057 |
not | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ursion | +0.057 |
bet | +0.055 |
anna | +0.055 |
Of | +0.053 |
Sure | +0.052 |
Neg logit contributions | |
es | -0.032 |
rats | -0.029 |
ts | -0.027 |
stains | -0.027 |
marks | -0.027 |
Token | tent |
Token ID | 11105 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
anna | +0.066 |
ursion | +0.065 |
bet | +0.062 |
Of | +0.062 |
Sure | +0.060 |
Neg logit contributions | |
es | -0.042 |
rats | -0.042 |
marks | -0.041 |
puzzles | -0.040 |
mice | -0.040 |
Token | smiled |
Token ID | 13541 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
es | +0.002 |
rats | +0.002 |
ts | +0.002 |
stains | +0.002 |
marks | +0.002 |
Neg logit contributions | |
ursion | -0.002 |
bet | -0.002 |
anna | -0.002 |
Of | -0.002 |
Sure | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
es | +0.004 |
not | +0.003 |
marks | +0.003 |
rats | +0.003 |
stains | +0.003 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.009 |
bet | -0.009 |
Of | -0.008 |
Sure | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
ursion | +0.009 |
anna | +0.009 |
bet | +0.008 |
pleasure | +0.008 |
uster | +0.008 |
Neg logit contributions | |
not | -0.006 |
es | -0.006 |
all | -0.005 |
ts | -0.005 |
cookies | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
ursion | +0.069 |
anna | +0.065 |
bet | +0.065 |
pleasure | +0.060 |
Sure | +0.060 |
Neg logit contributions | |
es | -0.037 |
not | -0.032 |
ts | -0.028 |
rats | -0.028 |
marks | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
not | +0.005 |
es | +0.004 |
oni | +0.003 |
mice | +0.003 |
rats | +0.003 |
Neg logit contributions | |
ursion | -0.010 |
bet | -0.010 |
anna | -0.010 |
pleasure | -0.009 |
sur | -0.009 |
Token | Of |
Token ID | 5189 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
anna | +0.004 |
ursion | +0.003 |
ird | +0.003 |
pleasure | +0.003 |
pad | +0.003 |
Neg logit contributions | |
not | -0.004 |
es | -0.004 |
stains | -0.003 |
rats | -0.003 |
't | -0.003 |
Token | course |
Token ID | 1781 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
ursion | +0.178 |
anna | +0.176 |
bet | +0.172 |
Sure | +0.169 |
ounded | +0.165 |
Neg logit contributions | |
es | -0.091 |
rats | -0.086 |
not | -0.082 |
marks | -0.080 |
ts | -0.078 |
Token | you |
Token ID | 345 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ursion | +0.180 |
bet | +0.170 |
anna | +0.166 |
sur | +0.158 |
Sure | +0.157 |
Neg logit contributions | |
es | -0.082 |
not | -0.076 |
rats | -0.072 |
mice | -0.066 |
ts | -0.063 |
Token | can |
Token ID | 460 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ursion | +0.076 |
anna | +0.074 |
Sure | +0.071 |
bet | +0.069 |
Of | +0.069 |
Neg logit contributions | |
es | -0.064 |
marks | -0.058 |
not | -0.057 |
stains | -0.055 |
rats | -0.054 |
Token | ! |
Token ID | 0 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ursion | +0.050 |
anna | +0.048 |
bet | +0.047 |
Of | +0.046 |
Sure | +0.046 |
Neg logit contributions | |
es | -0.026 |
not | -0.022 |
marks | -0.022 |
stains | -0.021 |
ts | -0.021 |
Token | But |
Token ID | 887 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
ya | +0.034 |
ursion | +0.034 |
anna | +0.033 |
sur | +0.032 |
den | +0.031 |
Neg logit contributions | |
es | -0.036 |
not | -0.033 |
isk | -0.031 |
mice | -0.030 |
't | -0.030 |
Token | explore |
Token ID | 7301 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
es | +0.043 |
rats | +0.040 |
ts | +0.040 |
stains | +0.039 |
marks | +0.039 |
Neg logit contributions | |
ursion | -0.048 |
anna | -0.045 |
bet | -0.044 |
Sure | -0.043 |
Of | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.004 |
stains | +0.004 |
ts | +0.004 |
marks | +0.004 |
Neg logit contributions | |
ursion | -0.008 |
bet | -0.008 |
anna | -0.008 |
Of | -0.008 |
Sure | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
es | +0.013 |
not | +0.013 |
rats | +0.013 |
mice | +0.013 |
bones | +0.012 |
Neg logit contributions | |
ursion | -0.020 |
ya | -0.019 |
anna | -0.019 |
ounded | -0.019 |
bet | -0.018 |
Token | found |
Token ID | 1043 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
es | +0.033 |
rats | +0.031 |
ts | +0.030 |
stains | +0.030 |
marks | +0.029 |
Neg logit contributions | |
ursion | -0.038 |
bet | -0.037 |
anna | -0.037 |
Of | -0.035 |
Sure | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
ts | +0.006 |
stains | +0.005 |
marks | +0.005 |
Neg logit contributions | |
ursion | -0.014 |
bet | -0.014 |
anna | -0.014 |
Sure | -0.013 |
Of | -0.013 |
Token | way |
Token ID | 835 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
anna | +0.003 |
ursion | +0.003 |
bet | +0.002 |
Sure | +0.002 |
ounded | +0.002 |
Neg logit contributions | |
not | -0.002 |
rats | -0.001 |
stains | -0.001 |
sandwiches | -0.001 |
marks | -0.001 |
Token | out |
Token ID | 503 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
ursion | +0.258 |
Of | +0.256 |
pleasure | +0.250 |
anna | +0.249 |
bet | +0.249 |
Neg logit contributions | |
not | -0.123 |
es | -0.121 |
rats | -0.108 |
marks | -0.104 |
stains | -0.102 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ursion | +0.111 |
anna | +0.108 |
Of | +0.107 |
bet | +0.106 |
Sure | +0.104 |
Neg logit contributions | |
es | -0.063 |
rats | -0.053 |
ts | -0.052 |
not | -0.051 |
marks | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
es | +0.010 |
rats | +0.008 |
ts | +0.008 |
stains | +0.008 |
marks | +0.008 |
Neg logit contributions | |
ursion | -0.021 |
bet | -0.021 |
anna | -0.020 |
pleasure | -0.020 |
Sure | -0.020 |
Token | lake |
Token ID | 13546 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
ursion | +0.035 |
anna | +0.035 |
bet | +0.033 |
Sure | +0.032 |
Of | +0.032 |
Neg logit contributions | |
es | -0.029 |
rats | -0.029 |
marks | -0.028 |
stains | -0.028 |
ts | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
ursion | +0.078 |
bet | +0.076 |
anna | +0.075 |
Of | +0.072 |
Sure | +0.072 |
Neg logit contributions | |
es | -0.044 |
rats | -0.040 |
ts | -0.038 |
stains | -0.038 |
marks | -0.038 |
Token | wet |
Token ID | 9583 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
bet | +0.010 |
ursion | +0.010 |
pleasure | +0.010 |
anna | +0.009 |
sur | +0.009 |
Neg logit contributions | |
es | -0.008 |
rats | -0.006 |
ts | -0.006 |
adoes | -0.006 |
bes | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
es | +0.042 |
ts | +0.038 |
rats | +0.038 |
isk | +0.035 |
bes | +0.035 |
Neg logit contributions | |
ursion | -0.059 |
bet | -0.057 |
anna | -0.056 |
sur | -0.054 |
pleasure | -0.053 |
Token | |
Token ID | 220 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
ursion | +0.013 |
anna | +0.013 |
bet | +0.012 |
sur | +0.012 |
Of | +0.011 |
Neg logit contributions | |
es | -0.012 |
rats | -0.011 |
not | -0.011 |
mice | -0.011 |
stains | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
ursion | +0.054 |
bet | +0.052 |
anna | +0.051 |
Sure | +0.048 |
Of | +0.048 |
Neg logit contributions | |
es | -0.056 |
rats | -0.053 |
ts | -0.052 |
stains | -0.051 |
marks | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
ursion | +0.008 |
anna | +0.008 |
bet | +0.007 |
pleasure | +0.007 |
sur | +0.007 |
Neg logit contributions | |
es | -0.005 |
not | -0.005 |
rats | -0.004 |
mice | -0.004 |
marks | -0.004 |
Token | Conf |
Token ID | 18546 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
ursion | +0.009 |
bet | +0.009 |
anna | +0.009 |
Sure | +0.008 |
Of | +0.008 |
Neg logit contributions | |
es | -0.007 |
rats | -0.007 |
ts | -0.007 |
stains | -0.007 |
marks | -0.007 |
Token | used |
Token ID | 1484 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
anna | +0.095 |
ursion | +0.093 |
bet | +0.088 |
pleasure | +0.085 |
Of | +0.084 |
Neg logit contributions | |
es | -0.176 |
not | -0.164 |
rats | -0.161 |
ts | -0.160 |
marks | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
ursion | +0.114 |
bet | +0.111 |
anna | +0.109 |
Sure | +0.105 |
Of | +0.104 |
Neg logit contributions | |
es | -0.088 |
rats | -0.081 |
ts | -0.080 |
stains | -0.079 |
marks | -0.077 |
Token | they |
Token ID | 484 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
ts | +0.006 |
stains | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.008 |
bet | -0.008 |
Sure | -0.008 |
Of | -0.008 |
Token | started |
Token ID | 2067 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
ursion | +0.026 |
anna | +0.025 |
bet | +0.024 |
Sure | +0.024 |
pleasure | +0.024 |
Neg logit contributions | |
es | -0.026 |
rats | -0.024 |
ts | -0.023 |
not | -0.023 |
marks | -0.023 |
Token | arguing |
Token ID | 11810 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
ursion | +0.079 |
bet | +0.079 |
anna | +0.077 |
Sure | +0.073 |
sur | +0.073 |
Neg logit contributions | |
es | -0.088 |
rats | -0.082 |
ts | -0.080 |
stains | -0.078 |
mice | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
not | +0.006 |
ts | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.009 |
anna | -0.008 |
bet | -0.008 |
pleasure | -0.008 |
sur | -0.008 |
Token | When |
Token ID | 2215 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
ts | +0.005 |
stains | +0.005 |
marks | +0.005 |
Neg logit contributions | |
ursion | -0.006 |
bet | -0.005 |
anna | -0.005 |
Of | -0.005 |
Sure | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
ursion | +0.063 |
bet | +0.061 |
anna | +0.059 |
Sure | +0.057 |
Of | +0.057 |
Neg logit contributions | |
es | -0.070 |
rats | -0.065 |
ts | -0.064 |
stains | -0.064 |
marks | -0.063 |
Token | arrived |
Token ID | 5284 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
ursion | +0.047 |
anna | +0.046 |
pleasure | +0.044 |
Sure | +0.043 |
Of | +0.043 |
Neg logit contributions | |
es | -0.024 |
not | -0.024 |
all | -0.023 |
ts | -0.023 |
stains | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
ursion | +0.045 |
bet | +0.043 |
anna | +0.043 |
Sure | +0.041 |
Of | +0.041 |
Neg logit contributions | |
es | -0.032 |
rats | -0.029 |
ts | -0.029 |
stains | -0.028 |
marks | -0.028 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
es | +0.009 |
ts | +0.008 |
stains | +0.008 |
rats | +0.008 |
marks | +0.008 |
Neg logit contributions | |
bet | -0.007 |
ursion | -0.007 |
Sure | -0.006 |
anna | -0.006 |
Of | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
ursion | +0.025 |
bet | +0.023 |
Of | +0.023 |
pleasure | +0.023 |
anna | +0.023 |
Neg logit contributions | |
es | -0.020 |
rats | -0.017 |
ts | -0.017 |
marks | -0.017 |
stains | -0.017 |
Token | very |
Token ID | 845 |
Feature activation | -7.15e-03 |
Pos logit contributions | |
ursion | +0.014 |
bet | +0.013 |
anna | +0.013 |
sur | +0.012 |
pleasure | +0.012 |
Neg logit contributions | |
es | -0.015 |
rats | -0.014 |
stains | -0.014 |
ts | -0.013 |
marks | -0.013 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
es | +0.011 |
not | +0.010 |
rats | +0.010 |
ts | +0.010 |
stains | +0.010 |
Neg logit contributions | |
ursion | -0.011 |
anna | -0.011 |
bet | -0.011 |
Sure | -0.010 |
Of | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
es | +0.015 |
rats | +0.014 |
ts | +0.013 |
stains | +0.013 |
marks | +0.013 |
Neg logit contributions | |
ursion | -0.021 |
anna | -0.021 |
bet | -0.020 |
Sure | -0.019 |
Of | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -5.87e-03 |
Pos logit contributions | |
ursion | +0.010 |
anna | +0.010 |
sur | +0.009 |
bet | +0.009 |
ounded | +0.009 |
Neg logit contributions | |
es | -0.007 |
rats | -0.007 |
mice | -0.006 |
not | -0.006 |
stains | -0.006 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
es | +0.029 |
rats | +0.025 |
ts | +0.025 |
stains | +0.024 |
mice | +0.023 |
Neg logit contributions | |
ursion | -0.040 |
bet | -0.039 |
anna | -0.039 |
pleasure | -0.038 |
Sure | -0.037 |
Token | snow |
Token ID | 6729 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
anna | +0.002 |
ursion | +0.002 |
bet | +0.002 |
Sure | +0.002 |
pleasure | +0.002 |
Neg logit contributions | |
es | -0.002 |
ts | -0.002 |
rats | -0.002 |
mice | -0.002 |
stains | -0.002 |
Token | man |
Token ID | 805 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
rats | +0.034 |
ts | +0.033 |
es | +0.032 |
stains | +0.032 |
mice | +0.032 |
Neg logit contributions | |
anna | -0.060 |
ursion | -0.058 |
bet | -0.057 |
Sure | -0.057 |
pleasure | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
es | +0.057 |
rats | +0.054 |
ts | +0.053 |
stains | +0.052 |
marks | +0.050 |
Neg logit contributions | |
ursion | -0.091 |
anna | -0.090 |
bet | -0.088 |
pleasure | -0.084 |
Of | -0.083 |
Token | But |
Token ID | 887 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
es | +0.017 |
rats | +0.016 |
not | +0.016 |
adoes | +0.015 |
stains | +0.015 |
Neg logit contributions | |
ursion | -0.017 |
anna | -0.017 |
bet | -0.016 |
ya | -0.016 |
ounded | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
ursion | +0.081 |
bet | +0.078 |
anna | +0.077 |
Sure | +0.073 |
Of | +0.073 |
Neg logit contributions | |
es | -0.079 |
rats | -0.073 |
ts | -0.072 |
stains | -0.071 |
marks | -0.070 |
Token | know |
Token ID | 760 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
bet | +0.046 |
ursion | +0.040 |
pleasure | +0.035 |
anna | +0.035 |
Of | +0.034 |
Neg logit contributions | |
es | -0.075 |
ings | -0.075 |
bes | -0.075 |
adoes | -0.073 |
rats | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
anna | +0.008 |
ursion | +0.008 |
bet | +0.008 |
Of | +0.007 |
pleasure | +0.007 |
Neg logit contributions | |
es | -0.006 |
rats | -0.005 |
ts | -0.005 |
bes | -0.005 |
stains | -0.005 |
Token | snow |
Token ID | 6729 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
es | +0.038 |
ts | +0.034 |
rats | +0.034 |
stains | +0.034 |
marks | +0.033 |
Neg logit contributions | |
bet | -0.038 |
anna | -0.037 |
ursion | -0.037 |
Of | -0.036 |
pleasure | -0.035 |
Token | men |
Token ID | 3653 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
rats | +0.033 |
puzzles | +0.033 |
mice | +0.033 |
stains | +0.032 |
es | +0.031 |
Neg logit contributions | |
anna | -0.057 |
bet | -0.057 |
Sure | -0.055 |
pleasure | -0.054 |
ursion | -0.054 |
Token | are |
Token ID | 389 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
ts | +0.005 |
bes | +0.005 |
mice | +0.005 |
Neg logit contributions | |
bet | -0.006 |
ursion | -0.006 |
anna | -0.006 |
pleasure | -0.006 |
sur | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
es | +0.008 |
rats | +0.008 |
stains | +0.007 |
marks | +0.007 |
ts | +0.007 |
Neg logit contributions | |
ursion | -0.012 |
bet | -0.011 |
anna | -0.011 |
Sure | -0.011 |
Of | -0.011 |
Token | its |
Token ID | 663 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ursion | +0.047 |
bet | +0.047 |
Sure | +0.045 |
pleasure | +0.045 |
anna | +0.044 |
Neg logit contributions | |
es | -0.025 |
rats | -0.022 |
ts | -0.022 |
stains | -0.022 |
marks | -0.021 |
Token | pocket |
Token ID | 10000 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
es | +0.035 |
rats | +0.032 |
stains | +0.031 |
ts | +0.031 |
marks | +0.031 |
Neg logit contributions | |
ursion | -0.042 |
bet | -0.040 |
anna | -0.040 |
Of | -0.038 |
Sure | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
ursion | +0.024 |
bet | +0.023 |
anna | +0.023 |
Sure | +0.022 |
Of | +0.022 |
Neg logit contributions | |
es | -0.013 |
rats | -0.012 |
ts | -0.011 |
stains | -0.011 |
marks | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
anna | +0.007 |
ursion | +0.007 |
sur | +0.006 |
bet | +0.006 |
ya | +0.006 |
Neg logit contributions | |
es | -0.004 |
mice | -0.003 |
bones | -0.003 |
not | -0.003 |
rats | -0.003 |
Token | me |
Token ID | 502 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
es | +0.034 |
rats | +0.033 |
stains | +0.032 |
marks | +0.032 |
adoes | +0.032 |
Neg logit contributions | |
bet | -0.030 |
ursion | -0.030 |
anna | -0.029 |
Of | -0.028 |
Sure | -0.028 |
Token | owed |
Token ID | 6972 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ursion | +0.038 |
anna | +0.037 |
bet | +0.037 |
Sure | +0.034 |
Of | +0.034 |
Neg logit contributions | |
es | -0.042 |
rats | -0.040 |
stains | -0.039 |
marks | -0.039 |
ts | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
bet | +0.029 |
pleasure | +0.029 |
Sure | +0.029 |
anna | +0.028 |
Of | +0.028 |
Neg logit contributions | |
rats | -0.028 |
stains | -0.027 |
es | -0.027 |
ts | -0.027 |
marks | -0.027 |
Token | let |
Token ID | 1309 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
es | +0.015 |
rats | +0.013 |
ts | +0.013 |
stains | +0.013 |
marks | +0.013 |
Neg logit contributions | |
ursion | -0.030 |
anna | -0.028 |
bet | -0.028 |
Of | -0.027 |
Sure | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
ursion | +0.165 |
bet | +0.162 |
anna | +0.160 |
Sure | +0.154 |
Of | +0.152 |
Neg logit contributions | |
es | -0.083 |
rats | -0.074 |
stains | -0.073 |
ts | -0.072 |
marks | -0.069 |
Token | child |
Token ID | 1200 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
ursion | +0.030 |
bet | +0.028 |
anna | +0.028 |
Of | +0.027 |
Sure | +0.026 |
Neg logit contributions | |
es | -0.040 |
ts | -0.037 |
rats | -0.037 |
stains | -0.036 |
marks | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ursion | +0.068 |
ounded | +0.066 |
bet | +0.064 |
anna | +0.064 |
sur | +0.064 |
Neg logit contributions | |
es | -0.047 |
not | -0.042 |
mice | -0.041 |
rats | -0.040 |
adoes | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ursion | +0.028 |
bet | +0.027 |
anna | +0.027 |
sur | +0.026 |
pleasure | +0.026 |
Neg logit contributions | |
es | -0.018 |
rats | -0.016 |
not | -0.016 |
marks | -0.015 |
ts | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
ursion | +0.021 |
anna | +0.020 |
pleasure | +0.020 |
bet | +0.020 |
ounded | +0.019 |
Neg logit contributions | |
es | -0.012 |
rats | -0.011 |
not | -0.011 |
ts | -0.010 |
bes | -0.010 |
Token | peanut |
Token ID | 26636 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
ursion | +0.014 |
anna | +0.014 |
bet | +0.013 |
Sure | +0.013 |
Of | +0.013 |
Neg logit contributions | |
es | -0.010 |
rats | -0.010 |
marks | -0.010 |
ts | -0.010 |
mice | -0.010 |
Token | stops |
Token ID | 9911 |
Feature activation | -2.12e-04 |
Pos logit contributions | |
isk | +0.110 |
adoes | +0.104 |
rats | +0.103 |
ings | +0.100 |
stains | +0.099 |
Neg logit contributions | |
ursion | -0.092 |
anna | -0.090 |
bet | -0.087 |
sur | -0.083 |
ya | -0.081 |
Token | spinning |
Token ID | 19493 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
es | +0.000 |
rats | +0.000 |
ts | +0.000 |
stains | +0.000 |
bes | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
anna | -0.000 |
Sure | -0.000 |
sur | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ursion | +0.033 |
bet | +0.032 |
anna | +0.031 |
Sure | +0.030 |
sur | +0.030 |
Neg logit contributions | |
es | -0.024 |
rats | -0.023 |
ts | -0.022 |
stains | -0.022 |
marks | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ursion | +0.021 |
ounded | +0.020 |
anna | +0.020 |
bet | +0.019 |
sur | +0.019 |
Neg logit contributions | |
es | -0.011 |
mice | -0.010 |
not | -0.010 |
rats | -0.010 |
puzzles | -0.009 |
Token | lands |
Token ID | 8604 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
es | +0.038 |
rats | +0.035 |
stains | +0.034 |
ts | +0.034 |
marks | +0.034 |
Neg logit contributions | |
ursion | -0.046 |
bet | -0.044 |
anna | -0.044 |
Of | -0.041 |
Sure | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
rats | +0.013 |
es | +0.012 |
stains | +0.012 |
ts | +0.012 |
adoes | +0.012 |
Neg logit contributions | |
ursion | -0.020 |
bet | -0.019 |
anna | -0.018 |
Sure | -0.018 |
sur | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
ts | +0.005 |
stains | +0.005 |
bes | +0.005 |
Neg logit contributions | |
bet | -0.012 |
ursion | -0.012 |
Sure | -0.012 |
pleasure | -0.011 |
anna | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
es | +0.018 |
rats | +0.016 |
stains | +0.016 |
ts | +0.016 |
isk | +0.015 |
Neg logit contributions | |
anna | -0.034 |
bet | -0.034 |
ursion | -0.033 |
pleasure | -0.032 |
Sure | -0.032 |
Token | stove |
Token ID | 27635 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
bet | +0.029 |
ursion | +0.029 |
anna | +0.028 |
Sure | +0.027 |
pleasure | +0.027 |
Neg logit contributions | |
es | -0.031 |
isk | -0.028 |
ts | -0.026 |
rats | -0.026 |
stains | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.51e-03 |
Pos logit contributions | |
es | +0.018 |
rats | +0.018 |
ts | +0.017 |
stains | +0.016 |
mice | +0.016 |
Neg logit contributions | |
ursion | -0.029 |
bet | -0.029 |
anna | -0.028 |
Sure | -0.027 |
pleasure | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-04 |
Pos logit contributions | |
ursion | +0.007 |
sur | +0.007 |
anna | +0.007 |
bet | +0.006 |
round | +0.006 |
Neg logit contributions | |
es | -0.007 |
mice | -0.006 |
not | -0.006 |
stains | -0.006 |
marks | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
ursion | +0.000 |
bet | +0.000 |
anna | +0.000 |
Sure | +0.000 |
Of | +0.000 |
Neg logit contributions | |
es | -0.000 |
rats | -0.000 |
ts | -0.000 |
stains | -0.000 |
marks | -0.000 |
Token | Emily |
Token ID | 48640 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
ursion | +0.002 |
bet | +0.002 |
anna | +0.002 |
Of | +0.002 |
Sure | +0.002 |
Neg logit contributions | |
es | -0.003 |
rats | -0.003 |
ts | -0.003 |
stains | -0.002 |
marks | -0.002 |
Token | learned |
Token ID | 4499 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
ursion | +0.042 |
anna | +0.041 |
bet | +0.041 |
Of | +0.038 |
sur | +0.038 |
Neg logit contributions | |
es | -0.039 |
rats | -0.038 |
ts | -0.036 |
stains | -0.036 |
marks | -0.035 |
Token | an |
Token ID | 281 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
es | +0.044 |
rats | +0.040 |
ts | +0.040 |
stains | +0.037 |
mice | +0.036 |
Neg logit contributions | |
ursion | -0.080 |
Of | -0.080 |
bet | -0.079 |
anna | -0.078 |
Sure | -0.076 |
Token | important |
Token ID | 1593 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ursion | +0.050 |
bet | +0.048 |
Sure | +0.047 |
anna | +0.046 |
sur | +0.046 |
Neg logit contributions | |
es | -0.032 |
rats | -0.030 |
marks | -0.029 |
stains | -0.028 |
ts | -0.028 |
Token | lesson |
Token ID | 11483 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ursion | +0.030 |
bet | +0.029 |
anna | +0.029 |
Sure | +0.027 |
Of | +0.027 |
Neg logit contributions | |
es | -0.025 |
rats | -0.023 |
ts | -0.022 |
stains | -0.022 |
marks | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ursion | +0.050 |
anna | +0.048 |
bet | +0.048 |
Sure | +0.046 |
Of | +0.046 |
Neg logit contributions | |
es | -0.026 |
rats | -0.023 |
ts | -0.023 |
stains | -0.022 |
marks | -0.022 |
Token | chest |
Token ID | 7721 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
es | +0.019 |
rats | +0.018 |
marks | +0.017 |
stains | +0.017 |
ts | +0.017 |
Neg logit contributions | |
ursion | -0.029 |
bet | -0.027 |
anna | -0.026 |
Of | -0.026 |
Sure | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
ursion | +0.009 |
anna | +0.009 |
bet | +0.009 |
Sure | +0.008 |
Of | +0.008 |
Neg logit contributions | |
es | -0.005 |
rats | -0.005 |
ts | -0.005 |
stains | -0.005 |
marks | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
not | +0.002 |
es | +0.002 |
cookies | +0.002 |
stains | +0.002 |
mice | +0.002 |
Neg logit contributions | |
ursion | -0.005 |
anna | -0.005 |
ya | -0.005 |
bet | -0.005 |
pleasure | -0.005 |
Token | Hmm |
Token ID | 44217 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
es | +0.012 |
stains | +0.011 |
rats | +0.011 |
ts | +0.011 |
marks | +0.011 |
Neg logit contributions | |
ursion | -0.020 |
anna | -0.020 |
pleasure | -0.019 |
sur | -0.018 |
ounded | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +9.57e-05 |
Pos logit contributions | |
ursion | +0.070 |
bet | +0.067 |
anna | +0.066 |
Of | +0.064 |
Sure | +0.064 |
Neg logit contributions | |
es | -0.047 |
rats | -0.043 |
ts | -0.042 |
stains | -0.040 |
marks | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ursion | +0.000 |
bet | +0.000 |
anna | +0.000 |
Of | +0.000 |
Sure | +0.000 |
Neg logit contributions | |
es | -0.000 |
rats | -0.000 |
ts | -0.000 |
stains | -0.000 |
marks | -0.000 |
Token | sounds |
Token ID | 5238 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
es | +0.020 |
rats | +0.019 |
ts | +0.019 |
stains | +0.019 |
mice | +0.018 |
Neg logit contributions | |
ursion | -0.024 |
bet | -0.024 |
anna | -0.024 |
Sure | -0.021 |
Of | -0.021 |
Token | good |
Token ID | 922 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
es | +0.016 |
not | +0.016 |
stains | +0.016 |
rats | +0.015 |
ts | +0.015 |
Neg logit contributions | |
ursion | -0.029 |
anna | -0.027 |
bet | -0.027 |
Sure | -0.027 |
sur | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
stains | +0.006 |
ts | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.011 |
bet | -0.011 |
anna | -0.010 |
Of | -0.010 |
Sure | -0.010 |
Token | You |
Token ID | 921 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
ursion | +0.025 |
anna | +0.023 |
ya | +0.023 |
sur | +0.023 |
ounded | +0.023 |
Neg logit contributions | |
es | -0.022 |
mice | -0.020 |
rats | -0.020 |
not | -0.020 |
adoes | -0.019 |
Token | are |
Token ID | 389 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
ursion | +0.061 |
bet | +0.060 |
anna | +0.057 |
Of | +0.054 |
pleasure | +0.054 |
Neg logit contributions | |
es | -0.067 |
rats | -0.063 |
stains | -0.061 |
ts | -0.061 |
marks | -0.060 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ursion | +0.025 |
anna | +0.024 |
bet | +0.024 |
Sure | +0.022 |
Of | +0.022 |
Neg logit contributions | |
es | -0.021 |
rats | -0.019 |
stains | -0.019 |
ts | -0.018 |
marks | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
anna | +0.077 |
pleasure | +0.076 |
ursion | +0.076 |
bet | +0.074 |
Shall | +0.073 |
Neg logit contributions | |
not | -0.018 |
es | -0.017 |
all | -0.015 |
marks | -0.011 |
with | -0.011 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
not | +0.007 |
es | +0.007 |
ts | +0.007 |
all | +0.006 |
rats | +0.006 |
Neg logit contributions | |
ursion | -0.016 |
anna | -0.016 |
pleasure | -0.016 |
bet | -0.015 |
uster | -0.015 |
Token | climbed |
Token ID | 19952 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
es | +0.007 |
not | +0.006 |
ts | +0.006 |
rats | +0.006 |
marks | +0.006 |
Neg logit contributions | |
ursion | -0.009 |
pleasure | -0.009 |
bet | -0.009 |
anna | -0.008 |
Of | -0.008 |
Token | up |
Token ID | 510 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ursion | +0.056 |
anna | +0.054 |
bet | +0.054 |
Of | +0.052 |
pleasure | +0.051 |
Neg logit contributions | |
es | -0.026 |
rats | -0.023 |
ts | -0.022 |
stains | -0.022 |
marks | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ursion | +0.062 |
bet | +0.060 |
anna | +0.059 |
Sure | +0.058 |
Of | +0.057 |
Neg logit contributions | |
es | -0.028 |
rats | -0.025 |
ts | -0.024 |
stains | -0.024 |
marks | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
all | +0.002 |
the | +0.001 |
not | +0.001 |
ts | +0.001 |
rats | +0.001 |
Neg logit contributions | |
anna | -0.031 |
ursion | -0.030 |
mber | -0.029 |
enna | -0.029 |
den | -0.028 |
Token | top |
Token ID | 1353 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
ursion | +0.038 |
bet | +0.037 |
anna | +0.037 |
Sure | +0.035 |
Of | +0.035 |
Neg logit contributions | |
es | -0.028 |
rats | -0.026 |
ts | -0.025 |
stains | -0.025 |
marks | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
pleasure | +0.120 |
Of | +0.117 |
anna | +0.116 |
bet | +0.114 |
ursion | +0.114 |
Neg logit contributions | |
es | -0.030 |
marks | -0.028 |
rats | -0.026 |
not | -0.025 |
stains | -0.024 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.40e-04 |
Pos logit contributions | |
not | +0.005 |
es | +0.005 |
mice | +0.004 |
stains | +0.004 |
bones | +0.004 |
Neg logit contributions | |
ursion | -0.008 |
anna | -0.008 |
bet | -0.007 |
ya | -0.007 |
sur | -0.007 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
es | +0.000 |
not | +0.000 |
rats | +0.000 |
ts | +0.000 |
marks | +0.000 |
Neg logit contributions | |
ursion | -0.000 |
bet | -0.000 |
pleasure | -0.000 |
anna | -0.000 |
Sure | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
es | +0.093 |
isk | +0.087 |
bes | +0.086 |
rats | +0.083 |
ts | +0.078 |
Neg logit contributions | |
bet | -0.122 |
anna | -0.118 |
pleasure | -0.117 |
Of | -0.116 |
sur | -0.113 |
Token | mint |
Token ID | 21043 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
es | +0.007 |
ts | +0.006 |
isk | +0.006 |
rats | +0.006 |
bes | +0.006 |
Neg logit contributions | |
bet | -0.007 |
pleasure | -0.007 |
ursion | -0.007 |
anna | -0.007 |
ya | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
rats | +0.018 |
es | +0.018 |
isk | +0.018 |
ts | +0.018 |
blood | +0.017 |
Neg logit contributions | |
bet | -0.024 |
anna | -0.024 |
ursion | -0.024 |
ya | -0.022 |
Of | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
es | +0.055 |
rats | +0.049 |
ts | +0.049 |
stains | +0.047 |
marks | +0.047 |
Neg logit contributions | |
bet | -0.038 |
Of | -0.036 |
ursion | -0.035 |
anna | -0.035 |
pleasure | -0.034 |
Token | basil |
Token ID | 37792 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bet | +0.003 |
ursion | +0.003 |
anna | +0.003 |
Of | +0.003 |
pleasure | +0.003 |
Neg logit contributions | |
es | -0.002 |
ts | -0.002 |
rats | -0.002 |
stains | -0.002 |
isk | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
rats | +0.014 |
es | +0.014 |
ts | +0.013 |
adoes | +0.013 |
isk | +0.013 |
Neg logit contributions | |
bet | -0.016 |
anna | -0.016 |
ursion | -0.016 |
pleasure | -0.015 |
Of | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
es | +0.031 |
rats | +0.029 |
ts | +0.028 |
bes | +0.028 |
marks | +0.027 |
Neg logit contributions | |
bet | -0.033 |
Of | -0.031 |
anna | -0.030 |
pleasure | -0.030 |
Shall | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
es | +0.001 |
rats | +0.001 |
ts | +0.001 |
stains | +0.001 |
marks | +0.001 |
Neg logit contributions | |
ursion | -0.003 |
anna | -0.003 |
bet | -0.003 |
Sure | -0.002 |
Of | -0.002 |
Token | rose |
Token ID | 8278 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
ursion | +0.012 |
bet | +0.012 |
anna | +0.011 |
Of | +0.011 |
pleasure | +0.011 |
Neg logit contributions | |
es | -0.008 |
rats | -0.007 |
ts | -0.007 |
stains | -0.007 |
marks | -0.006 |
Token | mary |
Token ID | 6874 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
bet | +0.044 |
ursion | +0.043 |
anna | +0.043 |
Of | +0.040 |
Sure | +0.040 |
Neg logit contributions | |
es | -0.034 |
rats | -0.033 |
ts | -0.031 |
stains | -0.030 |
adoes | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
es | +0.028 |
rats | +0.027 |
ts | +0.026 |
adoes | +0.026 |
stains | +0.025 |
Neg logit contributions | |
ursion | -0.036 |
bet | -0.036 |
anna | -0.036 |
Of | -0.034 |
Sure | -0.033 |
Token | so |
Token ID | 523 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
anna | +0.004 |
bet | +0.004 |
pleasure | +0.004 |
ursion | +0.004 |
Of | +0.004 |
Neg logit contributions | |
es | -0.006 |
rats | -0.005 |
ts | -0.005 |
stains | -0.005 |
adoes | -0.005 |
Token | lonely |
Token ID | 21757 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
ursion | +0.044 |
bet | +0.042 |
anna | +0.042 |
Of | +0.039 |
pleasure | +0.038 |
Neg logit contributions | |
es | -0.057 |
rats | -0.053 |
ts | -0.052 |
stains | -0.051 |
marks | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
es | +0.077 |
ts | +0.072 |
rats | +0.072 |
stains | +0.070 |
marks | +0.069 |
Neg logit contributions | |
ursion | -0.110 |
bet | -0.107 |
anna | -0.107 |
Sure | -0.102 |
Of | -0.101 |
Token |
|
Token ID | 198 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
es | +0.002 |
not | +0.002 |
rats | +0.002 |
mice | +0.002 |
stains | +0.002 |
Neg logit contributions | |
ursion | -0.004 |
sur | -0.004 |
bet | -0.004 |
anna | -0.004 |
ounded | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
es | +0.010 |
not | +0.008 |
rats | +0.008 |
marks | +0.008 |
ts | +0.008 |
Neg logit contributions | |
ursion | -0.014 |
bet | -0.013 |
anna | -0.013 |
sur | -0.013 |
pleasure | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
es | +0.010 |
rats | +0.009 |
ts | +0.009 |
stains | +0.009 |
marks | +0.009 |
Neg logit contributions | |
ursion | -0.007 |
bet | -0.007 |
anna | -0.007 |
Of | -0.007 |
Sure | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
ursion | +0.009 |
bet | +0.008 |
anna | +0.008 |
Sure | +0.008 |
Of | +0.008 |
Neg logit contributions | |
es | -0.007 |
rats | -0.007 |
stains | -0.007 |
marks | -0.007 |
ts | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
ursion | +0.123 |
anna | +0.121 |
Sure | +0.113 |
bet | +0.112 |
ounded | +0.108 |
Neg logit contributions | |
rats | -0.153 |
mice | -0.149 |
marks | -0.144 |
stains | -0.144 |
es | -0.143 |
Token | was |
Token ID | 373 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
ursion | +0.101 |
pleasure | +0.092 |
Of | +0.091 |
bet | +0.091 |
Sure | +0.088 |
Neg logit contributions | |
es | -0.070 |
rats | -0.060 |
not | -0.060 |
marks | -0.059 |
mice | -0.058 |
Token | about |
Token ID | 546 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
anna | +0.007 |
ursion | +0.007 |
bet | +0.007 |
pleasure | +0.007 |
Of | +0.007 |
Neg logit contributions | |
es | -0.007 |
rats | -0.006 |
ts | -0.006 |
stains | -0.006 |
marks | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
es | +0.100 |
ts | +0.090 |
stains | +0.087 |
rats | +0.087 |
bes | +0.086 |
Neg logit contributions | |
bet | -0.075 |
ursion | -0.074 |
anna | -0.072 |
Sure | -0.072 |
Of | -0.072 |
Token | shady |
Token ID | 36135 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ursion | +0.052 |
anna | +0.050 |
bet | +0.049 |
Sure | +0.049 |
Of | +0.048 |
Neg logit contributions | |
es | -0.022 |
rats | -0.021 |
stains | -0.021 |
not | -0.020 |
mice | -0.020 |
Token | rock |
Token ID | 3881 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
es | +0.016 |
rats | +0.015 |
stains | +0.015 |
ts | +0.015 |
marks | +0.014 |
Neg logit contributions | |
ursion | -0.020 |
anna | -0.019 |
bet | -0.019 |
Sure | -0.018 |
sur | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
ursion | +0.055 |
bet | +0.053 |
anna | +0.053 |
Of | +0.051 |
pleasure | +0.051 |
Neg logit contributions | |
es | -0.028 |
rats | -0.024 |
stains | -0.023 |
ts | -0.023 |
marks | -0.023 |
Token | watched |
Token ID | 7342 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
es | +0.006 |
rats | +0.005 |
ts | +0.005 |
not | +0.005 |
stains | +0.005 |
Neg logit contributions | |
ursion | -0.007 |
anna | -0.006 |
bet | -0.006 |
pleasure | -0.006 |
Of | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
anna | +0.050 |
ursion | +0.050 |
bet | +0.050 |
Sure | +0.048 |
Of | +0.048 |
Neg logit contributions | |
es | -0.032 |
rats | -0.029 |
stains | -0.028 |
ts | -0.028 |
marks | -0.027 |
Token | fish |
Token ID | 5916 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
bet | +0.019 |
ursion | +0.018 |
sur | +0.018 |
Of | +0.018 |
pleasure | +0.017 |
Neg logit contributions | |
es | -0.020 |
adoes | -0.017 |
ts | -0.017 |
isk | -0.017 |
stains | -0.016 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ursion | +0.005 |
bet | +0.005 |
anna | +0.005 |
Sure | +0.005 |
Of | +0.005 |
Neg logit contributions | |
es | -0.005 |
rats | -0.005 |
stains | -0.005 |
ts | -0.005 |
adoes | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ursion | +0.017 |
bet | +0.017 |
anna | +0.016 |
Sure | +0.016 |
Of | +0.016 |
Neg logit contributions | |
es | -0.017 |
rats | -0.016 |
ts | -0.015 |
stains | -0.015 |
marks | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
ursion | +0.043 |
bet | +0.043 |
pleasure | +0.041 |
anna | +0.041 |
Sure | +0.041 |
Neg logit contributions | |
es | -0.022 |
rats | -0.019 |
ts | -0.019 |
stains | -0.018 |
marks | -0.017 |
Token | water |
Token ID | 1660 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
marks | +0.003 |
stains | +0.003 |
rats | +0.003 |
mice | +0.003 |
blood | +0.003 |
Neg logit contributions | |
ursion | -0.007 |
anna | -0.007 |
Sure | -0.006 |
bet | -0.006 |
Of | -0.006 |
Token | below |
Token ID | 2174 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
ursion | +0.040 |
bet | +0.038 |
anna | +0.038 |
Sure | +0.037 |
Of | +0.037 |
Neg logit contributions | |
es | -0.021 |
rats | -0.019 |
ts | -0.018 |
stains | -0.018 |
marks | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
rats | +0.054 |
es | +0.053 |
sandwiches | +0.051 |
ings | +0.050 |
ts | +0.050 |
Neg logit contributions | |
ursion | -0.058 |
bet | -0.058 |
anna | -0.054 |
Of | -0.053 |
sur | -0.053 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
es | +0.019 |
rats | +0.017 |
ts | +0.017 |
stains | +0.017 |
marks | +0.016 |
Neg logit contributions | |
ursion | -0.024 |
bet | -0.024 |
anna | -0.023 |
pleasure | -0.023 |
Of | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
es | +0.005 |
rats | +0.005 |
ts | +0.005 |
stains | +0.005 |
marks | +0.005 |
Neg logit contributions | |
ursion | -0.009 |
bet | -0.008 |
anna | -0.008 |
Sure | -0.008 |
Of | -0.008 |
Token | learn |
Token ID | 2193 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
es | +0.046 |
not | +0.043 |
ts | +0.043 |
marks | +0.042 |
rats | +0.042 |
Neg logit contributions | |
ursion | -0.055 |
anna | -0.052 |
bet | -0.051 |
Sure | -0.050 |
Of | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
es | +0.075 |
rats | +0.068 |
ts | +0.066 |
stains | +0.065 |
marks | +0.063 |
Neg logit contributions | |
ursion | -0.125 |
bet | -0.122 |
anna | -0.121 |
Of | -0.116 |
Sure | -0.116 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
es | +0.006 |
mice | +0.005 |
not | +0.005 |
rats | +0.004 |
isk | +0.004 |
Neg logit contributions | |
ursion | -0.009 |
ounded | -0.009 |
sur | -0.009 |
anna | -0.009 |
bet | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
es | +0.151 |
rats | +0.142 |
ts | +0.138 |
stains | +0.137 |
marks | +0.135 |
Neg logit contributions | |
ursion | -0.168 |
bet | -0.161 |
anna | -0.159 |
Sure | -0.152 |
Of | -0.151 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
es | +0.033 |
rats | +0.030 |
ts | +0.029 |
not | +0.029 |
stains | +0.029 |
Neg logit contributions | |
ursion | -0.046 |
bet | -0.044 |
anna | -0.044 |
Of | -0.042 |
Sure | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
es | +0.073 |
adoes | +0.068 |
stains | +0.065 |
rats | +0.064 |
isk | +0.064 |
Neg logit contributions | |
bet | -0.112 |
ursion | -0.109 |
Sure | -0.106 |
Of | -0.106 |
anna | -0.105 |
Token | time |
Token ID | 640 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
ursion | +0.026 |
bet | +0.024 |
anna | +0.024 |
sur | +0.023 |
Of | +0.023 |
Neg logit contributions | |
es | -0.019 |
rats | -0.018 |
not | -0.018 |
ts | -0.017 |
stains | -0.017 |
Token | there |
Token ID | 612 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
ursion | +0.091 |
bet | +0.088 |
anna | +0.086 |
Sure | +0.084 |
Of | +0.082 |
Neg logit contributions | |
es | -0.077 |
rats | -0.072 |
ts | -0.071 |
stains | -0.071 |
marks | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
es | +0.070 |
ts | +0.069 |
rats | +0.068 |
adoes | +0.065 |
isk | +0.064 |
Neg logit contributions | |
ursion | -0.100 |
anna | -0.097 |
bet | -0.096 |
Sure | -0.093 |
sur | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
es | +0.034 |
ts | +0.028 |
rats | +0.028 |
isk | +0.028 |
adoes | +0.027 |
Neg logit contributions | |
bet | -0.067 |
Sure | -0.065 |
ursion | -0.065 |
anna | -0.065 |
Of | -0.065 |
Token | page |
Token ID | 2443 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
es | +0.003 |
rats | +0.002 |
stains | +0.002 |
ts | +0.002 |
marks | +0.002 |
Neg logit contributions | |
ursion | -0.004 |
bet | -0.004 |
anna | -0.004 |
Of | -0.004 |
Sure | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
es | +0.035 |
ts | +0.034 |
rats | +0.033 |
adoes | +0.032 |
stains | +0.032 |
Neg logit contributions | |
ursion | -0.045 |
anna | -0.043 |
bet | -0.043 |
Sure | -0.041 |
sur | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
es | +0.023 |
isk | +0.022 |
adoes | +0.020 |
bes | +0.020 |
ts | +0.020 |
Neg logit contributions | |
bet | -0.038 |
pleasure | -0.037 |
ursion | -0.036 |
anna | -0.036 |
Sure | -0.036 |
Token | pizza |
Token ID | 14256 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
es | +0.006 |
rats | +0.006 |
stains | +0.006 |
marks | +0.006 |
ts | +0.006 |
Neg logit contributions | |
ursion | -0.010 |
bet | -0.009 |
anna | -0.009 |
Of | -0.009 |
Sure | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
es | +0.106 |
ts | +0.105 |
adoes | +0.102 |
rats | +0.100 |
isk | +0.099 |
Neg logit contributions | |
ursion | -0.150 |
bet | -0.146 |
anna | -0.144 |
sur | -0.141 |
Sure | -0.140 |
Token | and |
Token ID | 290 |
Feature activation | -8.29e-03 |
Pos logit contributions | |
es | +0.034 |
isk | +0.031 |
ts | +0.030 |
rats | +0.030 |
adoes | +0.030 |
Neg logit contributions | |
bet | -0.061 |
Sure | -0.060 |
anna | -0.059 |
pleasure | -0.059 |
Of | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +4.43e-04 |
Pos logit contributions | |
es | +0.007 |
rats | +0.006 |
ts | +0.005 |
stains | +0.005 |
marks | +0.005 |
Neg logit contributions | |
ursion | -0.018 |
bet | -0.018 |
anna | -0.018 |
Of | -0.017 |
Sure | -0.017 |
Token | page |
Token ID | 2443 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ursion | +0.001 |
bet | +0.001 |
anna | +0.001 |
Of | +0.001 |
Sure | +0.001 |
Neg logit contributions | |
es | -0.001 |
rats | -0.000 |
stains | -0.000 |
ts | -0.000 |
marks | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
es | +0.028 |
ts | +0.028 |
rats | +0.027 |
adoes | +0.026 |
isk | +0.026 |
Neg logit contributions | |
ursion | -0.044 |
anna | -0.043 |
bet | -0.042 |
Sure | -0.040 |
sur | -0.040 |
Token | sorry |
Token ID | 7926 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
es | +0.065 |
rats | +0.060 |
isk | +0.059 |
stains | +0.058 |
ts | +0.058 |
Neg logit contributions | |
bet | -0.061 |
ursion | -0.060 |
pleasure | -0.057 |
Of | -0.056 |
sur | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
es | +0.077 |
ts | +0.075 |
rats | +0.074 |
stains | +0.070 |
bes | +0.070 |
Neg logit contributions | |
bet | -0.104 |
ursion | -0.103 |
anna | -0.100 |
Sure | -0.100 |
Of | -0.100 |
Token | They |
Token ID | 1119 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
es | +0.020 |
mice | +0.017 |
rats | +0.016 |
not | +0.016 |
stains | +0.016 |
Neg logit contributions | |
ursion | -0.037 |
anna | -0.037 |
ya | -0.034 |
ounded | -0.034 |
bet | -0.034 |
Token | had |
Token ID | 550 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
es | +0.038 |
rats | +0.035 |
ts | +0.035 |
stains | +0.035 |
not | +0.034 |
Neg logit contributions | |
ursion | -0.037 |
anna | -0.035 |
bet | -0.034 |
Sure | -0.033 |
pleasure | -0.032 |
Token | been |
Token ID | 587 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
es | +0.028 |
iders | +0.025 |
bes | +0.024 |
adoes | +0.024 |
ings | +0.023 |
Neg logit contributions | |
bet | -0.028 |
ursion | -0.027 |
pleasure | -0.026 |
Of | -0.026 |
sur | -0.025 |
Token | mean |
Token ID | 1612 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
es | +0.029 |
rats | +0.026 |
ts | +0.025 |
stains | +0.024 |
not | +0.024 |
Neg logit contributions | |
ursion | -0.049 |
bet | -0.047 |
anna | -0.047 |
Sure | -0.046 |
Of | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
es | +0.098 |
rats | +0.090 |
ts | +0.089 |
stains | +0.087 |
marks | +0.085 |
Neg logit contributions | |
ursion | -0.123 |
bet | -0.119 |
anna | -0.118 |
Sure | -0.112 |
Of | -0.112 |
Token | greedy |
Token ID | 31828 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
es | +0.013 |
rats | +0.012 |
ts | +0.012 |
stains | +0.012 |
not | +0.011 |
Neg logit contributions | |
ursion | -0.022 |
anna | -0.021 |
bet | -0.021 |
Sure | -0.020 |
pleasure | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
es | +0.089 |
rats | +0.081 |
ts | +0.080 |
stains | +0.078 |
marks | +0.076 |
Neg logit contributions | |
ursion | -0.155 |
bet | -0.152 |
anna | -0.150 |
Of | -0.143 |
Sure | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
es | +0.017 |
mice | +0.015 |
not | +0.015 |
rats | +0.014 |
stains | +0.014 |
Neg logit contributions | |
ursion | -0.033 |
anna | -0.033 |
ounded | -0.030 |
ya | -0.030 |
sur | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
es | +0.036 |
rats | +0.034 |
ts | +0.033 |
stains | +0.033 |
marks | +0.032 |
Neg logit contributions | |
ursion | -0.034 |
bet | -0.032 |
anna | -0.032 |
Sure | -0.030 |
Of | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
es | +0.013 |
rats | +0.011 |
stains | +0.011 |
ts | +0.010 |
marks | +0.010 |
Neg logit contributions | |
ursion | -0.026 |
bet | -0.025 |
anna | -0.025 |
Sure | -0.024 |
Of | -0.024 |
Token | so |
Token ID | 523 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
es | +0.050 |
not | +0.047 |
rats | +0.047 |
stains | +0.046 |
marks | +0.045 |
Neg logit contributions | |
ursion | -0.041 |
anna | -0.038 |
bet | -0.037 |
Sure | -0.035 |
sur | -0.034 |
Token | she |
Token ID | 673 |
Feature activation | +3.66e-04 |
Pos logit contributions | |
ursion | +0.074 |
anna | +0.070 |
bet | +0.070 |
pleasure | +0.066 |
sur | +0.065 |
Neg logit contributions | |
es | -0.058 |
not | -0.055 |
rats | -0.055 |
marks | -0.053 |
stains | -0.052 |
Token | set |
Token ID | 900 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ursion | +0.001 |
pleasure | +0.001 |
bet | +0.001 |
Sure | +0.001 |
anna | +0.001 |
Neg logit contributions | |
es | -0.001 |
not | -0.001 |
ts | -0.001 |
rats | -0.000 |
marks | -0.000 |
Token | off |
Token ID | 572 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
ursion | +0.080 |
bet | +0.077 |
anna | +0.076 |
Sure | +0.073 |
sur | +0.071 |
Neg logit contributions | |
es | -0.080 |
rats | -0.077 |
stains | -0.073 |
ts | -0.072 |
mice | -0.071 |
Token | for |
Token ID | 329 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
ursion | +0.079 |
bet | +0.076 |
anna | +0.076 |
Sure | +0.073 |
Of | +0.072 |
Neg logit contributions | |
es | -0.052 |
rats | -0.049 |
ts | -0.047 |
stains | -0.046 |
marks | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
es | +0.067 |
rats | +0.057 |
stains | +0.054 |
ts | +0.053 |
marks | +0.052 |
Neg logit contributions | |
ursion | -0.173 |
bet | -0.169 |
anna | -0.167 |
Sure | -0.161 |
Of | -0.161 |
Token | walk |
Token ID | 2513 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
ursion | +0.032 |
anna | +0.030 |
Shall | +0.029 |
bet | +0.029 |
eal | +0.028 |
Neg logit contributions | |
not | -0.015 |
puzzles | -0.015 |
sandwiches | -0.014 |
cookies | -0.014 |
rats | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
ursion | +0.088 |
bet | +0.086 |
anna | +0.086 |
pleasure | +0.086 |
Of | +0.084 |
Neg logit contributions | |
es | -0.028 |
not | -0.019 |
ts | -0.019 |
marks | -0.019 |
rats | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
es | +0.008 |
marks | +0.007 |
not | +0.007 |
pictures | +0.007 |
stains | +0.007 |
Neg logit contributions | |
ursion | -0.016 |
anna | -0.015 |
sur | -0.015 |
ya | -0.014 |
mber | -0.014 |
Token | passed |
Token ID | 3804 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
es | +0.024 |
ts | +0.022 |
not | +0.021 |
rats | +0.021 |
marks | +0.020 |
Neg logit contributions | |
ursion | -0.032 |
pleasure | -0.031 |
Of | -0.029 |
anna | -0.029 |
bet | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
es | +0.059 |
ts | +0.055 |
rats | +0.054 |
stains | +0.051 |
mice | +0.050 |
Neg logit contributions | |
ursion | -0.091 |
bet | -0.090 |
anna | -0.088 |
Sure | -0.086 |
Of | -0.086 |
Token | He |
Token ID | 679 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
es | +0.012 |
not | +0.012 |
rats | +0.011 |
mice | +0.011 |
blood | +0.011 |
Neg logit contributions | |
ursion | -0.021 |
anna | -0.021 |
bet | -0.019 |
ounded | -0.019 |
ya | -0.019 |
Token | wished |
Token ID | 16555 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
es | +0.039 |
rats | +0.036 |
ts | +0.035 |
stains | +0.035 |
marks | +0.035 |
Neg logit contributions | |
ursion | -0.032 |
bet | -0.030 |
anna | -0.030 |
Of | -0.028 |
Sure | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | +9.06e-04 |
Pos logit contributions | |
ursion | +0.029 |
Sure | +0.028 |
bet | +0.028 |
anna | +0.028 |
Of | +0.028 |
Neg logit contributions | |
es | -0.041 |
rats | -0.038 |
stains | -0.038 |
ts | -0.037 |
marks | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | +2.66e-04 |
Pos logit contributions | |
Of | +0.001 |
anna | +0.001 |
ursion | +0.001 |
bet | +0.001 |
sur | +0.001 |
Neg logit contributions | |
ings | -0.002 |
es | -0.002 |
marks | -0.002 |
adoes | -0.002 |
slices | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ursion | +0.000 |
anna | +0.000 |
bet | +0.000 |
pleasure | +0.000 |
Of | +0.000 |
Neg logit contributions | |
es | -0.000 |
stains | -0.000 |
rats | -0.000 |
ings | -0.000 |
bes | -0.000 |
Token | rude |
Token ID | 22066 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
es | +0.079 |
rats | +0.071 |
ts | +0.069 |
stains | +0.068 |
marks | +0.067 |
Neg logit contributions | |
ursion | -0.135 |
bet | -0.130 |
anna | -0.130 |
Of | -0.124 |
Sure | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
es | +0.064 |
ts | +0.059 |
rats | +0.058 |
stains | +0.056 |
marks | +0.054 |
Neg logit contributions | |
ursion | -0.104 |
bet | -0.102 |
anna | -0.102 |
Of | -0.096 |
sur | -0.096 |
Token | mean |
Token ID | 1612 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
es | +0.013 |
rats | +0.012 |
ts | +0.011 |
stains | +0.011 |
marks | +0.011 |
Neg logit contributions | |
ursion | -0.022 |
bet | -0.021 |
anna | -0.021 |
Of | -0.020 |
Sure | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
es | +0.067 |
rats | +0.060 |
ts | +0.060 |
stains | +0.058 |
marks | +0.056 |
Neg logit contributions | |
ursion | -0.116 |
bet | -0.113 |
anna | -0.112 |
Of | -0.107 |
Sure | -0.107 |
Token | He |
Token ID | 679 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
es | +0.018 |
not | +0.017 |
rats | +0.016 |
marks | +0.015 |
bones | +0.015 |
Neg logit contributions | |
ursion | -0.029 |
anna | -0.028 |
ya | -0.026 |
ounded | -0.026 |
bet | -0.026 |