Token | . |
Token ID | 13 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.006 |
risk | +0.006 |
top | +0.005 |
anish | +0.005 |
Neg logit contributions | |
aky | -0.011 |
spac | -0.011 |
ev | -0.011 |
v | -0.011 |
polar | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
v | +0.004 |
aky | +0.004 |
spac | +0.004 |
b | +0.004 |
ev | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
anish | -0.004 |
risk | -0.004 |
� | -0.003 |
Token | used |
Token ID | 973 |
Feature activation | -8.81e-04 |
Pos logit contributions | |
lot | +0.011 |
temptation | +0.010 |
anish | +0.010 |
aroma | +0.010 |
face | +0.010 |
Neg logit contributions | |
spac | -0.011 |
v | -0.011 |
aky | -0.011 |
ang | -0.011 |
ev | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -3.35e-04 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
anish | -0.001 |
lot | -0.001 |
consequences | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
v | +0.000 |
spac | +0.000 |
aky | +0.000 |
b | +0.000 |
ev | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
risk | -0.000 |
consequences | -0.000 |
deed | -0.000 |
Token | itt |
Token ID | 715 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
temptation | +0.019 |
anish | +0.018 |
risk | +0.018 |
lot | +0.018 |
consequences | +0.017 |
Neg logit contributions | |
v | -0.021 |
aky | -0.019 |
ev | -0.019 |
ang | -0.018 |
spac | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.69e-03 |
Pos logit contributions | |
temptation | +0.069 |
risk | +0.066 |
lot | +0.065 |
anish | +0.063 |
consequences | +0.063 |
Neg logit contributions | |
v | -0.058 |
spac | -0.058 |
aky | -0.055 |
ev | -0.053 |
ang | -0.053 |
Token | take |
Token ID | 1011 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.003 |
ev | +0.003 |
b | +0.003 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.003 |
lot | -0.003 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
temptation | +0.003 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
lot | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
b | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
temptation | +0.020 |
anish | +0.019 |
risk | +0.019 |
� | +0.019 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.015 |
wrapped | -0.014 |
b | -0.014 |
Token | pan |
Token ID | 3425 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
temptation | +0.012 |
anish | +0.011 |
wered | +0.011 |
deed | +0.011 |
� | +0.011 |
Neg logit contributions | |
spac | -0.013 |
v | -0.012 |
aky | -0.012 |
wrapped | -0.011 |
b | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
anish | +0.076 |
temptation | +0.074 |
wered | +0.073 |
risk | +0.072 |
consequence | +0.071 |
Neg logit contributions | |
v | -0.050 |
aky | -0.045 |
wrapped | -0.044 |
ev | -0.044 |
ang | -0.044 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ang | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
consequences | -0.003 |
anish | -0.003 |
lot | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | -6.13e-04 |
Pos logit contributions | |
lot | +0.009 |
temptation | +0.008 |
risk | +0.007 |
� | +0.007 |
Enjoy | +0.007 |
Neg logit contributions | |
v | -0.017 |
spac | -0.017 |
aky | -0.016 |
ang | -0.016 |
azz | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
consequences | -0.001 |
� | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
azz | +0.002 |
aky | +0.002 |
ev | +0.002 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.001 |
scent | -0.001 |
Dogs | -0.001 |
others | -0.001 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.010 |
� | +0.010 |
Dogs | +0.009 |
risk | +0.009 |
Neg logit contributions | |
spac | -0.020 |
aky | -0.018 |
v | -0.018 |
lov | -0.018 |
astronauts | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
anish | +0.088 |
wered | +0.083 |
temptation | +0.082 |
consequence | +0.081 |
risk | +0.080 |
Neg logit contributions | |
v | -0.043 |
wrapped | -0.040 |
aky | -0.040 |
said | -0.039 |
b | -0.038 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.007 |
consequences | +0.007 |
risk | +0.007 |
wered | +0.006 |
Neg logit contributions | |
spac | -0.012 |
aky | -0.012 |
v | -0.012 |
Tw | -0.011 |
wrapped | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-03 |
Pos logit contributions | |
temptation | +0.011 |
lot | +0.010 |
risk | +0.010 |
anish | +0.009 |
consequences | +0.009 |
Neg logit contributions | |
v | -0.014 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
lot | -0.005 |
anish | -0.005 |
consequences | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
spac | +0.002 |
aky | +0.002 |
v | +0.002 |
polar | +0.001 |
trapped | +0.001 |
Neg logit contributions | |
lot | -0.001 |
risk | -0.001 |
temptation | -0.001 |
top | -0.001 |
anish | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
temptation | +0.003 |
risk | +0.003 |
anish | +0.003 |
lot | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
b | -0.002 |
Token | numbering |
Token ID | 47622 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
v | +0.016 |
spac | +0.015 |
b | +0.015 |
z | +0.015 |
wrapped | +0.014 |
Neg logit contributions | |
temptation | -0.016 |
anish | -0.016 |
risk | -0.015 |
consequences | -0.015 |
wered | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
anish | +0.014 |
� | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.013 |
spac | -0.012 |
aky | -0.012 |
b | -0.012 |
ev | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
v | +0.011 |
spac | +0.010 |
aky | +0.010 |
ev | +0.010 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.011 |
risk | -0.010 |
lot | -0.010 |
anish | -0.010 |
consequences | -0.010 |
Token | m |
Token ID | 285 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
temptation | +0.006 |
lot | +0.006 |
consequences | +0.006 |
risk | +0.006 |
anish | +0.005 |
Neg logit contributions | |
spac | -0.008 |
v | -0.008 |
aky | -0.007 |
ev | -0.007 |
azz | -0.007 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
temptation | +0.019 |
risk | +0.018 |
anish | +0.018 |
lot | +0.018 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.019 |
aky | -0.018 |
spac | -0.018 |
ev | -0.017 |
ang | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
temptation | +0.073 |
anish | +0.070 |
risk | +0.069 |
wered | +0.068 |
lot | +0.068 |
Neg logit contributions | |
v | -0.056 |
b | -0.051 |
aky | -0.051 |
ev | -0.050 |
ang | -0.049 |
Token | She |
Token ID | 1375 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
risk | +0.004 |
temptation | +0.004 |
aroma | +0.004 |
consequences | +0.004 |
anish | +0.004 |
Neg logit contributions | |
spac | -0.002 |
azz | -0.002 |
v | -0.002 |
says | -0.002 |
Robo | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | +8.63e-04 |
Pos logit contributions | |
lot | +0.008 |
anish | +0.008 |
top | +0.008 |
others | +0.007 |
habits | +0.007 |
Neg logit contributions | |
spac | -0.011 |
aky | -0.011 |
ang | -0.011 |
ev | -0.011 |
eddy | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
lot | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | lost |
Token ID | 2626 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
azz | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
lot | -0.007 |
risk | -0.007 |
consequences | -0.007 |
anish | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
temptation | +0.003 |
wered | +0.003 |
risk | +0.003 |
anish | +0.003 |
consequence | +0.003 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
eddy | -0.002 |
aky | -0.002 |
wrapped | -0.002 |
Token | Sue |
Token ID | 26089 |
Feature activation | +9.21e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.003 |
ang | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
consequences | -0.005 |
lot | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -9.20e-06 |
Pos logit contributions | |
lot | +0.007 |
others | +0.006 |
stomach | +0.006 |
temptation | +0.006 |
habits | +0.006 |
Neg logit contributions | |
spac | -0.016 |
v | -0.015 |
azz | -0.014 |
polar | -0.014 |
Pluto | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -4.05e-04 |
Token | m |
Token ID | 285 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
azz | +0.001 |
ev | +0.001 |
Neg logit contributions | |
lot | -0.001 |
temptation | -0.000 |
risk | -0.000 |
scent | -0.000 |
consequences | -0.000 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
temptation | +0.012 |
lot | +0.011 |
risk | +0.010 |
� | +0.010 |
anish | +0.010 |
Neg logit contributions | |
spac | -0.016 |
v | -0.015 |
aky | -0.015 |
ev | -0.014 |
Tw | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
anish | +0.087 |
wered | +0.082 |
temptation | +0.081 |
consequence | +0.080 |
risk | +0.079 |
Neg logit contributions | |
v | -0.041 |
wrapped | -0.039 |
aky | -0.038 |
said | -0.038 |
b | -0.037 |
Token | much |
Token ID | 881 |
Feature activation | +7.12e-04 |
Pos logit contributions | |
v | +0.009 |
spac | +0.008 |
aky | +0.008 |
ev | +0.008 |
ang | +0.008 |
Neg logit contributions | |
temptation | -0.009 |
risk | -0.008 |
lot | -0.008 |
anish | -0.008 |
consequences | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
risk | +0.001 |
consequences | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ang | -0.001 |
ev | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
lot | -0.003 |
consequences | -0.003 |
Token | wore |
Token ID | 12408 |
Feature activation | -2.57e-04 |
Pos logit contributions | |
lot | +0.006 |
temptation | +0.006 |
risk | +0.005 |
� | +0.005 |
stomach | +0.005 |
Neg logit contributions | |
v | -0.010 |
spac | -0.010 |
aky | -0.010 |
ang | -0.010 |
ev | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
lot | +0.014 |
consequences | +0.014 |
anish | +0.014 |
Neg logit contributions | |
v | -0.012 |
aky | -0.012 |
spac | -0.012 |
ev | -0.011 |
b | -0.011 |
Token | sauce |
Token ID | 10746 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
wrapped | +0.022 |
spac | +0.022 |
v | +0.022 |
said | +0.022 |
says | +0.021 |
Neg logit contributions | |
temptation | -0.023 |
risk | -0.022 |
deed | -0.022 |
anish | -0.022 |
consequences | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
lot | +0.014 |
anish | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.011 |
spac | -0.011 |
aky | -0.011 |
ev | -0.010 |
ang | -0.010 |
Token | cheese |
Token ID | 9891 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
wrapped | +0.008 |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
says | +0.008 |
Neg logit contributions | |
temptation | -0.013 |
risk | -0.013 |
deed | -0.012 |
anish | -0.012 |
consequence | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.009 |
risk | +0.009 |
anish | +0.009 |
consequences | +0.009 |
Neg logit contributions | |
v | -0.009 |
spac | -0.009 |
aky | -0.009 |
ev | -0.008 |
ang | -0.008 |
Token | topp |
Token ID | 23126 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
wrapped | +0.007 |
b | +0.007 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
anish | -0.005 |
deed | -0.005 |
� | -0.005 |
Token | ings |
Token ID | 654 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
temptation | +0.034 |
risk | +0.032 |
consequences | +0.027 |
� | +0.026 |
wered | +0.026 |
Neg logit contributions | |
v | -0.095 |
aky | -0.090 |
spac | -0.088 |
b | -0.088 |
ev | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
v | +0.006 |
wrapped | +0.005 |
aky | +0.005 |
spac | +0.005 |
said | +0.005 |
Neg logit contributions | |
risk | -0.009 |
temptation | -0.008 |
deed | -0.008 |
wered | -0.008 |
consequence | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +3.67e-04 |
Pos logit contributions | |
v | +0.006 |
spac | +0.005 |
aky | +0.005 |
ev | +0.005 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
lot | -0.005 |
anish | -0.005 |
consequences | -0.005 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
lot | +0.000 |
grapes | +0.000 |
temptation | +0.000 |
aroma | +0.000 |
fruits | +0.000 |
Neg logit contributions | |
spac | -0.000 |
v | -0.000 |
aky | -0.000 |
ang | -0.000 |
azz | -0.000 |
Token | them |
Token ID | 606 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.001 |
risk | +0.001 |
anish | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
v | +0.009 |
aky | +0.008 |
spac | +0.008 |
b | +0.008 |
ents | +0.008 |
Neg logit contributions | |
temptation | -0.013 |
� | -0.013 |
anish | -0.013 |
aroma | -0.013 |
risk | -0.013 |
Token | number |
Token ID | 1271 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
wrapped | +0.003 |
ck | +0.003 |
spac | +0.003 |
said | +0.003 |
z | +0.003 |
Neg logit contributions | |
consequences | -0.004 |
mons | -0.004 |
grapes | -0.004 |
temptation | -0.004 |
lot | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
anish | +0.012 |
consequences | +0.011 |
� | +0.011 |
Neg logit contributions | |
v | -0.012 |
spac | -0.012 |
aky | -0.012 |
ev | -0.011 |
b | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
aky | +0.006 |
ev | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.006 |
anish | -0.006 |
lot | -0.006 |
� | -0.006 |
Token | m |
Token ID | 285 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
temptation | +0.008 |
lot | +0.007 |
risk | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.009 |
spac | -0.009 |
aky | -0.009 |
ev | -0.009 |
ang | -0.009 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
temptation | +0.020 |
risk | +0.019 |
anish | +0.019 |
lot | +0.019 |
consequences | +0.019 |
Neg logit contributions | |
v | -0.018 |
aky | -0.017 |
spac | -0.016 |
ang | -0.016 |
ev | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
temptation | +0.076 |
wered | +0.072 |
anish | +0.072 |
lot | +0.071 |
risk | +0.071 |
Neg logit contributions | |
v | -0.049 |
b | -0.045 |
aky | -0.045 |
ev | -0.044 |
wrapped | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
aky | +0.006 |
ev | +0.005 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
anish | -0.006 |
lot | -0.006 |
consequences | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +6.99e-04 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
anish | +0.013 |
lot | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.014 |
spac | -0.013 |
aky | -0.013 |
ev | -0.013 |
ang | -0.012 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
lot | +0.001 |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ang | -0.001 |
ev | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
lot | +0.012 |
anish | +0.011 |
consequences | +0.011 |
Neg logit contributions | |
v | -0.033 |
spac | -0.033 |
aky | -0.033 |
ev | -0.031 |
ang | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
temptation | +0.016 |
anish | +0.015 |
risk | +0.015 |
lot | +0.015 |
� | +0.015 |
Neg logit contributions | |
v | -0.012 |
aky | -0.011 |
spac | -0.011 |
b | -0.010 |
ev | -0.010 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
temptation | +0.014 |
risk | +0.013 |
lot | +0.013 |
anish | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.017 |
spac | -0.016 |
aky | -0.016 |
ev | -0.016 |
ang | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
temptation | +0.015 |
lot | +0.014 |
anish | +0.014 |
risk | +0.014 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.015 |
ev | -0.015 |
ang | -0.015 |
Token | sauce |
Token ID | 10746 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
wrapped | +0.006 |
says | +0.006 |
Neg logit contributions | |
temptation | -0.006 |
anish | -0.005 |
risk | -0.005 |
� | -0.005 |
deed | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
temptation | +0.015 |
lot | +0.014 |
risk | +0.014 |
anish | +0.014 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.017 |
spac | -0.017 |
aky | -0.017 |
ev | -0.016 |
ang | -0.016 |
Token | topp |
Token ID | 23126 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
aky | +0.004 |
wrapped | +0.004 |
says | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
anish | -0.003 |
� | -0.003 |
risk | -0.003 |
deed | -0.003 |
Token | ings |
Token ID | 654 |
Feature activation | +1.50e-04 |
Pos logit contributions | |
temptation | +0.030 |
risk | +0.027 |
� | +0.024 |
anish | +0.023 |
consequences | +0.023 |
Neg logit contributions | |
v | -0.096 |
aky | -0.092 |
spac | -0.091 |
b | -0.088 |
ev | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
temptation | +0.000 |
risk | +0.000 |
anish | +0.000 |
deed | +0.000 |
� | +0.000 |
Neg logit contributions | |
v | -0.000 |
aky | -0.000 |
spac | -0.000 |
says | -0.000 |
ev | -0.000 |
Token | The |
Token ID | 383 |
Feature activation | +5.88e-04 |
Pos logit contributions | |
v | +0.003 |
aky | +0.003 |
spac | +0.003 |
b | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
anish | -0.002 |
Enjoy | -0.002 |
risk | -0.002 |
Token | people |
Token ID | 661 |
Feature activation | -4.10e-04 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
� | +0.001 |
risk | +0.001 |
Tears | +0.001 |
Neg logit contributions | |
spac | -0.001 |
v | -0.001 |
polar | -0.001 |
aky | -0.001 |
unicorn | -0.001 |
Token | who |
Token ID | 508 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.000 |
risk | -0.000 |
lot | -0.000 |
consequences | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
temptation | +0.005 |
lot | +0.005 |
� | +0.005 |
Enjoy | +0.005 |
risk | +0.005 |
Neg logit contributions | |
v | -0.006 |
aky | -0.006 |
spac | -0.005 |
b | -0.005 |
ck | -0.005 |
Token | always |
Token ID | 1464 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
lot | +0.006 |
temptation | +0.006 |
anish | +0.005 |
risk | +0.005 |
� | +0.005 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.006 |
ang | -0.006 |
Token | forgot |
Token ID | 16453 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
v | +0.011 |
spac | +0.010 |
aky | +0.010 |
ev | +0.010 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.013 |
risk | -0.012 |
anish | -0.012 |
lot | -0.012 |
consequences | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
said | +0.001 |
spac | +0.001 |
wrapped | +0.001 |
ents | +0.001 |
says | +0.001 |
Neg logit contributions | |
� | -0.002 |
anish | -0.002 |
temptation | -0.002 |
risk | -0.002 |
OM | -0.002 |
Token | m |
Token ID | 285 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
anish | +0.009 |
wered | +0.008 |
temptation | +0.008 |
risk | +0.008 |
Enjoy | +0.008 |
Neg logit contributions | |
spac | -0.006 |
v | -0.006 |
wrapped | -0.006 |
aky | -0.006 |
b | -0.006 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
temptation | +0.020 |
anish | +0.020 |
risk | +0.019 |
lot | +0.019 |
consequences | +0.019 |
Neg logit contributions | |
v | -0.015 |
ang | -0.014 |
aky | -0.013 |
ev | -0.013 |
b | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
wered | +0.079 |
anish | +0.078 |
temptation | +0.076 |
consequence | +0.071 |
consequences | +0.071 |
Neg logit contributions | |
wrapped | -0.044 |
v | -0.043 |
said | -0.043 |
b | -0.042 |
trapped | -0.040 |
Token | now |
Token ID | 783 |
Feature activation | +5.56e-03 |
Pos logit contributions | |
spac | +0.002 |
wrapped | +0.002 |
v | +0.002 |
aky | +0.002 |
said | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
anish | -0.002 |
risk | -0.002 |
� | -0.002 |
wered | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.008 |
risk | +0.008 |
consequences | +0.008 |
wered | +0.007 |
Neg logit contributions | |
spac | -0.006 |
v | -0.006 |
ev | -0.006 |
aky | -0.006 |
wrapped | -0.006 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -6.55e-03 |
Pos logit contributions | |
temptation | +0.010 |
anish | +0.010 |
risk | +0.010 |
lot | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.009 |
spac | -0.009 |
aky | -0.008 |
ev | -0.008 |
b | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -5.09e-03 |
Pos logit contributions | |
v | +0.009 |
spac | +0.009 |
aky | +0.009 |
ev | +0.009 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.007 |
lot | -0.007 |
anish | -0.007 |
consequences | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
v | +0.001 |
says | +0.001 |
spac | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.001 |
consequences | -0.001 |
aroma | -0.001 |
anish | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | -5.89e-04 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.009 |
risk | +0.009 |
anish | +0.009 |
consequences | +0.008 |
Neg logit contributions | |
v | -0.013 |
spac | -0.012 |
aky | -0.012 |
ev | -0.012 |
ang | -0.012 |
Token | very |
Token ID | 845 |
Feature activation | -6.27e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
azz | +0.001 |
ev | +0.001 |
aky | +0.001 |
Neg logit contributions | |
lot | -0.001 |
temptation | -0.001 |
fruits | -0.001 |
others | -0.001 |
grapes | -0.001 |
Token | pretty |
Token ID | 2495 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
v | +0.009 |
spac | +0.009 |
azz | +0.009 |
ev | +0.008 |
hole | +0.008 |
Neg logit contributions | |
lot | -0.008 |
temptation | -0.008 |
fruits | -0.007 |
others | -0.007 |
Enjoy | -0.007 |
Token | m |
Token ID | 285 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
temptation | +0.007 |
risk | +0.007 |
anish | +0.007 |
wered | +0.006 |
consequence | +0.006 |
Neg logit contributions | |
v | -0.006 |
spac | -0.005 |
aky | -0.005 |
ang | -0.005 |
ev | -0.005 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
temptation | +0.022 |
lot | +0.020 |
risk | +0.020 |
� | +0.020 |
anish | +0.019 |
Neg logit contributions | |
spac | -0.029 |
v | -0.028 |
aky | -0.028 |
ev | -0.026 |
Tw | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
anish | +0.076 |
temptation | +0.074 |
wered | +0.073 |
risk | +0.072 |
consequence | +0.071 |
Neg logit contributions | |
v | -0.050 |
aky | -0.045 |
wrapped | -0.044 |
ev | -0.044 |
ang | -0.044 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ang | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
consequences | -0.003 |
anish | -0.003 |
lot | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | -6.13e-04 |
Pos logit contributions | |
lot | +0.009 |
temptation | +0.008 |
risk | +0.007 |
� | +0.007 |
Enjoy | +0.007 |
Neg logit contributions | |
v | -0.017 |
spac | -0.017 |
aky | -0.016 |
ang | -0.016 |
azz | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
consequences | -0.001 |
� | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
azz | +0.002 |
aky | +0.002 |
ev | +0.002 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.001 |
scent | -0.001 |
Dogs | -0.001 |
others | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
deed | +0.001 |
risk | +0.001 |
consequences | +0.001 |
temptation | +0.001 |
anish | +0.001 |
Neg logit contributions | |
says | -0.000 |
said | -0.000 |
v | -0.000 |
Mir | -0.000 |
ents | -0.000 |
Token | took |
Token ID | 1718 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
lot | +0.008 |
pause | +0.007 |
eyes | +0.007 |
face | +0.006 |
top | +0.006 |
Neg logit contributions | |
spac | -0.012 |
eddy | -0.011 |
ang | -0.011 |
v | -0.011 |
azz | -0.011 |
Token | off |
Token ID | 572 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
temptation | +0.005 |
lot | +0.005 |
risk | +0.005 |
anish | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.006 |
ang | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
temptation | +0.015 |
anish | +0.014 |
consequences | +0.014 |
risk | +0.014 |
consequence | +0.014 |
Neg logit contributions | |
wrapped | -0.008 |
v | -0.007 |
ev | -0.007 |
spac | -0.007 |
Tw | -0.007 |
Token | m |
Token ID | 285 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
lot | +0.002 |
temptation | +0.002 |
risk | +0.002 |
fruits | +0.002 |
top | +0.002 |
Neg logit contributions | |
v | -0.003 |
aky | -0.003 |
spac | -0.003 |
azz | -0.003 |
ev | -0.003 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
lot | +0.012 |
anish | +0.011 |
consequences | +0.011 |
Neg logit contributions | |
spac | -0.015 |
v | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +7.88e-04 |
Pos logit contributions | |
temptation | +0.072 |
anish | +0.067 |
risk | +0.067 |
lot | +0.066 |
consequences | +0.066 |
Neg logit contributions | |
v | -0.051 |
spac | -0.049 |
aky | -0.048 |
ev | -0.046 |
ang | -0.045 |
Token | put |
Token ID | 1234 |
Feature activation | +2.35e-04 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
lot | +0.001 |
anish | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | them |
Token ID | 606 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
temptation | +0.000 |
risk | +0.000 |
anish | +0.000 |
lot | +0.000 |
consequences | +0.000 |
Neg logit contributions | |
v | -0.000 |
spac | -0.000 |
aky | -0.000 |
ev | -0.000 |
ang | -0.000 |
Token | down |
Token ID | 866 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
lot | +0.008 |
temptation | +0.008 |
risk | +0.008 |
pause | +0.007 |
top | +0.007 |
Neg logit contributions | |
spac | -0.013 |
v | -0.013 |
aky | -0.013 |
ev | -0.012 |
ang | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
temptation | +0.004 |
anish | +0.004 |
risk | +0.004 |
consequences | +0.004 |
deed | +0.004 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
wrapped | -0.003 |
ev | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.013 |
anish | +0.013 |
lot | +0.012 |
consequences | +0.012 |
Neg logit contributions | |
v | -0.008 |
spac | -0.008 |
aky | -0.007 |
ev | -0.007 |
ang | -0.007 |
Token | always |
Token ID | 1464 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ang | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
anish | -0.002 |
risk | -0.002 |
consequences | -0.002 |
Token | numbered |
Token ID | 25840 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
v | +0.010 |
spac | +0.010 |
aky | +0.010 |
ang | +0.009 |
ev | +0.009 |
Neg logit contributions | |
temptation | -0.010 |
risk | -0.009 |
lot | -0.009 |
anish | -0.009 |
consequences | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
temptation | +0.005 |
risk | +0.005 |
lot | +0.005 |
anish | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.005 |
ang | -0.005 |
Token | m |
Token ID | 285 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
risk | +0.002 |
consequences | +0.002 |
anish | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
azz | -0.002 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
anish | +0.012 |
lot | +0.012 |
consequences | +0.012 |
Neg logit contributions | |
v | -0.010 |
aky | -0.009 |
spac | -0.009 |
ev | -0.009 |
ang | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +6.94e-04 |
Pos logit contributions | |
temptation | +0.080 |
wered | +0.078 |
consequences | +0.075 |
consequence | +0.075 |
anish | +0.074 |
Neg logit contributions | |
v | -0.041 |
b | -0.040 |
ev | -0.037 |
ang | -0.037 |
trapped | -0.037 |
Token | never |
Token ID | 1239 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
� | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
b | -0.001 |
Token | lost |
Token ID | 2626 |
Feature activation | +7.29e-04 |
Pos logit contributions | |
temptation | +0.020 |
risk | +0.018 |
lot | +0.018 |
anish | +0.018 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.019 |
spac | -0.018 |
aky | -0.018 |
ev | -0.017 |
ang | -0.017 |
Token | them |
Token ID | 606 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
lot | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
b | -0.001 |
Token | again |
Token ID | 757 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
temptation | +0.017 |
anish | +0.016 |
lot | +0.016 |
consequences | +0.015 |
risk | +0.015 |
Neg logit contributions | |
v | -0.015 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
b | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
temptation | +0.005 |
� | +0.005 |
risk | +0.005 |
consequence | +0.005 |
anish | +0.005 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
z | -0.003 |
aky | -0.003 |
b | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
lot | +0.004 |
temptation | +0.004 |
� | +0.004 |
Tears | +0.004 |
Dogs | +0.004 |
Neg logit contributions | |
aky | -0.004 |
v | -0.004 |
spac | -0.004 |
b | -0.004 |
ev | -0.004 |
Token | used |
Token ID | 973 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
lot | +0.008 |
temptation | +0.007 |
risk | +0.007 |
pause | +0.007 |
fruits | +0.007 |
Neg logit contributions | |
v | -0.011 |
spac | -0.010 |
ang | -0.010 |
ev | -0.010 |
azz | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
ev | +0.008 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
lot | -0.008 |
risk | -0.007 |
anish | -0.007 |
consequences | -0.007 |
Token | m |
Token ID | 285 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.003 |
risk | +0.003 |
consequences | +0.003 |
anish | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ang | -0.003 |
azz | -0.003 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.007 |
risk | +0.007 |
anish | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
spac | -0.009 |
v | -0.009 |
aky | -0.008 |
ev | -0.008 |
Tw | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +3.56e-04 |
Pos logit contributions | |
temptation | +0.065 |
anish | +0.060 |
wered | +0.059 |
risk | +0.058 |
consequence | +0.058 |
Neg logit contributions | |
v | -0.059 |
b | -0.055 |
aky | -0.054 |
spac | -0.054 |
ev | -0.053 |
Token | make |
Token ID | 787 |
Feature activation | -4.15e-04 |
Pos logit contributions | |
temptation | +0.000 |
anish | +0.000 |
consequences | +0.000 |
risk | +0.000 |
lot | +0.000 |
Neg logit contributions | |
v | -0.001 |
spac | -0.000 |
aky | -0.000 |
ev | -0.000 |
b | -0.000 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
aky | +0.001 |
spac | +0.001 |
v | +0.001 |
azz | +0.000 |
ang | +0.000 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
consequences | -0.001 |
risk | -0.001 |
anish | -0.000 |
Token | balls |
Token ID | 21591 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
temptation | +0.035 |
risk | +0.032 |
lot | +0.032 |
anish | +0.032 |
consequences | +0.031 |
Neg logit contributions | |
v | -0.031 |
spac | -0.031 |
aky | -0.030 |
ev | -0.029 |
ang | -0.028 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
v | +0.011 |
spac | +0.011 |
aky | +0.011 |
ev | +0.010 |
ang | +0.010 |
Neg logit contributions | |
temptation | -0.017 |
risk | -0.016 |
anish | -0.016 |
lot | -0.015 |
consequences | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
temptation | +0.021 |
risk | +0.019 |
lot | +0.019 |
consequences | +0.019 |
anish | +0.018 |
Neg logit contributions | |
v | -0.025 |
spac | -0.025 |
aky | -0.025 |
ev | -0.024 |
ang | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
azz | +0.003 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
lot | -0.005 |
consequences | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.007 |
risk | +0.007 |
anish | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.009 |
spac | -0.008 |
aky | -0.008 |
ang | -0.008 |
ev | -0.008 |
Token | many |
Token ID | 867 |
Feature activation | -9.41e-04 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
aky | +0.005 |
ev | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
lot | -0.005 |
� | -0.005 |
Token | bruises |
Token ID | 42232 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
b | +0.001 |
ev | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
� | -0.001 |
Enjoy | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
temptation | +0.070 |
anish | +0.065 |
risk | +0.065 |
lot | +0.064 |
consequences | +0.063 |
Neg logit contributions | |
v | -0.052 |
spac | -0.049 |
aky | -0.049 |
ev | -0.046 |
b | -0.045 |
Token | cuts |
Token ID | 6630 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
anish | +0.003 |
� | +0.003 |
temptation | +0.003 |
risk | +0.003 |
deed | +0.003 |
Neg logit contributions | |
v | -0.003 |
aky | -0.003 |
spac | -0.003 |
wrapped | -0.003 |
b | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
temptation | +0.026 |
risk | +0.025 |
� | +0.025 |
anish | +0.025 |
lot | +0.024 |
Neg logit contributions | |
v | -0.023 |
aky | -0.021 |
spac | -0.021 |
ev | -0.020 |
b | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.007 |
lot | -0.007 |
anish | -0.007 |
consequences | -0.007 |
Token | also |
Token ID | 635 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
temptation | +0.012 |
lot | +0.011 |
risk | +0.011 |
anish | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.013 |
spac | -0.012 |
aky | -0.012 |
ev | -0.012 |
ang | -0.012 |
Token | ostr |
Token ID | 42387 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
temptation | +0.007 |
anish | +0.007 |
risk | +0.006 |
consequences | +0.006 |
lot | +0.006 |
Neg logit contributions | |
spac | -0.007 |
v | -0.007 |
aky | -0.006 |
ev | -0.006 |
polar | -0.006 |
Token | ich |
Token ID | 488 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
lot | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.001 |
b | -0.001 |
Token | pen |
Token ID | 3112 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
temptation | +0.027 |
consequences | +0.026 |
anish | +0.025 |
risk | +0.025 |
lot | +0.025 |
Neg logit contributions | |
v | -0.015 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
temptation | +0.009 |
risk | +0.008 |
lot | +0.008 |
anish | +0.008 |
consequences | +0.008 |
Neg logit contributions | |
v | -0.008 |
spac | -0.007 |
aky | -0.007 |
ev | -0.007 |
ang | -0.007 |
Token | Ost |
Token ID | 38919 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
aky | +0.003 |
v | +0.003 |
b | +0.003 |
spac | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
Dogs | -0.002 |
Enjoy | -0.002 |
anish | -0.002 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
temptation | +0.019 |
risk | +0.018 |
lot | +0.017 |
anish | +0.017 |
consequences | +0.017 |
Neg logit contributions | |
v | -0.031 |
aky | -0.030 |
spac | -0.030 |
ev | -0.029 |
ang | -0.029 |
Token | hes |
Token ID | 956 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
temptation | +0.059 |
risk | +0.055 |
lot | +0.054 |
anish | +0.054 |
consequences | +0.053 |
Neg logit contributions | |
v | -0.062 |
spac | -0.061 |
aky | -0.060 |
ev | -0.057 |
ang | -0.056 |
Token | are |
Token ID | 389 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
temptation | +0.009 |
� | +0.009 |
risk | +0.008 |
deed | +0.008 |
anish | +0.008 |
Neg logit contributions | |
v | -0.007 |
aky | -0.007 |
says | -0.007 |
b | -0.007 |
said | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
lot | +0.013 |
temptation | +0.012 |
fruits | +0.012 |
grapes | +0.012 |
stories | +0.011 |
Neg logit contributions | |
v | -0.019 |
spac | -0.018 |
ev | -0.018 |
azz | -0.017 |
ang | -0.017 |
Token | birds |
Token ID | 10087 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
consequences | -0.004 |
risk | -0.004 |
anish | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
temptation | +0.011 |
risk | +0.011 |
lot | +0.011 |
anish | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.013 |
spac | -0.013 |
aky | -0.012 |
ev | -0.012 |
ang | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
temptation | +0.003 |
anish | +0.003 |
risk | +0.003 |
consequences | +0.003 |
lot | +0.003 |
Neg logit contributions | |
v | -0.003 |
aky | -0.002 |
spac | -0.002 |
b | -0.002 |
ev | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
aky | +0.005 |
ev | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
lot | -0.004 |
risk | -0.004 |
anish | -0.004 |
consequences | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
temptation | +0.005 |
risk | +0.005 |
anish | +0.005 |
consequences | +0.004 |
lot | +0.004 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | called |
Token ID | 1444 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
lot | +0.001 |
temptation | +0.001 |
others | +0.001 |
fruits | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
ev | -0.002 |
aky | -0.001 |
azz | -0.001 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
temptation | +0.005 |
anish | +0.005 |
consequences | +0.005 |
risk | +0.005 |
� | +0.005 |
Neg logit contributions | |
spac | -0.006 |
v | -0.006 |
polar | -0.005 |
Pluto | -0.005 |
Tw | -0.005 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
lot | +0.014 |
anish | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.022 |
aky | -0.021 |
spac | -0.021 |
ev | -0.020 |
ang | -0.020 |
Token | hes |
Token ID | 956 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
temptation | +0.065 |
risk | +0.061 |
anish | +0.059 |
lot | +0.058 |
deed | +0.058 |
Neg logit contributions | |
v | -0.059 |
aky | -0.057 |
spac | -0.055 |
b | -0.052 |
ang | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
temptation | +0.016 |
risk | +0.015 |
� | +0.014 |
anish | +0.014 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.010 |
aky | -0.009 |
spac | -0.009 |
said | -0.009 |
wrapped | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
v | +0.005 |
aky | +0.005 |
spac | +0.005 |
b | +0.005 |
ev | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
lot | -0.005 |
risk | -0.004 |
anish | -0.004 |
� | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
aky | +0.004 |
ev | +0.004 |
ang | +0.004 |
Neg logit contributions | |
lot | -0.003 |
temptation | -0.003 |
anish | -0.003 |
risk | -0.003 |
habits | -0.003 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
temptation | +0.005 |
risk | +0.004 |
lot | +0.004 |
anish | +0.004 |
consequences | +0.004 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.002 |
ang | -0.002 |
Token | ostr |
Token ID | 42387 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
lot | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | ich |
Token ID | 488 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
lot | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.001 |
ev | -0.001 |
b | -0.001 |
Token | pen |
Token ID | 3112 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
temptation | +0.016 |
risk | +0.014 |
anish | +0.014 |
lot | +0.014 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.012 |
spac | -0.012 |
aky | -0.011 |
ev | -0.011 |
ang | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
temptation | +0.003 |
anish | +0.003 |
lot | +0.003 |
risk | +0.003 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
ang | -0.003 |
Token | Ost |
Token ID | 38919 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
aky | +0.012 |
v | +0.011 |
b | +0.011 |
ev | +0.011 |
spac | +0.011 |
Neg logit contributions | |
temptation | -0.005 |
lot | -0.005 |
Enjoy | -0.005 |
Dogs | -0.005 |
anish | -0.004 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
temptation | +0.017 |
risk | +0.016 |
lot | +0.015 |
anish | +0.015 |
consequences | +0.015 |
Neg logit contributions | |
v | -0.030 |
aky | -0.029 |
spac | -0.029 |
ev | -0.028 |
ang | -0.027 |
Token | hes |
Token ID | 956 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
temptation | +0.057 |
lot | +0.053 |
risk | +0.053 |
anish | +0.053 |
consequences | +0.051 |
Neg logit contributions | |
v | -0.062 |
spac | -0.062 |
aky | -0.060 |
ev | -0.058 |
ang | -0.057 |
Token | are |
Token ID | 389 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
temptation | +0.006 |
� | +0.006 |
anish | +0.006 |
risk | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.006 |
aky | -0.006 |
says | -0.005 |
b | -0.005 |
spac | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
lot | +0.011 |
temptation | +0.011 |
fruits | +0.010 |
grapes | +0.010 |
rules | +0.010 |
Neg logit contributions | |
v | -0.015 |
spac | -0.015 |
ev | -0.014 |
azz | -0.014 |
eddy | -0.014 |
Token | birds |
Token ID | 10087 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
aky | +0.005 |
ev | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
consequences | -0.004 |
risk | -0.004 |
anish | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
temptation | +0.008 |
lot | +0.007 |
risk | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
spac | -0.012 |
v | -0.012 |
ev | -0.011 |
aky | -0.011 |
azz | -0.011 |
Token | ongo |
Token ID | 25162 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
temptation | +0.010 |
� | +0.010 |
risk | +0.010 |
lot | +0.010 |
deed | +0.009 |
Neg logit contributions | |
spac | -0.012 |
v | -0.011 |
aky | -0.011 |
ck | -0.011 |
astronauts | -0.011 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
lot | +0.016 |
others | +0.013 |
fruits | +0.013 |
habits | +0.012 |
foods | +0.012 |
Neg logit contributions | |
spac | -0.039 |
v | -0.037 |
azz | -0.036 |
ang | -0.036 |
inery | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
temptation | +0.005 |
anish | +0.005 |
� | +0.005 |
aroma | +0.005 |
risk | +0.005 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
z | -0.005 |
polar | -0.005 |
b | -0.005 |
Token | eat |
Token ID | 4483 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
temptation | +0.005 |
consequences | +0.005 |
anish | +0.005 |
Tears | +0.004 |
risk | +0.004 |
Neg logit contributions | |
v | -0.005 |
spac | -0.004 |
polar | -0.004 |
wrapped | -0.004 |
Tw | -0.004 |
Token | av |
Token ID | 1196 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
temptation | +0.007 |
anish | +0.007 |
risk | +0.007 |
� | +0.006 |
consequence | +0.006 |
Neg logit contributions | |
v | -0.010 |
spac | -0.010 |
aky | -0.009 |
b | -0.009 |
polar | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
lot | +0.031 |
temptation | +0.030 |
foods | +0.029 |
fruits | +0.029 |
deed | +0.029 |
Neg logit contributions | |
spac | -0.021 |
polar | -0.018 |
v | -0.018 |
Georg | -0.017 |
Robo | -0.017 |
Token | ados |
Token ID | 22484 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
lot | +0.041 |
temptation | +0.039 |
risk | +0.038 |
consequence | +0.036 |
pause | +0.035 |
Neg logit contributions | |
v | -0.079 |
ents | -0.075 |
ev | -0.073 |
spac | -0.071 |
b | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.003 |
risk | +0.003 |
anish | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
spac | -0.005 |
v | -0.005 |
aky | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | One |
Token ID | 1881 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
temptation | +0.011 |
lot | +0.011 |
risk | +0.010 |
anish | +0.010 |
� | +0.010 |
Neg logit contributions | |
v | -0.011 |
aky | -0.011 |
spac | -0.010 |
ev | -0.010 |
ang | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | +5.48e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.002 |
deed | -0.001 |
anish | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
temptation | +0.009 |
anish | +0.008 |
consequences | +0.008 |
risk | +0.008 |
aroma | +0.008 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
aky | -0.005 |
b | -0.005 |
ev | -0.005 |
Token | old |
Token ID | 1468 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
fruits | +0.001 |
law | +0.001 |
stomach | +0.001 |
Neg logit contributions | |
v | -0.001 |
b | -0.001 |
ck | -0.001 |
ev | -0.001 |
aky | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +9.68e-04 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
wrapped | +0.004 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.007 |
anish | -0.007 |
wered | -0.007 |
Enjoy | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
consequences | +0.001 |
lot | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -9.34e-04 |
Pos logit contributions | |
lot | +0.006 |
temptation | +0.006 |
risk | +0.005 |
anish | +0.005 |
� | +0.005 |
Neg logit contributions | |
spac | -0.011 |
v | -0.011 |
aky | -0.010 |
azz | -0.010 |
ev | -0.010 |
Token | m |
Token ID | 285 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
polar | +0.001 |
z | +0.001 |
ev | +0.001 |
Neg logit contributions | |
anish | -0.001 |
temptation | -0.001 |
risk | -0.001 |
� | -0.001 |
aroma | -0.001 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
temptation | +0.027 |
risk | +0.025 |
anish | +0.025 |
lot | +0.025 |
consequences | +0.025 |
Neg logit contributions | |
v | -0.028 |
aky | -0.026 |
spac | -0.026 |
ev | -0.026 |
ang | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-03 |
Pos logit contributions | |
anish | +0.086 |
wered | +0.079 |
risk | +0.077 |
consequence | +0.077 |
temptation | +0.076 |
Neg logit contributions | |
v | -0.042 |
aky | -0.038 |
b | -0.037 |
wrapped | -0.035 |
said | -0.035 |
Token | One |
Token ID | 1881 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
says | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.004 |
consequences | -0.004 |
anish | -0.004 |
aroma | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +8.10e-04 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
temptation | +0.002 |
rules | +0.002 |
consequence | +0.002 |
consequences | +0.002 |
expense | +0.002 |
Neg logit contributions | |
said | -0.000 |
says | -0.000 |
b | -0.000 |
orse | -0.000 |
ev | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
ang | +0.005 |
ev | +0.005 |
Pluto | +0.005 |
Neg logit contributions | |
lot | -0.004 |
temptation | -0.003 |
risk | -0.003 |
consequences | -0.003 |
stomach | -0.003 |
Token | All |
Token ID | 1439 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
Tw | +0.002 |
azz | +0.002 |
aky | +0.002 |
Neg logit contributions | |
risk | -0.004 |
temptation | -0.004 |
anish | -0.004 |
consequences | -0.004 |
deed | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
temptation | +0.006 |
anish | +0.006 |
risk | +0.006 |
lot | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
aky | -0.005 |
ev | -0.005 |
ang | -0.005 |
Token | children |
Token ID | 1751 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.007 |
risk | +0.007 |
� | +0.007 |
lot | +0.007 |
Neg logit contributions | |
v | -0.007 |
spac | -0.007 |
aky | -0.007 |
ev | -0.007 |
ang | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
temptation | +0.016 |
risk | +0.015 |
lot | +0.015 |
anish | +0.015 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.015 |
ev | -0.015 |
ang | -0.014 |
Token | m |
Token ID | 285 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
v | +0.008 |
aky | +0.008 |
spac | +0.008 |
wrapped | +0.007 |
b | +0.007 |
Neg logit contributions | |
temptation | -0.009 |
anish | -0.009 |
� | -0.008 |
risk | -0.008 |
deed | -0.008 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
temptation | +0.016 |
risk | +0.015 |
lot | +0.015 |
anish | +0.015 |
consequences | +0.014 |
Neg logit contributions | |
v | -0.019 |
spac | -0.018 |
aky | -0.018 |
ev | -0.017 |
ang | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
temptation | +0.067 |
anish | +0.065 |
risk | +0.062 |
wered | +0.061 |
consequence | +0.061 |
Neg logit contributions | |
v | -0.053 |
aky | -0.050 |
b | -0.049 |
spac | -0.049 |
ev | -0.048 |
Token | keep |
Token ID | 1394 |
Feature activation | -3.57e-04 |
Pos logit contributions | |
anish | +0.004 |
temptation | +0.004 |
consequences | +0.004 |
risk | +0.004 |
� | +0.004 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
polar | -0.004 |
wrapped | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | -6.52e-04 |
Pos logit contributions | |
v | +0.000 |
spac | +0.000 |
aky | +0.000 |
ev | +0.000 |
b | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
risk | -0.000 |
consequences | -0.000 |
� | -0.000 |
Token | hands |
Token ID | 2832 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
risk | -0.001 |
consequences | -0.001 |
anish | -0.001 |
Token | warm |
Token ID | 5814 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
temptation | +0.007 |
risk | +0.006 |
anish | +0.006 |
lot | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.005 |
ang | -0.005 |
Token | ie |
Token ID | 494 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
lot | +0.012 |
anish | +0.012 |
consequences | +0.012 |
Neg logit contributions | |
v | -0.008 |
spac | -0.008 |
aky | -0.008 |
ev | -0.007 |
ang | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-04 |
Pos logit contributions | |
temptation | +0.020 |
lot | +0.018 |
risk | +0.018 |
anish | +0.018 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.024 |
spac | -0.023 |
aky | -0.023 |
ev | -0.022 |
ang | -0.021 |
Token | Unlike |
Token ID | 12101 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
temptation | +0.000 |
lot | +0.000 |
risk | +0.000 |
� | +0.000 |
Enjoy | +0.000 |
Neg logit contributions | |
v | -0.000 |
aky | -0.000 |
spac | -0.000 |
ev | -0.000 |
ck | -0.000 |
Token | other |
Token ID | 584 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
v | +0.015 |
spac | +0.015 |
aky | +0.014 |
ev | +0.014 |
ang | +0.014 |
Neg logit contributions | |
temptation | -0.014 |
risk | -0.013 |
lot | -0.013 |
anish | -0.012 |
consequences | -0.012 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
� | +0.018 |
temptation | +0.018 |
anish | +0.017 |
risk | +0.016 |
Tears | +0.016 |
Neg logit contributions | |
v | -0.017 |
spac | -0.016 |
aky | -0.015 |
b | -0.015 |
ev | -0.015 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
lot | +0.012 |
anish | +0.012 |
consequences | +0.011 |
Neg logit contributions | |
v | -0.026 |
spac | -0.025 |
aky | -0.025 |
ev | -0.024 |
ang | -0.024 |
Token | hes |
Token ID | 956 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
temptation | +0.062 |
risk | +0.058 |
anish | +0.056 |
lot | +0.056 |
consequences | +0.055 |
Neg logit contributions | |
v | -0.059 |
aky | -0.057 |
spac | -0.056 |
ev | -0.053 |
b | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
temptation | +0.007 |
� | +0.007 |
anish | +0.007 |
risk | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.007 |
aky | -0.006 |
spac | -0.006 |
b | -0.006 |
ang | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
v | +0.005 |
polar | +0.005 |
spac | +0.005 |
b | +0.005 |
ang | +0.005 |
Neg logit contributions | |
anish | -0.009 |
temptation | -0.009 |
consequences | -0.009 |
� | -0.009 |
deed | -0.009 |
Token | feathers |
Token ID | 27400 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
temptation | +0.004 |
risk | +0.004 |
lot | +0.004 |
anish | +0.004 |
consequences | +0.004 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | gl |
Token ID | 1278 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
temptation | +0.015 |
anish | +0.014 |
risk | +0.014 |
consequences | +0.013 |
lot | +0.013 |
Neg logit contributions | |
v | -0.014 |
aky | -0.014 |
spac | -0.013 |
b | -0.013 |
ev | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
v | +0.000 |
spac | +0.000 |
aky | +0.000 |
ev | +0.000 |
ang | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
risk | -0.000 |
lot | -0.000 |
anish | -0.000 |
consequences | -0.000 |
Token | did |
Token ID | 750 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
v | +0.020 |
spac | +0.020 |
aky | +0.019 |
ev | +0.019 |
ang | +0.018 |
Neg logit contributions | |
temptation | -0.023 |
risk | -0.022 |
lot | -0.022 |
anish | -0.021 |
consequences | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
� | +0.005 |
temptation | +0.004 |
anish | +0.004 |
aroma | +0.004 |
deed | +0.004 |
Neg logit contributions | |
v | -0.007 |
b | -0.006 |
spac | -0.006 |
ck | -0.006 |
aky | -0.006 |
Token | see |
Token ID | 766 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
� | +0.007 |
temptation | +0.007 |
aroma | +0.006 |
lot | +0.006 |
anish | +0.006 |
Neg logit contributions | |
v | -0.005 |
aky | -0.005 |
spac | -0.005 |
b | -0.005 |
ev | -0.005 |
Token | your |
Token ID | 534 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
v | +0.011 |
spac | +0.011 |
aky | +0.011 |
ev | +0.010 |
ang | +0.010 |
Neg logit contributions | |
temptation | -0.011 |
risk | -0.010 |
lot | -0.010 |
anish | -0.010 |
consequences | -0.010 |
Token | trophy |
Token ID | 16383 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
spac | +0.013 |
v | +0.012 |
aky | +0.011 |
Robo | +0.011 |
says | +0.011 |
Neg logit contributions | |
temptation | -0.011 |
wered | -0.010 |
Enjoy | -0.010 |
anish | -0.010 |
� | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
spac | +0.067 |
ev | +0.067 |
ang | +0.067 |
aky | +0.066 |
v | +0.066 |
Neg logit contributions | |
temptation | -0.039 |
consequences | -0.036 |
risk | -0.036 |
anish | -0.035 |
rules | -0.033 |
Token | Please |
Token ID | 4222 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
v | +0.009 |
aky | +0.008 |
spac | +0.008 |
b | +0.008 |
ang | +0.008 |
Neg logit contributions | |
temptation | -0.006 |
anish | -0.005 |
risk | -0.005 |
lot | -0.005 |
consequences | -0.005 |
Token | tell |
Token ID | 1560 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
wrapped | +0.006 |
said | +0.006 |
says | +0.006 |
spac | +0.005 |
v | +0.005 |
Neg logit contributions | |
temptation | -0.008 |
consequences | -0.007 |
deed | -0.007 |
outcomes | -0.007 |
grapes | -0.007 |
Token | me |
Token ID | 502 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
Tw | +0.003 |
Neg logit contributions | |
� | -0.005 |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
lot | -0.005 |
Token | what |
Token ID | 644 |
Feature activation | +4.67e-04 |
Pos logit contributions | |
spac | +0.007 |
v | +0.007 |
aky | +0.007 |
says | +0.007 |
Robo | +0.007 |
Neg logit contributions | |
� | -0.012 |
anish | -0.011 |
temptation | -0.011 |
aroma | -0.011 |
IT | -0.010 |
Token | us |
Token ID | 514 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
ev | +0.007 |
Tw | +0.007 |
Neg logit contributions | |
temptation | -0.013 |
risk | -0.012 |
� | -0.012 |
anish | -0.012 |
deed | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
consequences | +0.002 |
anish | +0.002 |
risk | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
ang | -0.002 |
aky | -0.002 |
ev | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
v | +0.013 |
aky | +0.013 |
spac | +0.012 |
b | +0.012 |
ev | +0.012 |
Neg logit contributions | |
temptation | -0.012 |
lot | -0.012 |
risk | -0.011 |
anish | -0.011 |
consequences | -0.011 |
Token | ," |
Token ID | 553 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
spac | +0.025 |
v | +0.024 |
erg | +0.024 |
ang | +0.024 |
Tw | +0.024 |
Neg logit contributions | |
temptation | -0.017 |
consequences | -0.015 |
lot | -0.015 |
risk | -0.015 |
anish | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
v | +0.022 |
aky | +0.021 |
spac | +0.020 |
ev | +0.020 |
ang | +0.020 |
Neg logit contributions | |
temptation | -0.017 |
lot | -0.016 |
risk | -0.015 |
others | -0.015 |
grapes | -0.015 |
Token | dancer |
Token ID | 38619 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
spac | +0.005 |
v | +0.004 |
Tw | +0.004 |
aky | +0.004 |
ang | +0.004 |
Neg logit contributions | |
� | -0.005 |
anish | -0.005 |
temptation | -0.005 |
risk | -0.005 |
Tears | -0.005 |
Token | says |
Token ID | 1139 |
Feature activation | +8.53e-04 |
Pos logit contributions | |
aky | +0.031 |
ev | +0.029 |
v | +0.029 |
spac | +0.028 |
Ar | +0.028 |
Neg logit contributions | |
temptation | -0.067 |
lot | -0.067 |
others | -0.066 |
face | -0.066 |
pause | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
lot | +0.001 |
anish | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
v | +0.011 |
aky | +0.010 |
spac | +0.010 |
b | +0.010 |
ev | +0.010 |
Neg logit contributions | |
temptation | -0.005 |
lot | -0.005 |
� | -0.004 |
anish | -0.004 |
Tears | -0.004 |
Token | You |
Token ID | 1639 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.007 |
lot | +0.007 |
risk | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.017 |
spac | -0.017 |
aky | -0.017 |
ev | -0.017 |
ang | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | -3.46e-05 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
ang | +0.005 |
aky | +0.005 |
ev | +0.005 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
spac | +0.008 |
v | +0.008 |
polar | +0.008 |
aky | +0.008 |
ev | +0.008 |
Neg logit contributions | |
temptation | -0.007 |
lot | -0.007 |
anish | -0.007 |
risk | -0.006 |
rules | -0.006 |
Token | Follow |
Token ID | 7155 |
Feature activation | -2.28e-03 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
aky | +0.004 |
polar | +0.004 |
ev | +0.004 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
lot | -0.001 |
law | -0.001 |
No | -0.001 |
Token | me |
Token ID | 502 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ang | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
lot | -0.003 |
anish | -0.002 |
consequences | -0.002 |
Token | ," |
Token ID | 553 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
temptation | +0.006 |
risk | +0.006 |
lot | +0.006 |
anish | +0.006 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.007 |
spac | -0.006 |
aky | -0.006 |
ang | -0.006 |
ev | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
v | +0.014 |
aky | +0.013 |
spac | +0.012 |
b | +0.012 |
ang | +0.012 |
Neg logit contributions | |
temptation | -0.020 |
risk | -0.019 |
lot | -0.018 |
anish | -0.018 |
� | -0.018 |
Token | sun |
Token ID | 4252 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
v | +0.009 |
spac | +0.009 |
aky | +0.009 |
says | +0.008 |
b | +0.008 |
Neg logit contributions | |
temptation | -0.009 |
risk | -0.009 |
anish | -0.009 |
consequences | -0.009 |
� | -0.009 |
Token | flower |
Token ID | 25547 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
v | +0.052 |
spac | +0.050 |
aky | +0.049 |
ev | +0.047 |
ang | +0.046 |
Neg logit contributions | |
temptation | -0.055 |
risk | -0.051 |
lot | -0.050 |
anish | -0.050 |
consequences | -0.049 |
Token | says |
Token ID | 1139 |
Feature activation | -9.42e-04 |
Pos logit contributions | |
spac | +0.008 |
aky | +0.008 |
v | +0.008 |
ev | +0.008 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.022 |
anish | -0.020 |
pause | -0.020 |
lot | -0.020 |
risk | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
lot | -0.001 |
anish | -0.001 |
consequences | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
v | +0.005 |
aky | +0.005 |
spac | +0.005 |
ev | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
anish | -0.002 |
risk | -0.002 |
� | -0.002 |
Token | bends |
Token ID | 44370 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.002 |
lot | -0.002 |
Token | fishing |
Token ID | 12478 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
spac | +0.001 |
v | +0.001 |
b | +0.001 |
aky | +0.000 |
trapped | +0.000 |
Neg logit contributions | |
anish | -0.001 |
temptation | -0.001 |
aroma | -0.001 |
meanings | -0.001 |
consequences | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
temptation | +0.015 |
aroma | +0.013 |
anish | +0.013 |
risk | +0.013 |
� | +0.013 |
Neg logit contributions | |
v | -0.010 |
aky | -0.010 |
spac | -0.010 |
b | -0.009 |
ang | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.003 |
lot | -0.003 |
Token | On |
Token ID | 2202 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.007 |
risk | +0.007 |
anish | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.005 |
spac | -0.004 |
aky | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
v | +0.059 |
aky | +0.056 |
spac | +0.055 |
ang | +0.053 |
b | +0.052 |
Neg logit contributions | |
temptation | -0.037 |
lot | -0.037 |
risk | -0.034 |
top | -0.033 |
� | -0.033 |
Token | bright |
Token ID | 6016 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
v | +0.048 |
spac | +0.046 |
aky | +0.045 |
ev | +0.043 |
ang | +0.043 |
Neg logit contributions | |
lot | -0.036 |
temptation | -0.035 |
risk | -0.033 |
top | -0.030 |
pause | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
v | +0.061 |
spac | +0.058 |
aky | +0.057 |
ev | +0.056 |
azz | +0.055 |
Neg logit contributions | |
temptation | -0.045 |
lot | -0.044 |
risk | -0.042 |
deed | -0.039 |
pause | -0.039 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
ev | +0.004 |
aky | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
risk | -0.004 |
anish | -0.004 |
consequences | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
v | +0.036 |
spac | +0.035 |
aky | +0.034 |
ev | +0.032 |
ang | +0.032 |
Neg logit contributions | |
temptation | -0.046 |
anish | -0.044 |
consequences | -0.043 |
risk | -0.042 |
consequence | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
spac | +0.007 |
wrapped | +0.007 |
said | +0.006 |
v | +0.006 |
Tw | +0.006 |
Neg logit contributions | |
temptation | -0.017 |
anish | -0.016 |
warnings | -0.016 |
rules | -0.016 |
consequences | -0.016 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
spac | +0.009 |
Tw | +0.009 |
v | +0.009 |
aky | +0.008 |
ev | +0.008 |
Neg logit contributions | |
temptation | -0.016 |
anish | -0.016 |
consequences | -0.016 |
risk | -0.015 |
deed | -0.015 |
Token | forever |
Token ID | 8097 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
temptation | +0.022 |
risk | +0.020 |
anish | +0.020 |
consequences | +0.020 |
lot | +0.019 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.016 |
ev | -0.015 |
ang | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
temptation | +0.017 |
anish | +0.016 |
wered | +0.016 |
risk | +0.015 |
consequence | +0.015 |
Neg logit contributions | |
v | -0.012 |
aky | -0.012 |
spac | -0.012 |
trapped | -0.011 |
ev | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.003 |
lot | -0.003 |
Token | On |
Token ID | 2202 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
anish | +0.002 |
risk | +0.002 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
b | -0.001 |
ev | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
v | +0.065 |
aky | +0.061 |
spac | +0.060 |
ang | +0.059 |
b | +0.057 |
Neg logit contributions | |
lot | -0.037 |
temptation | -0.036 |
top | -0.034 |
risk | -0.033 |
wered | -0.033 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
v | +0.049 |
spac | +0.047 |
aky | +0.045 |
ang | +0.044 |
ev | +0.044 |
Neg logit contributions | |
lot | -0.037 |
temptation | -0.035 |
risk | -0.034 |
top | -0.030 |
pause | -0.030 |
Token | day |
Token ID | 1110 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
v | +0.056 |
spac | +0.054 |
aky | +0.054 |
ev | +0.051 |
ang | +0.050 |
Neg logit contributions | |
temptation | -0.049 |
risk | -0.045 |
lot | -0.045 |
anish | -0.044 |
consequences | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
v | +0.014 |
spac | +0.014 |
aky | +0.013 |
ang | +0.013 |
Tw | +0.013 |
Neg logit contributions | |
temptation | -0.028 |
anish | -0.027 |
consequences | -0.027 |
risk | -0.026 |
deed | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
spac | +0.017 |
v | +0.017 |
aky | +0.016 |
Tw | +0.016 |
ev | +0.016 |
Neg logit contributions | |
temptation | -0.023 |
anish | -0.022 |
risk | -0.022 |
consequences | -0.022 |
deed | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.94e-03 |
Pos logit contributions | |
spac | +0.015 |
aky | +0.014 |
v | +0.014 |
ang | +0.014 |
ev | +0.014 |
Neg logit contributions | |
temptation | -0.017 |
anish | -0.017 |
consequences | -0.016 |
risk | -0.016 |
habits | -0.015 |
Token | my |
Token ID | 1820 |
Feature activation | -5.97e-04 |
Pos logit contributions | |
temptation | +0.008 |
lot | +0.008 |
risk | +0.008 |
aroma | +0.007 |
anish | +0.007 |
Neg logit contributions | |
spac | -0.007 |
aky | -0.007 |
v | -0.006 |
ang | -0.006 |
ev | -0.006 |
Token | hair |
Token ID | 4190 |
Feature activation | +6.38e-03 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
temptation | +0.009 |
lot | +0.008 |
risk | +0.008 |
anish | +0.008 |
consequences | +0.008 |
Neg logit contributions | |
spac | -0.008 |
v | -0.008 |
aky | -0.007 |
ev | -0.007 |
ang | -0.007 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
v | +0.018 |
spac | +0.017 |
aky | +0.017 |
ev | +0.015 |
ang | +0.015 |
Neg logit contributions | |
temptation | -0.040 |
lot | -0.038 |
risk | -0.037 |
anish | -0.037 |
consequences | -0.036 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
Ar | +0.030 |
spac | +0.030 |
v | +0.030 |
erg | +0.028 |
inery | +0.028 |
Neg logit contributions | |
anish | -0.013 |
lot | -0.012 |
temptation | -0.012 |
others | -0.012 |
pause | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
aky | +0.026 |
v | +0.025 |
eddy | +0.023 |
b | +0.023 |
polar | +0.023 |
Neg logit contributions | |
temptation | -0.015 |
others | -0.013 |
top | -0.013 |
All | -0.012 |
lot | -0.012 |
Token | bar |
Token ID | 2318 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ang | +0.003 |
b | +0.003 |
Neg logit contributions | |
anish | -0.004 |
temptation | -0.004 |
risk | -0.004 |
� | -0.003 |
consequences | -0.003 |
Token | ber |
Token ID | 527 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
spac | +0.044 |
lov | +0.042 |
aky | +0.041 |
Tal | +0.041 |
ev | +0.041 |
Neg logit contributions | |
temptation | -0.052 |
lot | -0.050 |
anish | -0.047 |
Again | -0.046 |
deed | -0.046 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
Ar | +0.025 |
spac | +0.024 |
aky | +0.023 |
erg | +0.023 |
ev | +0.022 |
Neg logit contributions | |
face | -0.032 |
Again | -0.031 |
stomach | -0.030 |
temptation | -0.030 |
Tears | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
aky | +0.005 |
ev | +0.005 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.004 |
lot | -0.004 |
anish | -0.004 |
consequences | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -9.40e-04 |
Pos logit contributions | |
ck | +0.003 |
aky | +0.003 |
v | +0.003 |
b | +0.003 |
ang | +0.003 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.002 |
Tears | -0.002 |
All | -0.002 |
Again | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
aky | +0.002 |
cest | +0.002 |
polar | +0.002 |
spac | +0.002 |
oval | +0.002 |
Neg logit contributions | |
lot | -0.001 |
top | -0.001 |
rules | -0.001 |
All | -0.001 |
temptation | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
v | +0.013 |
aky | +0.013 |
spac | +0.013 |
ang | +0.012 |
ev | +0.012 |
Neg logit contributions | |
temptation | -0.009 |
risk | -0.009 |
lot | -0.009 |
consequences | -0.008 |
anish | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
temptation | +0.016 |
risk | +0.015 |
anish | +0.015 |
wered | +0.015 |
consequences | +0.015 |
Neg logit contributions | |
v | -0.014 |
spac | -0.013 |
aky | -0.013 |
ev | -0.012 |
b | -0.012 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
ang | +0.003 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.007 |
anish | -0.007 |
consequences | -0.007 |
lot | -0.007 |
Token | On |
Token ID | 2202 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
lot | +0.006 |
� | +0.006 |
temptation | +0.006 |
anish | +0.006 |
risk | +0.006 |
Neg logit contributions | |
aky | -0.005 |
v | -0.005 |
spac | -0.005 |
ck | -0.005 |
b | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
v | +0.060 |
aky | +0.057 |
spac | +0.055 |
ang | +0.054 |
azz | +0.053 |
Neg logit contributions | |
lot | -0.035 |
temptation | -0.035 |
top | -0.032 |
risk | -0.032 |
wered | -0.031 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
v | +0.051 |
spac | +0.050 |
aky | +0.047 |
ev | +0.046 |
ang | +0.046 |
Neg logit contributions | |
lot | -0.034 |
temptation | -0.033 |
risk | -0.031 |
� | -0.028 |
top | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
v | +0.052 |
spac | +0.050 |
aky | +0.049 |
ev | +0.047 |
ang | +0.047 |
Neg logit contributions | |
temptation | -0.051 |
risk | -0.048 |
anish | -0.047 |
lot | -0.047 |
consequences | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
v | +0.015 |
spac | +0.014 |
aky | +0.014 |
ang | +0.013 |
Tw | +0.013 |
Neg logit contributions | |
temptation | -0.030 |
consequences | -0.028 |
anish | -0.028 |
risk | -0.027 |
deed | -0.027 |
Token | Joe |
Token ID | 5689 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
v | +0.017 |
spac | +0.016 |
aky | +0.016 |
Tw | +0.015 |
ev | +0.015 |
Neg logit contributions | |
temptation | -0.023 |
risk | -0.021 |
anish | -0.021 |
consequences | -0.021 |
deed | -0.021 |
Token | decided |
Token ID | 3066 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
spac | +0.006 |
v | +0.006 |
aky | +0.006 |
ang | +0.005 |
ev | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
lot | -0.005 |
consequences | -0.005 |
anish | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
said | +0.004 |
z | +0.004 |
b | +0.004 |
spac | +0.004 |
says | +0.004 |
Neg logit contributions | |
� | -0.008 |
anish | -0.008 |
aroma | -0.008 |
temptation | -0.008 |
ocolate | -0.007 |
Token | again |
Token ID | 757 |
Feature activation | +4.16e-04 |
Pos logit contributions | |
temptation | +0.007 |
risk | +0.006 |
anish | +0.006 |
consequences | +0.006 |
lot | +0.006 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.006 |
ang | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.000 |
anish | +0.000 |
lot | +0.000 |
consequences | +0.000 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
temptation | +0.004 |
lot | +0.004 |
risk | +0.004 |
anish | +0.004 |
consequences | +0.004 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
b | -0.003 |
Token | On |
Token ID | 2202 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.007 |
anish | +0.006 |
� | +0.006 |
risk | +0.006 |
Neg logit contributions | |
v | -0.006 |
aky | -0.006 |
spac | -0.006 |
ck | -0.005 |
b | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
v | +0.061 |
aky | +0.058 |
ang | +0.056 |
spac | +0.056 |
azz | +0.054 |
Neg logit contributions | |
lot | -0.034 |
temptation | -0.033 |
top | -0.032 |
wered | -0.031 |
risk | -0.030 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
v | +0.047 |
spac | +0.045 |
aky | +0.043 |
ang | +0.042 |
ev | +0.042 |
Neg logit contributions | |
lot | -0.034 |
temptation | -0.033 |
risk | -0.031 |
top | -0.028 |
pause | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
v | +0.061 |
spac | +0.058 |
aky | +0.058 |
ev | +0.056 |
azz | +0.055 |
Neg logit contributions | |
temptation | -0.042 |
lot | -0.041 |
risk | -0.039 |
pause | -0.036 |
deed | -0.036 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
ev | +0.002 |
ang | +0.002 |
azz | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.001 |
others | -0.001 |
wered | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
v | +0.037 |
spac | +0.036 |
aky | +0.035 |
ev | +0.034 |
ang | +0.034 |
Neg logit contributions | |
temptation | -0.046 |
anish | -0.043 |
consequences | -0.042 |
risk | -0.042 |
lot | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
spac | +0.006 |
v | +0.006 |
aky | +0.006 |
ev | +0.006 |
polar | +0.006 |
Neg logit contributions | |
temptation | -0.014 |
anish | -0.013 |
consequences | -0.013 |
risk | -0.013 |
warnings | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
spac | +0.010 |
v | +0.010 |
aky | +0.009 |
ev | +0.009 |
polar | +0.009 |
Neg logit contributions | |
temptation | -0.017 |
anish | -0.016 |
risk | -0.016 |
consequences | -0.016 |
deed | -0.015 |
Token | nic |
Token ID | 9200 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
spac | +0.005 |
v | +0.005 |
aky | +0.005 |
Tw | +0.005 |
unicorn | +0.005 |
Neg logit contributions | |
temptation | -0.006 |
anish | -0.005 |
risk | -0.005 |
� | -0.005 |
consequences | -0.005 |
Token | est |
Token ID | 395 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
temptation | +0.004 |
� | +0.004 |
treadmill | +0.004 |
grapes | +0.004 |
risk | +0.004 |
Neg logit contributions | |
v | -0.003 |
aky | -0.002 |
spac | -0.002 |
ev | -0.002 |
eddy | -0.002 |
Token | jazz |
Token ID | 21274 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
wered | +0.005 |
temptation | +0.005 |
Sale | +0.004 |
NOT | +0.004 |
Enjoy | +0.004 |
Neg logit contributions | |
spac | -0.003 |
unicorn | -0.003 |
wrapped | -0.003 |
polar | -0.003 |
z | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
unicorn | +0.003 |
wrapped | +0.003 |
Tw | +0.003 |
Neg logit contributions | |
temptation | -0.005 |
wered | -0.005 |
risk | -0.005 |
anish | -0.005 |
Enjoy | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
spac | +0.018 |
Tw | +0.017 |
aky | +0.016 |
v | +0.016 |
ev | +0.016 |
Neg logit contributions | |
anish | -0.029 |
temptation | -0.028 |
risk | -0.028 |
consequences | -0.027 |
� | -0.027 |
Token | whole |
Token ID | 2187 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
v | +0.012 |
aky | +0.011 |
spac | +0.011 |
ev | +0.011 |
ck | +0.011 |
Neg logit contributions | |
temptation | -0.006 |
lot | -0.006 |
risk | -0.005 |
consequences | -0.005 |
anish | -0.005 |
Token | town |
Token ID | 3240 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
v | +0.066 |
aky | +0.064 |
spac | +0.064 |
ev | +0.063 |
ck | +0.062 |
Neg logit contributions | |
temptation | -0.033 |
lot | -0.032 |
risk | -0.030 |
anish | -0.029 |
consequences | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
v | +0.005 |
aky | +0.005 |
spac | +0.004 |
ang | +0.004 |
b | +0.004 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
anish | -0.006 |
consequences | -0.006 |
consequence | -0.006 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
temptation | +0.005 |
consequences | +0.005 |
risk | +0.005 |
anish | +0.005 |
aroma | +0.005 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
Tw | -0.003 |
azz | -0.003 |
says | -0.003 |
Token | jazz |
Token ID | 21274 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
temptation | +0.015 |
anish | +0.014 |
risk | +0.014 |
consequences | +0.014 |
aroma | +0.013 |
Neg logit contributions | |
spac | -0.014 |
v | -0.014 |
aky | -0.013 |
ang | -0.013 |
ev | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
b | +0.006 |
unicorn | +0.006 |
wrapped | +0.005 |
Neg logit contributions | |
temptation | -0.008 |
wered | -0.007 |
risk | -0.007 |
anish | -0.007 |
Enjoy | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
ev | +0.004 |
azz | +0.004 |
aky | +0.004 |
Neg logit contributions | |
temptation | -0.009 |
lot | -0.009 |
risk | -0.009 |
Enjoy | -0.009 |
� | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +1.75e-04 |
Pos logit contributions | |
temptation | +0.006 |
wered | +0.005 |
anish | +0.005 |
risk | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
spac | -0.003 |
v | -0.003 |
said | -0.003 |
says | -0.003 |
wrapped | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
temptation | +0.000 |
risk | +0.000 |
consequences | +0.000 |
anish | +0.000 |
lot | +0.000 |
Neg logit contributions | |
v | -0.000 |
spac | -0.000 |
aky | -0.000 |
ev | -0.000 |
ang | -0.000 |
Token | On |
Token ID | 2202 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
temptation | +0.007 |
risk | +0.006 |
lot | +0.006 |
anish | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
ev | -0.004 |
ang | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
v | +0.057 |
aky | +0.055 |
spac | +0.053 |
ang | +0.052 |
b | +0.051 |
Neg logit contributions | |
temptation | -0.036 |
lot | -0.036 |
risk | -0.033 |
top | -0.033 |
wered | -0.032 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
v | +0.047 |
spac | +0.045 |
aky | +0.044 |
ev | +0.042 |
ang | +0.042 |
Neg logit contributions | |
lot | -0.035 |
temptation | -0.032 |
risk | -0.031 |
top | -0.029 |
pause | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
v | +0.052 |
spac | +0.051 |
aky | +0.050 |
ev | +0.048 |
ang | +0.047 |
Neg logit contributions | |
temptation | -0.048 |
risk | -0.045 |
lot | -0.044 |
anish | -0.044 |
consequences | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
spac | +0.012 |
v | +0.012 |
aky | +0.011 |
wrapped | +0.011 |
Tw | +0.011 |
Neg logit contributions | |
temptation | -0.027 |
anish | -0.026 |
consequences | -0.026 |
risk | -0.025 |
deed | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
spac | +0.017 |
v | +0.017 |
aky | +0.016 |
ev | +0.015 |
Tw | +0.015 |
Neg logit contributions | |
temptation | -0.022 |
anish | -0.021 |
risk | -0.021 |
consequences | -0.020 |
deed | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
spac | +0.014 |
v | +0.014 |
aky | +0.014 |
ang | +0.013 |
ev | +0.013 |
Neg logit contributions | |
temptation | -0.016 |
anish | -0.015 |
consequences | -0.015 |
risk | -0.014 |
� | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.010 |
risk | +0.010 |
deed | +0.009 |
� | +0.009 |
Neg logit contributions | |
v | -0.009 |
aky | -0.008 |
spac | -0.008 |
b | -0.008 |
ev | -0.008 |
Token | worm |
Token ID | 25323 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
v | +0.009 |
spac | +0.009 |
aky | +0.009 |
ang | +0.008 |
b | +0.008 |
Neg logit contributions | |
temptation | -0.016 |
anish | -0.015 |
consequences | -0.015 |
risk | -0.015 |
� | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
v | +0.003 |
aky | +0.003 |
spac | +0.003 |
ang | +0.003 |
b | +0.003 |
Neg logit contributions | |
temptation | -0.005 |
anish | -0.005 |
consequences | -0.005 |
risk | -0.005 |
aroma | -0.005 |
Token | lived |
Token ID | 5615 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
risk | -0.004 |
lot | -0.003 |
anish | -0.003 |
consequences | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
temptation | +0.011 |
risk | +0.010 |
anish | +0.010 |
lot | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.010 |
spac | -0.010 |
aky | -0.010 |
ev | -0.009 |
ang | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
v | +0.024 |
aky | +0.023 |
spac | +0.023 |
ang | +0.022 |
azz | +0.022 |
Neg logit contributions | |
temptation | -0.016 |
lot | -0.016 |
risk | -0.014 |
consequences | -0.013 |
top | -0.013 |
Token | cozy |
Token ID | 37438 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
v | +0.013 |
azz | +0.013 |
oke | +0.013 |
rocket | +0.012 |
spac | +0.012 |
Neg logit contributions | |
lot | -0.007 |
top | -0.006 |
others | -0.006 |
stomach | -0.006 |
temptation | -0.005 |
Token | home |
Token ID | 1363 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
v | +0.045 |
aky | +0.041 |
spac | +0.041 |
ev | +0.040 |
azz | +0.040 |
Neg logit contributions | |
lot | -0.055 |
temptation | -0.055 |
risk | -0.052 |
deed | -0.051 |
stomach | -0.051 |
Token | near |
Token ID | 1474 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
v | +0.005 |
aky | +0.004 |
spac | +0.004 |
ang | +0.004 |
b | +0.004 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
anish | -0.005 |
consequences | -0.005 |
aroma | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
spac | +0.011 |
v | +0.011 |
polar | +0.011 |
aky | +0.010 |
Pluto | +0.010 |
Neg logit contributions | |
temptation | -0.020 |
anish | -0.020 |
risk | -0.019 |
� | -0.019 |
consequences | -0.019 |
Token | me |
Token ID | 502 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
v | +0.021 |
aky | +0.019 |
spac | +0.018 |
ev | +0.018 |
ang | +0.018 |
Neg logit contributions | |
lot | -0.019 |
temptation | -0.018 |
risk | -0.017 |
top | -0.016 |
law | -0.016 |
Token | adow |
Token ID | 4584 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
spac | +0.010 |
v | +0.009 |
ev | +0.009 |
Ar | +0.008 |
Tw | +0.008 |
Neg logit contributions | |
temptation | -0.015 |
risk | -0.014 |
lot | -0.014 |
anish | -0.013 |
consequences | -0.013 |
Token | else |
Token ID | 2073 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
temptation | +0.006 |
risk | +0.006 |
lot | +0.006 |
consequences | +0.005 |
anish | +0.005 |
Neg logit contributions | |
spac | -0.012 |
v | -0.012 |
aky | -0.012 |
ev | -0.011 |
ang | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
temptation | +0.008 |
risk | +0.007 |
lot | +0.007 |
consequences | +0.007 |
anish | +0.007 |
Neg logit contributions | |
v | -0.010 |
spac | -0.010 |
aky | -0.010 |
ev | -0.009 |
ang | -0.009 |
Token | wear |
Token ID | 5806 |
Feature activation | +9.96e-04 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.007 |
risk | +0.007 |
lot | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.010 |
spac | -0.009 |
aky | -0.009 |
ev | -0.009 |
b | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
consequences | +0.001 |
lot | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
b | -0.001 |
ev | -0.001 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.47e-04 |
Pos logit contributions | |
v | +0.007 |
aky | +0.007 |
spac | +0.007 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.009 |
lot | -0.008 |
risk | -0.008 |
consequences | -0.008 |
anish | -0.008 |
Token | bl |
Token ID | 698 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
anish | -0.001 |
lot | -0.001 |
consequences | -0.001 |
Token | ouse |
Token ID | 1076 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
v | +0.047 |
spac | +0.047 |
aky | +0.045 |
ev | +0.043 |
ang | +0.042 |
Neg logit contributions | |
temptation | -0.051 |
lot | -0.048 |
anish | -0.048 |
risk | -0.048 |
� | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
v | +0.014 |
aky | +0.013 |
spac | +0.013 |
b | +0.012 |
wrapped | +0.012 |
Neg logit contributions | |
temptation | -0.017 |
anish | -0.016 |
risk | -0.016 |
wered | -0.015 |
lot | -0.015 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
risk | +0.005 |
temptation | +0.005 |
anish | +0.005 |
deed | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.004 |
spac | -0.003 |
azz | -0.003 |
says | -0.003 |
ev | -0.003 |
Token | got |
Token ID | 1392 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
ang | -0.003 |
Token | angry |
Token ID | 7954 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
temptation | +0.011 |
risk | +0.010 |
anish | +0.010 |
lot | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.008 |
spac | -0.007 |
aky | -0.007 |
ev | -0.007 |
ang | -0.007 |
Token | sur |
Token ID | 969 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
v | +0.014 |
spac | +0.014 |
aky | +0.013 |
b | +0.013 |
ev | +0.013 |
Neg logit contributions | |
temptation | -0.013 |
anish | -0.013 |
risk | -0.012 |
� | -0.012 |
consequences | -0.012 |
Token | fer |
Token ID | 2232 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
aky | +0.044 |
spac | +0.043 |
v | +0.042 |
polar | +0.039 |
ev | +0.039 |
Neg logit contributions | |
temptation | -0.050 |
risk | -0.050 |
anish | -0.049 |
� | -0.048 |
lot | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
v | +0.023 |
spac | +0.022 |
aky | +0.022 |
ev | +0.021 |
ang | +0.021 |
Neg logit contributions | |
temptation | -0.021 |
risk | -0.020 |
lot | -0.019 |
anish | -0.019 |
consequences | -0.019 |
Token | Whenever |
Token ID | 21326 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.002 |
anish | +0.002 |
risk | +0.002 |
� | +0.002 |
Neg logit contributions | |
v | -0.003 |
aky | -0.003 |
spac | -0.003 |
ev | -0.003 |
b | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
temptation | +0.024 |
anish | +0.022 |
risk | +0.022 |
lot | +0.022 |
consequences | +0.022 |
Neg logit contributions | |
spac | -0.017 |
v | -0.017 |
aky | -0.016 |
ev | -0.016 |
ang | -0.016 |
Token | sur |
Token ID | 969 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
spac | +0.011 |
v | +0.011 |
b | +0.010 |
aky | +0.010 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.015 |
anish | -0.015 |
� | -0.014 |
risk | -0.014 |
lot | -0.014 |
Token | fer |
Token ID | 2232 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
aky | +0.044 |
spac | +0.043 |
v | +0.042 |
ev | +0.039 |
polar | +0.039 |
Neg logit contributions | |
anish | -0.051 |
temptation | -0.051 |
risk | -0.050 |
� | -0.049 |
lot | -0.047 |
Token | balanced |
Token ID | 12974 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
v | +0.027 |
aky | +0.027 |
spac | +0.027 |
ev | +0.025 |
ang | +0.025 |
Neg logit contributions | |
temptation | -0.024 |
risk | -0.024 |
lot | -0.024 |
anish | -0.023 |
consequences | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
v | +0.018 |
spac | +0.017 |
b | +0.017 |
aky | +0.017 |
ev | +0.016 |
Neg logit contributions | |
temptation | -0.021 |
risk | -0.019 |
anish | -0.019 |
lot | -0.019 |
consequences | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
ev | +0.004 |
Pluto | +0.004 |
Robo | +0.004 |
Neg logit contributions | |
temptation | -0.006 |
anish | -0.006 |
risk | -0.006 |
consequences | -0.006 |
aroma | -0.006 |
Token | board |
Token ID | 3096 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
spac | +0.009 |
v | +0.009 |
b | +0.008 |
aky | +0.008 |
ev | +0.008 |
Neg logit contributions | |
anish | -0.011 |
� | -0.010 |
temptation | -0.010 |
Enjoy | -0.010 |
deed | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
lot | +0.002 |
anish | +0.002 |
temptation | +0.002 |
Enjoy | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
azz | -0.004 |
ev | -0.004 |
b | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
v | +0.020 |
aky | +0.018 |
spac | +0.017 |
b | +0.017 |
ev | +0.017 |
Neg logit contributions | |
lot | -0.016 |
temptation | -0.015 |
risk | -0.014 |
� | -0.013 |
deed | -0.013 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
temptation | +0.005 |
lot | +0.005 |
risk | +0.004 |
anish | +0.004 |
deed | +0.004 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
b | -0.004 |
ev | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
temptation | +0.027 |
risk | +0.025 |
consequences | +0.025 |
anish | +0.024 |
aroma | +0.024 |
Neg logit contributions | |
v | -0.015 |
aky | -0.015 |
spac | -0.014 |
ang | -0.014 |
ev | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
v | +0.030 |
spac | +0.029 |
aky | +0.028 |
ev | +0.027 |
ang | +0.027 |
Neg logit contributions | |
temptation | -0.027 |
risk | -0.025 |
lot | -0.025 |
anish | -0.025 |
consequences | -0.024 |
Token | cozy |
Token ID | 37438 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
v | +0.022 |
azz | +0.022 |
oke | +0.021 |
ents | +0.021 |
b | +0.020 |
Neg logit contributions | |
lot | -0.013 |
temptation | -0.011 |
others | -0.011 |
top | -0.011 |
warnings | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
v | +0.052 |
aky | +0.047 |
b | +0.047 |
azz | +0.046 |
spac | +0.046 |
Neg logit contributions | |
lot | -0.049 |
temptation | -0.047 |
stomach | -0.046 |
deed | -0.045 |
risk | -0.044 |
Token | hole |
Token ID | 7604 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
ev | +0.007 |
aky | +0.007 |
b | +0.007 |
Neg logit contributions | |
temptation | -0.007 |
lot | -0.007 |
risk | -0.006 |
consequences | -0.006 |
anish | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
v | +0.006 |
aky | +0.006 |
ang | +0.006 |
wrapped | +0.006 |
b | +0.006 |
Neg logit contributions | |
temptation | -0.012 |
risk | -0.011 |
deed | -0.011 |
Enjoy | -0.011 |
Sale | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -5.44e-04 |
Pos logit contributions | |
wrapped | +0.008 |
spac | +0.008 |
trapped | +0.008 |
Mir | +0.007 |
z | +0.007 |
Neg logit contributions | |
anish | -0.023 |
mons | -0.022 |
� | -0.022 |
endor | -0.022 |
OM | -0.021 |
Token | wall |
Token ID | 3355 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
spac | +0.001 |
aky | +0.001 |
v | +0.001 |
polar | +0.001 |
ev | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
� | -0.001 |
deed | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
temptation | +0.022 |
risk | +0.020 |
anish | +0.020 |
lot | +0.020 |
consequences | +0.020 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.015 |
ev | -0.015 |
ang | -0.014 |
Token | we |
Token ID | 356 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
lot | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.003 |
aky | -0.003 |
spac | -0.003 |
ev | -0.003 |
ang | -0.003 |
Token | do |
Token ID | 466 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
lot | +0.002 |
anish | +0.002 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ang | -0.003 |
ev | -0.003 |
Token | ," |
Token ID | 553 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
temptation | +0.012 |
lot | +0.012 |
risk | +0.012 |
anish | +0.011 |
consequences | +0.011 |
Neg logit contributions | |
v | -0.008 |
aky | -0.008 |
spac | -0.008 |
ev | -0.008 |
ang | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
aky | +0.016 |
v | +0.016 |
spac | +0.014 |
b | +0.014 |
ev | +0.014 |
Neg logit contributions | |
temptation | -0.014 |
lot | -0.014 |
risk | -0.013 |
grapes | -0.012 |
fruits | -0.012 |
Token | dancer |
Token ID | 38619 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
ang | +0.006 |
b | +0.006 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.008 |
anish | -0.008 |
consequences | -0.007 |
� | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
aky | +0.033 |
polar | +0.031 |
ev | +0.030 |
eddy | +0.029 |
spac | +0.029 |
Neg logit contributions | |
temptation | -0.060 |
stories | -0.058 |
lot | -0.058 |
pause | -0.058 |
jokes | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
v | +0.004 |
aky | +0.004 |
spac | +0.004 |
ev | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
lot | -0.003 |
consequences | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
v | +0.002 |
aky | +0.002 |
spac | +0.002 |
ev | +0.002 |
b | +0.002 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
anish | -0.001 |
� | -0.001 |
risk | -0.001 |
Token | It |
Token ID | 1026 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
temptation | +0.015 |
lot | +0.015 |
anish | +0.014 |
risk | +0.014 |
Enjoy | +0.013 |
Neg logit contributions | |
spac | -0.025 |
v | -0.025 |
aky | -0.025 |
ev | -0.024 |
polar | -0.024 |
Token | is |
Token ID | 318 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
aky | +0.016 |
spac | +0.015 |
ev | +0.015 |
polar | +0.015 |
inery | +0.015 |
Neg logit contributions | |
lot | -0.007 |
temptation | -0.006 |
consequences | -0.006 |
risk | -0.006 |
anish | -0.006 |
Token | but |
Token ID | 475 |
Feature activation | -9.07e-04 |
Pos logit contributions | |
anish | +0.001 |
temptation | +0.001 |
risk | +0.001 |
consequences | +0.001 |
� | +0.001 |
Neg logit contributions | |
spac | -0.001 |
v | -0.001 |
aky | -0.001 |
wrapped | -0.001 |
ev | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
Ar | +0.001 |
ev | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
Tears | -0.001 |
warnings | -0.001 |
pause | -0.001 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.003 |
anish | +0.003 |
risk | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
ang | -0.004 |
aky | -0.004 |
ev | -0.004 |
Token | watching |
Token ID | 4964 |
Feature activation | +1.84e-04 |
Pos logit contributions | |
spac | +0.002 |
v | +0.002 |
ev | +0.002 |
b | +0.002 |
Tw | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
anish | -0.002 |
risk | -0.002 |
� | -0.002 |
consequences | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
temptation | +0.000 |
risk | +0.000 |
anish | +0.000 |
lot | +0.000 |
consequences | +0.000 |
Neg logit contributions | |
v | -0.000 |
spac | -0.000 |
aky | -0.000 |
ev | -0.000 |
ang | -0.000 |
Token | sur |
Token ID | 969 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
v | +0.014 |
spac | +0.014 |
aky | +0.013 |
b | +0.013 |
ev | +0.013 |
Neg logit contributions | |
temptation | -0.013 |
anish | -0.013 |
risk | -0.012 |
� | -0.012 |
consequences | -0.012 |
Token | fer |
Token ID | 2232 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
aky | +0.044 |
spac | +0.043 |
v | +0.042 |
polar | +0.039 |
ev | +0.039 |
Neg logit contributions | |
temptation | -0.050 |
risk | -0.050 |
anish | -0.049 |
� | -0.048 |
lot | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
v | +0.023 |
spac | +0.022 |
aky | +0.022 |
ev | +0.021 |
ang | +0.021 |
Neg logit contributions | |
temptation | -0.021 |
risk | -0.020 |
lot | -0.019 |
anish | -0.019 |
consequences | -0.019 |
Token | Whenever |
Token ID | 21326 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.002 |
anish | +0.002 |
risk | +0.002 |
� | +0.002 |
Neg logit contributions | |
v | -0.003 |
aky | -0.003 |
spac | -0.003 |
ev | -0.003 |
b | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
temptation | +0.024 |
anish | +0.022 |
risk | +0.022 |
lot | +0.022 |
consequences | +0.022 |
Neg logit contributions | |
spac | -0.017 |
v | -0.017 |
aky | -0.016 |
ev | -0.016 |
ang | -0.016 |
Token | sur |
Token ID | 969 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
spac | +0.011 |
v | +0.011 |
b | +0.010 |
aky | +0.010 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.015 |
anish | -0.015 |
� | -0.014 |
risk | -0.014 |
lot | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
said | +0.012 |
wrapped | +0.012 |
spac | +0.011 |
says | +0.011 |
v | +0.011 |
Neg logit contributions | |
temptation | -0.029 |
anish | -0.029 |
risk | -0.029 |
consequences | -0.028 |
wered | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +6.82e-04 |
Pos logit contributions | |
temptation | +0.004 |
lot | +0.004 |
anish | +0.004 |
Enjoy | +0.004 |
Tears | +0.004 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
wrapped | -0.005 |
til | -0.005 |
ev | -0.005 |
Token | At |
Token ID | 2953 |
Feature activation | -9.23e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
anish | +0.001 |
Enjoy | +0.001 |
risk | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
til | -0.001 |
ev | -0.001 |
wrapped | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
v | +0.015 |
aky | +0.015 |
spac | +0.014 |
ang | +0.013 |
azz | +0.013 |
Neg logit contributions | |
temptation | -0.010 |
risk | -0.010 |
lot | -0.010 |
top | -0.009 |
wered | -0.009 |
Token | end |
Token ID | 886 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
consequences | +0.001 |
lot | +0.001 |
Neg logit contributions | |
spac | -0.002 |
v | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
v | +0.013 |
spac | +0.013 |
aky | +0.013 |
ev | +0.012 |
b | +0.012 |
Neg logit contributions | |
temptation | -0.013 |
lot | -0.012 |
risk | -0.012 |
anish | -0.012 |
consequences | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
v | +0.068 |
aky | +0.065 |
spac | +0.061 |
azz | +0.060 |
b | +0.059 |
Neg logit contributions | |
temptation | -0.036 |
lot | -0.035 |
risk | -0.032 |
� | -0.032 |
top | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
spac | +0.003 |
v | +0.003 |
aky | +0.003 |
ang | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.004 |
anish | -0.003 |
consequences | -0.003 |
risk | -0.003 |
� | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
risk | +0.001 |
anish | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
aky | -0.001 |
spac | -0.001 |
ev | -0.001 |
b | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.002 |
anish | -0.002 |
consequences | -0.002 |
lot | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.002 |
lot | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
ev | +0.006 |
ang | +0.006 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
risk | -0.004 |
anish | -0.004 |
consequences | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
temptation | +0.024 |
lot | +0.023 |
anish | +0.022 |
risk | +0.022 |
� | +0.022 |
Neg logit contributions | |
v | -0.015 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.013 |
Token | At |
Token ID | 2953 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
temptation | +0.006 |
lot | +0.006 |
anish | +0.006 |
Tears | +0.006 |
Enjoy | +0.006 |
Neg logit contributions | |
spac | -0.006 |
v | -0.006 |
aky | -0.006 |
ev | -0.005 |
b | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
v | +0.016 |
aky | +0.016 |
spac | +0.015 |
ang | +0.014 |
ev | +0.014 |
Neg logit contributions | |
temptation | -0.013 |
risk | -0.012 |
lot | -0.012 |
anish | -0.012 |
� | -0.011 |
Token | end |
Token ID | 886 |
Feature activation | -9.40e-03 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
consequences | +0.001 |
risk | +0.001 |
deed | +0.001 |
Neg logit contributions | |
spac | -0.001 |
aky | -0.001 |
v | -0.001 |
Tw | -0.001 |
polar | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
v | +0.012 |
spac | +0.011 |
aky | +0.011 |
ev | +0.011 |
ang | +0.010 |
Neg logit contributions | |
temptation | -0.013 |
risk | -0.012 |
lot | -0.012 |
anish | -0.012 |
consequences | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
v | +0.062 |
aky | +0.059 |
spac | +0.057 |
azz | +0.055 |
b | +0.054 |
Neg logit contributions | |
temptation | -0.040 |
lot | -0.038 |
risk | -0.036 |
� | -0.035 |
anish | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
spac | +0.002 |
aky | +0.002 |
Tw | +0.002 |
v | +0.002 |
ang | +0.002 |
Neg logit contributions | |
anish | -0.002 |
temptation | -0.002 |
consequences | -0.002 |
Tears | -0.002 |
� | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +7.09e-04 |
Pos logit contributions | |
temptation | +0.003 |
risk | +0.002 |
lot | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | Ad |
Token ID | 1215 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
consequences | +0.001 |
lot | +0.001 |
Neg logit contributions | |
spac | -0.001 |
v | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | eline |
Token ID | 4470 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.010 |
anish | +0.010 |
deed | +0.010 |
risk | +0.010 |
Neg logit contributions | |
spac | -0.009 |
polar | -0.009 |
til | -0.009 |
aky | -0.009 |
Pluto | -0.008 |
Token | best |
Token ID | 1266 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
v | +0.010 |
spac | +0.009 |
aky | +0.009 |
ev | +0.009 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.009 |
risk | -0.009 |
anish | -0.009 |
lot | -0.008 |
consequences | -0.008 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
temptation | +0.032 |
wered | +0.031 |
anish | +0.030 |
risk | +0.030 |
aroma | +0.030 |
Neg logit contributions | |
v | -0.020 |
spac | -0.019 |
ang | -0.019 |
aky | -0.018 |
ev | -0.018 |
Token | forever |
Token ID | 8097 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
temptation | +0.022 |
risk | +0.020 |
anish | +0.020 |
consequences | +0.020 |
lot | +0.019 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.016 |
ev | -0.015 |
ang | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
temptation | +0.017 |
anish | +0.016 |
wered | +0.016 |
risk | +0.015 |
consequence | +0.015 |
Neg logit contributions | |
v | -0.012 |
aky | -0.012 |
spac | -0.012 |
trapped | -0.011 |
ev | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.003 |
lot | -0.003 |
Token | On |
Token ID | 2202 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
anish | +0.002 |
risk | +0.002 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
b | -0.001 |
ev | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
v | +0.065 |
aky | +0.061 |
spac | +0.060 |
ang | +0.059 |
b | +0.057 |
Neg logit contributions | |
lot | -0.037 |
temptation | -0.036 |
top | -0.034 |
risk | -0.033 |
wered | -0.033 |
Token | sunny |
Token ID | 27737 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
v | +0.049 |
spac | +0.047 |
aky | +0.045 |
ang | +0.044 |
ev | +0.044 |
Neg logit contributions | |
lot | -0.037 |
temptation | -0.035 |
risk | -0.034 |
top | -0.030 |
pause | -0.030 |
Token | day |
Token ID | 1110 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
v | +0.056 |
spac | +0.054 |
aky | +0.054 |
ev | +0.051 |
ang | +0.050 |
Neg logit contributions | |
temptation | -0.049 |
risk | -0.045 |
lot | -0.045 |
anish | -0.044 |
consequences | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
v | +0.014 |
spac | +0.014 |
aky | +0.013 |
ang | +0.013 |
Tw | +0.013 |
Neg logit contributions | |
temptation | -0.028 |
anish | -0.027 |
consequences | -0.027 |
risk | -0.026 |
deed | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
spac | +0.017 |
v | +0.017 |
aky | +0.016 |
Tw | +0.016 |
ev | +0.016 |
Neg logit contributions | |
temptation | -0.023 |
anish | -0.022 |
risk | -0.022 |
consequences | -0.022 |
deed | -0.021 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
v | +0.007 |
aky | +0.007 |
b | +0.007 |
ev | +0.006 |
spac | +0.006 |
Neg logit contributions | |
temptation | -0.006 |
lot | -0.006 |
risk | -0.006 |
anish | -0.005 |
pause | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
spac | +0.023 |
inery | +0.022 |
Tw | +0.022 |
v | +0.022 |
ang | +0.021 |
Neg logit contributions | |
temptation | -0.017 |
consequences | -0.016 |
anish | -0.016 |
lot | -0.015 |
fruits | -0.015 |
Token | Mia |
Token ID | 32189 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
aky | +0.006 |
ev | +0.006 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.008 |
lot | -0.007 |
risk | -0.007 |
anish | -0.007 |
consequences | -0.007 |
Token | ," |
Token ID | 553 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
spac | +0.007 |
azz | +0.006 |
v | +0.006 |
ang | +0.006 |
aky | +0.006 |
Neg logit contributions | |
temptation | -0.005 |
lot | -0.005 |
consequences | -0.005 |
risk | -0.005 |
anish | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
v | +0.011 |
aky | +0.010 |
spac | +0.010 |
ev | +0.009 |
b | +0.009 |
Neg logit contributions | |
temptation | -0.011 |
lot | -0.010 |
risk | -0.010 |
anish | -0.010 |
grapes | -0.009 |
Token | comet |
Token ID | 31733 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
v | +0.007 |
aky | +0.007 |
spac | +0.006 |
azz | +0.006 |
ev | +0.006 |
Neg logit contributions | |
temptation | -0.007 |
lot | -0.007 |
risk | -0.007 |
consequences | -0.007 |
anish | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
aky | +0.037 |
ev | +0.036 |
v | +0.035 |
eddy | +0.035 |
inery | +0.034 |
Neg logit contributions | |
face | -0.054 |
lot | -0.053 |
pause | -0.053 |
temptation | -0.052 |
anish | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.002 |
lot | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
consequences | -0.001 |
lot | -0.001 |
anish | -0.001 |
Token | I |
Token ID | 40 |
Feature activation | -4.40e-04 |
Pos logit contributions | |
temptation | +0.012 |
risk | +0.011 |
lot | +0.010 |
anish | +0.010 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.022 |
spac | -0.021 |
aky | -0.021 |
ev | -0.020 |
ang | -0.020 |
Token | am |
Token ID | 716 |
Feature activation | -5.86e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
ang | +0.001 |
ents | +0.001 |
eddy | +0.001 |
Neg logit contributions | |
lot | -0.000 |
risk | -0.000 |
temptation | -0.000 |
Enjoy | -0.000 |
taste | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
v | +0.009 |
aky | +0.008 |
spac | +0.008 |
b | +0.008 |
ents | +0.008 |
Neg logit contributions | |
temptation | -0.013 |
� | -0.013 |
anish | -0.013 |
aroma | -0.013 |
risk | -0.013 |
Token | number |
Token ID | 1271 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
wrapped | +0.003 |
ck | +0.003 |
spac | +0.003 |
said | +0.003 |
z | +0.003 |
Neg logit contributions | |
consequences | -0.004 |
mons | -0.004 |
grapes | -0.004 |
temptation | -0.004 |
lot | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
anish | +0.012 |
consequences | +0.011 |
� | +0.011 |
Neg logit contributions | |
v | -0.012 |
spac | -0.012 |
aky | -0.012 |
ev | -0.011 |
b | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
aky | +0.006 |
ev | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.006 |
anish | -0.006 |
lot | -0.006 |
� | -0.006 |
Token | m |
Token ID | 285 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
temptation | +0.008 |
lot | +0.007 |
risk | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.009 |
spac | -0.009 |
aky | -0.009 |
ev | -0.009 |
ang | -0.009 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
temptation | +0.020 |
risk | +0.019 |
anish | +0.019 |
lot | +0.019 |
consequences | +0.019 |
Neg logit contributions | |
v | -0.018 |
aky | -0.017 |
spac | -0.016 |
ang | -0.016 |
ev | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
temptation | +0.076 |
wered | +0.072 |
anish | +0.072 |
lot | +0.071 |
risk | +0.071 |
Neg logit contributions | |
v | -0.049 |
b | -0.045 |
aky | -0.045 |
ev | -0.044 |
wrapped | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
aky | +0.006 |
ev | +0.005 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
anish | -0.006 |
lot | -0.006 |
consequences | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +6.99e-04 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
anish | +0.013 |
lot | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.014 |
spac | -0.013 |
aky | -0.013 |
ev | -0.013 |
ang | -0.012 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
lot | +0.001 |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ang | -0.001 |
ev | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
lot | +0.012 |
anish | +0.011 |
consequences | +0.011 |
Neg logit contributions | |
v | -0.033 |
spac | -0.033 |
aky | -0.033 |
ev | -0.031 |
ang | -0.031 |
Token | started |
Token ID | 2067 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
temptation | +0.003 |
risk | +0.003 |
anish | +0.003 |
lot | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
b | -0.002 |
Token | numbering |
Token ID | 47622 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
v | +0.016 |
spac | +0.015 |
b | +0.015 |
z | +0.015 |
wrapped | +0.014 |
Neg logit contributions | |
temptation | -0.016 |
anish | -0.016 |
risk | -0.015 |
consequences | -0.015 |
wered | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
temptation | +0.015 |
risk | +0.014 |
anish | +0.014 |
� | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.013 |
spac | -0.012 |
aky | -0.012 |
b | -0.012 |
ev | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
v | +0.011 |
spac | +0.010 |
aky | +0.010 |
ev | +0.010 |
ang | +0.009 |
Neg logit contributions | |
temptation | -0.011 |
risk | -0.010 |
lot | -0.010 |
anish | -0.010 |
consequences | -0.010 |
Token | m |
Token ID | 285 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
temptation | +0.006 |
lot | +0.006 |
consequences | +0.006 |
risk | +0.006 |
anish | +0.005 |
Neg logit contributions | |
spac | -0.008 |
v | -0.008 |
aky | -0.007 |
ev | -0.007 |
azz | -0.007 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
temptation | +0.019 |
risk | +0.018 |
anish | +0.018 |
lot | +0.018 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.019 |
aky | -0.018 |
spac | -0.018 |
ev | -0.017 |
ang | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
temptation | +0.073 |
anish | +0.070 |
risk | +0.069 |
wered | +0.068 |
lot | +0.068 |
Neg logit contributions | |
v | -0.056 |
b | -0.051 |
aky | -0.051 |
ev | -0.050 |
ang | -0.049 |
Token | She |
Token ID | 1375 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
risk | +0.004 |
temptation | +0.004 |
aroma | +0.004 |
consequences | +0.004 |
anish | +0.004 |
Neg logit contributions | |
spac | -0.002 |
azz | -0.002 |
v | -0.002 |
says | -0.002 |
Robo | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | +8.63e-04 |
Pos logit contributions | |
lot | +0.008 |
anish | +0.008 |
top | +0.008 |
others | +0.007 |
habits | +0.007 |
Neg logit contributions | |
spac | -0.011 |
aky | -0.011 |
ang | -0.011 |
ev | -0.011 |
eddy | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
anish | +0.001 |
lot | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | lost |
Token ID | 2626 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
azz | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
lot | -0.007 |
risk | -0.007 |
consequences | -0.007 |
anish | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
anish | +0.076 |
temptation | +0.074 |
wered | +0.073 |
risk | +0.072 |
consequence | +0.071 |
Neg logit contributions | |
v | -0.050 |
aky | -0.045 |
wrapped | -0.044 |
ev | -0.044 |
ang | -0.044 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ang | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
consequences | -0.003 |
anish | -0.003 |
lot | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | -6.13e-04 |
Pos logit contributions | |
lot | +0.009 |
temptation | +0.008 |
risk | +0.007 |
� | +0.007 |
Enjoy | +0.007 |
Neg logit contributions | |
v | -0.017 |
spac | -0.017 |
aky | -0.016 |
ang | -0.016 |
azz | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
consequences | -0.001 |
� | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
azz | +0.002 |
aky | +0.002 |
ev | +0.002 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.001 |
scent | -0.001 |
Dogs | -0.001 |
others | -0.001 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
temptation | +0.010 |
lot | +0.010 |
� | +0.010 |
Dogs | +0.009 |
risk | +0.009 |
Neg logit contributions | |
spac | -0.020 |
aky | -0.018 |
v | -0.018 |
lov | -0.018 |
astronauts | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
anish | +0.088 |
wered | +0.083 |
temptation | +0.082 |
consequence | +0.081 |
risk | +0.080 |
Neg logit contributions | |
v | -0.043 |
wrapped | -0.040 |
aky | -0.040 |
said | -0.039 |
b | -0.038 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.007 |
consequences | +0.007 |
risk | +0.007 |
wered | +0.006 |
Neg logit contributions | |
spac | -0.012 |
aky | -0.012 |
v | -0.012 |
Tw | -0.011 |
wrapped | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-03 |
Pos logit contributions | |
temptation | +0.011 |
lot | +0.010 |
risk | +0.010 |
anish | +0.009 |
consequences | +0.009 |
Neg logit contributions | |
v | -0.014 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
lot | -0.005 |
anish | -0.005 |
consequences | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
spac | +0.002 |
aky | +0.002 |
v | +0.002 |
polar | +0.001 |
trapped | +0.001 |
Neg logit contributions | |
lot | -0.001 |
risk | -0.001 |
temptation | -0.001 |
top | -0.001 |
anish | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
temptation | +0.003 |
wered | +0.003 |
risk | +0.003 |
anish | +0.003 |
consequence | +0.003 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
eddy | -0.002 |
aky | -0.002 |
wrapped | -0.002 |
Token | Sue |
Token ID | 26089 |
Feature activation | +9.21e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.003 |
ang | +0.003 |
ev | +0.003 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
consequences | -0.005 |
lot | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -9.20e-06 |
Pos logit contributions | |
lot | +0.007 |
others | +0.006 |
stomach | +0.006 |
temptation | +0.006 |
habits | +0.006 |
Neg logit contributions | |
spac | -0.016 |
v | -0.015 |
azz | -0.014 |
polar | -0.014 |
Pluto | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -4.05e-04 |
Token | m |
Token ID | 285 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
azz | +0.001 |
ev | +0.001 |
Neg logit contributions | |
lot | -0.001 |
temptation | -0.000 |
risk | -0.000 |
scent | -0.000 |
consequences | -0.000 |
Token | ittens |
Token ID | 34978 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
temptation | +0.012 |
lot | +0.011 |
risk | +0.010 |
� | +0.010 |
anish | +0.010 |
Neg logit contributions | |
spac | -0.016 |
v | -0.015 |
aky | -0.015 |
ev | -0.014 |
Tw | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
anish | +0.087 |
wered | +0.082 |
temptation | +0.081 |
consequence | +0.080 |
risk | +0.079 |
Neg logit contributions | |
v | -0.041 |
wrapped | -0.039 |
aky | -0.038 |
said | -0.038 |
b | -0.037 |
Token | much |
Token ID | 881 |
Feature activation | +7.12e-04 |
Pos logit contributions | |
v | +0.009 |
spac | +0.008 |
aky | +0.008 |
ev | +0.008 |
ang | +0.008 |
Neg logit contributions | |
temptation | -0.009 |
risk | -0.008 |
lot | -0.008 |
anish | -0.008 |
consequences | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
risk | +0.001 |
consequences | +0.001 |
� | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ang | -0.001 |
ev | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
lot | -0.003 |
consequences | -0.003 |
Token | wore |
Token ID | 12408 |
Feature activation | -2.57e-04 |
Pos logit contributions | |
lot | +0.006 |
temptation | +0.006 |
risk | +0.005 |
� | +0.005 |
stomach | +0.005 |
Neg logit contributions | |
v | -0.010 |
spac | -0.010 |
aky | -0.010 |
ang | -0.010 |
ev | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.006 |
risk | +0.006 |
top | +0.005 |
anish | +0.005 |
Neg logit contributions | |
aky | -0.011 |
spac | -0.011 |
ev | -0.011 |
v | -0.011 |
polar | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
v | +0.004 |
aky | +0.004 |
spac | +0.004 |
b | +0.004 |
ev | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
lot | -0.004 |
anish | -0.004 |
risk | -0.004 |
� | -0.003 |
Token | used |
Token ID | 973 |
Feature activation | -8.81e-04 |
Pos logit contributions | |
lot | +0.011 |
temptation | +0.010 |
anish | +0.010 |
aroma | +0.010 |
face | +0.010 |
Neg logit contributions | |
spac | -0.011 |
v | -0.011 |
aky | -0.011 |
ang | -0.011 |
ev | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -3.35e-04 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
anish | -0.001 |
lot | -0.001 |
consequences | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
v | +0.000 |
spac | +0.000 |
aky | +0.000 |
b | +0.000 |
ev | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
risk | -0.000 |
consequences | -0.000 |
deed | -0.000 |
Token | itt |
Token ID | 715 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
temptation | +0.019 |
anish | +0.018 |
risk | +0.018 |
lot | +0.018 |
consequences | +0.017 |
Neg logit contributions | |
v | -0.021 |
aky | -0.019 |
ev | -0.019 |
ang | -0.018 |
spac | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.69e-03 |
Pos logit contributions | |
temptation | +0.069 |
risk | +0.066 |
lot | +0.065 |
anish | +0.063 |
consequences | +0.063 |
Neg logit contributions | |
v | -0.058 |
spac | -0.058 |
aky | -0.055 |
ev | -0.053 |
ang | -0.053 |
Token | take |
Token ID | 1011 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.003 |
ev | +0.003 |
b | +0.003 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
anish | -0.003 |
consequences | -0.003 |
lot | -0.003 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
temptation | +0.003 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
lot | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
b | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
temptation | +0.020 |
anish | +0.019 |
risk | +0.019 |
� | +0.019 |
consequences | +0.018 |
Neg logit contributions | |
v | -0.016 |
spac | -0.016 |
aky | -0.015 |
wrapped | -0.014 |
b | -0.014 |
Token | pan |
Token ID | 3425 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
temptation | +0.012 |
anish | +0.011 |
wered | +0.011 |
deed | +0.011 |
� | +0.011 |
Neg logit contributions | |
spac | -0.013 |
v | -0.012 |
aky | -0.012 |
wrapped | -0.011 |
b | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
temptation | +0.004 |
risk | +0.004 |
anish | +0.004 |
lot | +0.004 |
� | +0.004 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
wrapped | -0.003 |
Token | into |
Token ID | 656 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
b | +0.004 |
wrapped | +0.004 |
Neg logit contributions | |
temptation | -0.004 |
anish | -0.004 |
consequences | -0.003 |
aroma | -0.003 |
risk | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
temptation | +0.009 |
risk | +0.008 |
lot | +0.008 |
anish | +0.008 |
consequences | +0.008 |
Neg logit contributions | |
v | -0.010 |
spac | -0.009 |
aky | -0.009 |
ev | -0.009 |
ang | -0.009 |
Token | woods |
Token ID | 16479 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
temptation | +0.009 |
risk | +0.008 |
lot | +0.008 |
anish | +0.008 |
consequences | +0.008 |
Neg logit contributions | |
v | -0.012 |
spac | -0.011 |
aky | -0.011 |
ev | -0.011 |
ang | -0.011 |
Token | collecting |
Token ID | 13157 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
temptation | +0.003 |
anish | +0.003 |
consequences | +0.003 |
aroma | +0.003 |
lot | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.002 |
aky | -0.002 |
ang | -0.002 |
wrapped | -0.002 |
Token | berries |
Token ID | 36322 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
temptation | +0.005 |
anish | +0.005 |
� | +0.005 |
risk | +0.005 |
consequence | +0.005 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
b | -0.006 |
wrapped | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
temptation | +0.033 |
anish | +0.031 |
risk | +0.030 |
consequences | +0.030 |
lot | +0.029 |
Neg logit contributions | |
v | -0.029 |
aky | -0.028 |
spac | -0.027 |
b | -0.026 |
ang | -0.026 |
Token | nuts |
Token ID | 14380 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
anish | +0.003 |
temptation | +0.003 |
risk | +0.002 |
Dogs | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
wrapped | -0.002 |
said | -0.002 |
b | -0.002 |
imagined | -0.002 |
pretended | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
temptation | +0.003 |
anish | +0.003 |
risk | +0.002 |
lot | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.002 |
aky | -0.002 |
spac | -0.002 |
b | -0.002 |
ev | -0.002 |
Token | One |
Token ID | 1881 |
Feature activation | +9.91e-04 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
consequence | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
ev | -0.001 |
says | -0.001 |
aky | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
temptation | +0.001 |
lot | +0.001 |
risk | +0.001 |
deed | +0.001 |
consequences | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
azz | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
b | +0.004 |
aky | +0.004 |
ang | +0.004 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.002 |
consequences | -0.002 |
anish | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
v | +0.009 |
aky | +0.009 |
spac | +0.009 |
ck | +0.008 |
ev | +0.008 |
Neg logit contributions | |
lot | -0.005 |
anish | -0.004 |
risk | -0.004 |
temptation | -0.004 |
� | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
v | +0.007 |
spac | +0.006 |
azz | +0.006 |
ann | +0.006 |
ents | +0.006 |
Neg logit contributions | |
lot | -0.004 |
top | -0.003 |
anish | -0.003 |
Tears | -0.003 |
pause | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
b | +0.003 |
aky | +0.003 |
ev | +0.003 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.001 |
risk | -0.001 |
� | -0.001 |
deed | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
lot | +0.017 |
temptation | +0.016 |
risk | +0.016 |
deed | +0.015 |
anish | +0.014 |
Neg logit contributions | |
v | -0.019 |
spac | -0.017 |
aky | -0.017 |
b | -0.017 |
ck | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
temptation | +0.008 |
lot | +0.007 |
risk | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.009 |
spac | -0.008 |
aky | -0.008 |
ev | -0.008 |
b | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.03e-04 |
Pos logit contributions | |
temptation | +0.031 |
risk | +0.030 |
anish | +0.029 |
consequences | +0.029 |
lot | +0.029 |
Neg logit contributions | |
v | -0.017 |
spac | -0.016 |
aky | -0.016 |
ev | -0.015 |
ang | -0.015 |
Token | went |
Token ID | 1816 |
Feature activation | -7.07e-03 |
Pos logit contributions | |
spac | +0.001 |
ang | +0.001 |
v | +0.001 |
ents | +0.001 |
Pluto | +0.001 |
Neg logit contributions | |
lot | -0.001 |
temptation | -0.001 |
risk | -0.001 |
consequences | -0.001 |
anish | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
v | +0.011 |
spac | +0.011 |
aky | +0.011 |
ev | +0.010 |
ang | +0.010 |
Neg logit contributions | |
temptation | -0.008 |
anish | -0.007 |
risk | -0.007 |
lot | -0.007 |
consequences | -0.007 |
Token | camp |
Token ID | 1413 |
Feature activation | -8.92e-04 |
Pos logit contributions | |
aky | +0.019 |
v | +0.019 |
ang | +0.018 |
b | +0.018 |
spac | +0.017 |
Neg logit contributions | |
lot | -0.011 |
temptation | -0.011 |
risk | -0.010 |
wered | -0.010 |
pause | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ang | +0.001 |
ev | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
risk | -0.001 |
consequences | -0.001 |
lot | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
lot | +0.002 |
pause | +0.001 |
face | +0.001 |
Tears | +0.001 |
eyes | +0.001 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ang | -0.002 |
dot | -0.002 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
temptation | +0.004 |
risk | +0.004 |
lot | +0.004 |
anish | +0.004 |
consequences | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
ang | -0.003 |
Token | trying |
Token ID | 2111 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
spac | +0.001 |
v | +0.001 |
Ar | +0.001 |
aky | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.002 |
lot | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
b | +0.004 |
z | +0.004 |
Robo | +0.003 |
wrapped | +0.003 |
said | +0.003 |
Neg logit contributions | |
� | -0.008 |
anish | -0.008 |
temptation | -0.007 |
aroma | -0.007 |
deed | -0.007 |
Token | climb |
Token ID | 12080 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
temptation | +0.004 |
anish | +0.004 |
lot | +0.003 |
consequences | +0.003 |
risk | +0.003 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
aky | -0.005 |
ev | -0.004 |
b | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
temptation | +0.010 |
risk | +0.009 |
anish | +0.009 |
lot | +0.009 |
consequences | +0.009 |
Neg logit contributions | |
v | -0.009 |
spac | -0.009 |
aky | -0.009 |
ev | -0.009 |
ang | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -9.99e-05 |
Pos logit contributions | |
temptation | +0.030 |
risk | +0.028 |
anish | +0.028 |
� | +0.027 |
consequences | +0.027 |
Neg logit contributions | |
v | -0.022 |
spac | -0.021 |
aky | -0.020 |
ev | -0.019 |
ang | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
spac | +0.000 |
v | +0.000 |
aky | +0.000 |
ev | +0.000 |
ang | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
risk | -0.000 |
consequences | -0.000 |
lot | -0.000 |
Token | crib |
Token ID | 48083 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
lot | +0.005 |
temptation | +0.005 |
risk | +0.004 |
consequences | +0.004 |
stomach | +0.004 |
Neg logit contributions | |
v | -0.006 |
aky | -0.006 |
azz | -0.006 |
spac | -0.006 |
b | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-04 |
Pos logit contributions | |
v | +0.020 |
spac | +0.019 |
aky | +0.019 |
ev | +0.018 |
ang | +0.018 |
Neg logit contributions | |
temptation | -0.018 |
risk | -0.017 |
lot | -0.017 |
anish | -0.017 |
consequences | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
ev | +0.001 |
aky | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
consequences | -0.001 |
anish | -0.001 |
deed | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
v | +0.002 |
aky | +0.002 |
spac | +0.002 |
b | +0.002 |
Tw | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
anish | -0.002 |
risk | -0.002 |
consequences | -0.002 |
� | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
z | +0.002 |
Tw | +0.001 |
b | +0.001 |
Neg logit contributions | |
anish | -0.002 |
temptation | -0.002 |
� | -0.002 |
aroma | -0.002 |
risk | -0.002 |
Token | fly |
Token ID | 6129 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
temptation | +0.005 |
anish | +0.005 |
consequences | +0.005 |
� | +0.005 |
risk | +0.004 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.003 |
Tw | -0.003 |
b | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
v | +0.014 |
spac | +0.014 |
aky | +0.014 |
ev | +0.013 |
ang | +0.013 |
Neg logit contributions | |
temptation | -0.017 |
risk | -0.016 |
lot | -0.016 |
anish | -0.016 |
consequences | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
Tw | +0.004 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
consequences | -0.005 |
lot | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
spac | +0.020 |
ev | +0.019 |
v | +0.019 |
azz | +0.019 |
aky | +0.019 |
Neg logit contributions | |
temptation | -0.012 |
lot | -0.012 |
others | -0.011 |
risk | -0.011 |
wered | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
temptation | +0.020 |
lot | +0.020 |
risk | +0.019 |
� | +0.018 |
consequences | +0.017 |
Neg logit contributions | |
v | -0.029 |
spac | -0.029 |
aky | -0.028 |
ev | -0.027 |
ang | -0.027 |
Token | One |
Token ID | 1881 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
temptation | +0.008 |
risk | +0.007 |
lot | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.008 |
spac | -0.008 |
aky | -0.008 |
ev | -0.007 |
ang | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
spac | +0.005 |
v | +0.005 |
Robo | +0.005 |
ents | +0.005 |
azz | +0.005 |
Neg logit contributions | |
lot | -0.003 |
temptation | -0.002 |
risk | -0.002 |
deed | -0.002 |
pause | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
temptation | +0.011 |
anish | +0.010 |
consequences | +0.010 |
warnings | +0.010 |
aroma | +0.010 |
Neg logit contributions | |
v | -0.005 |
spac | -0.004 |
b | -0.004 |
ev | -0.004 |
ang | -0.004 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
spac | +0.002 |
wrapped | +0.002 |
b | +0.002 |
Tw | +0.002 |
polar | +0.002 |
Neg logit contributions | |
anish | -0.008 |
temptation | -0.008 |
consequences | -0.007 |
rules | -0.007 |
deed | -0.007 |
Token | excited |
Token ID | 6568 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
spac | +0.001 |
azz | +0.001 |
ev | +0.001 |
unicorn | +0.001 |
v | +0.001 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.002 |
Enjoy | -0.002 |
others | -0.002 |
risk | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
anish | +0.009 |
temptation | +0.009 |
� | +0.009 |
consequence | +0.008 |
wered | +0.008 |
Neg logit contributions | |
v | -0.007 |
said | -0.006 |
says | -0.006 |
ev | -0.006 |
b | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
temptation | +0.008 |
anish | +0.008 |
risk | +0.008 |
consequences | +0.008 |
� | +0.008 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
aky | -0.005 |
ev | -0.005 |
b | -0.005 |
Token | spl |
Token ID | 4328 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
temptation | +0.007 |
lot | +0.007 |
risk | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.008 |
spac | -0.008 |
aky | -0.008 |
ev | -0.007 |
ang | -0.007 |
Token | ashed |
Token ID | 5263 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
v | +0.002 |
aky | +0.001 |
ang | +0.001 |
b | +0.001 |
azz | +0.001 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.002 |
consequences | -0.002 |
rules | -0.002 |
lot | -0.002 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
� | +0.015 |
Dogs | +0.014 |
Sale | +0.014 |
consequence | +0.014 |
risk | +0.014 |
Neg logit contributions | |
v | -0.007 |
b | -0.007 |
aky | -0.007 |
wrapped | -0.006 |
z | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
temptation | +0.037 |
anish | +0.036 |
risk | +0.036 |
consequences | +0.036 |
Enjoy | +0.036 |
Neg logit contributions | |
v | -0.023 |
aky | -0.022 |
wrapped | -0.022 |
spac | -0.022 |
b | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
lot | +0.002 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | water |
Token ID | 1660 |
Feature activation | -4.64e-03 |
Pos logit contributions | |
anish | +0.008 |
� | +0.008 |
Sale | +0.008 |
ados | +0.008 |
Enjoy | +0.008 |
Neg logit contributions | |
polar | -0.005 |
spac | -0.005 |
aky | -0.005 |
z | -0.005 |
v | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
v | +0.005 |
wrapped | +0.005 |
b | +0.005 |
aky | +0.005 |
spac | +0.005 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.007 |
anish | -0.007 |
Enjoy | -0.007 |
consequences | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.002 |
anish | -0.002 |
risk | -0.002 |
consequences | -0.001 |
lot | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
spac | +0.004 |
ev | +0.003 |
v | +0.003 |
til | +0.003 |
unicorn | +0.003 |
Neg logit contributions | |
lot | -0.003 |
temptation | -0.003 |
anish | -0.002 |
rules | -0.002 |
top | -0.002 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
ang | +0.003 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
anish | -0.001 |
risk | -0.001 |
consequences | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e-04 |
Pos logit contributions | |
temptation | +0.028 |
risk | +0.026 |
anish | +0.026 |
consequences | +0.026 |
lot | +0.025 |
Neg logit contributions | |
v | -0.018 |
spac | -0.017 |
aky | -0.016 |
ev | -0.016 |
ang | -0.015 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
temptation | +0.000 |
lot | +0.000 |
risk | +0.000 |
anish | +0.000 |
consequences | +0.000 |
Neg logit contributions | |
v | -0.000 |
aky | -0.000 |
spac | -0.000 |
ev | -0.000 |
ang | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
v | +0.002 |
aky | +0.002 |
spac | +0.002 |
ev | +0.002 |
says | +0.002 |
Neg logit contributions | |
temptation | -0.003 |
risk | -0.003 |
wered | -0.003 |
lot | -0.003 |
anish | -0.003 |
Token | we |
Token ID | 356 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
temptation | +0.007 |
risk | +0.007 |
consequences | +0.007 |
anish | +0.007 |
� | +0.007 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.005 |
ev | -0.005 |
b | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
temptation | +0.001 |
anish | +0.001 |
risk | +0.001 |
deed | +0.001 |
aroma | +0.001 |
Neg logit contributions | |
v | -0.001 |
aky | -0.001 |
spac | -0.001 |
ev | -0.001 |
b | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.003 |
top | +0.003 |
fruits | +0.003 |
others | +0.003 |
Neg logit contributions | |
azz | -0.005 |
v | -0.005 |
jo | -0.005 |
ev | -0.005 |
aky | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
aky | +0.002 |
v | +0.002 |
spac | +0.002 |
b | +0.002 |
ev | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
anish | -0.002 |
lot | -0.002 |
risk | -0.002 |
Enjoy | -0.002 |
Token | I |
Token ID | 314 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
v | +0.019 |
spac | +0.019 |
aky | +0.018 |
ev | +0.017 |
ang | +0.017 |
Neg logit contributions | |
temptation | -0.021 |
risk | -0.019 |
lot | -0.019 |
anish | -0.019 |
consequences | -0.019 |
Token | am |
Token ID | 716 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
spac | +0.012 |
v | +0.012 |
aky | +0.011 |
ev | +0.011 |
ang | +0.011 |
Neg logit contributions | |
temptation | -0.009 |
lot | -0.009 |
risk | -0.009 |
consequences | -0.008 |
anish | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
said | +0.004 |
polar | +0.004 |
wrapped | +0.004 |
stuck | +0.004 |
spac | +0.004 |
Neg logit contributions | |
temptation | -0.009 |
� | -0.009 |
anish | -0.009 |
aroma | -0.009 |
risk | -0.008 |
Token | dad |
Token ID | 9955 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
spac | +0.003 |
v | +0.003 |
aky | +0.003 |
b | +0.003 |
polar | +0.003 |
Neg logit contributions | |
temptation | -0.004 |
anish | -0.004 |
aroma | -0.004 |
Enjoy | -0.004 |
risk | -0.004 |
Token | teaching |
Token ID | 7743 |
Feature activation | +5.79e-04 |
Pos logit contributions | |
v | +0.005 |
aky | +0.004 |
spac | +0.004 |
ev | +0.004 |
b | +0.004 |
Neg logit contributions | |
temptation | -0.009 |
anish | -0.009 |
lot | -0.008 |
� | -0.008 |
risk | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
� | +0.001 |
anish | +0.001 |
risk | +0.001 |
aroma | +0.001 |
temptation | +0.001 |
Neg logit contributions | |
v | -0.000 |
said | -0.000 |
Robo | -0.000 |
says | -0.000 |
b | -0.000 |
Token | how |
Token ID | 703 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
� | +0.016 |
aroma | +0.014 |
umm | +0.013 |
OM | +0.013 |
anish | +0.013 |
Neg logit contributions | |
v | -0.007 |
else | -0.006 |
b | -0.006 |
says | -0.006 |
aky | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
anish | +0.013 |
aroma | +0.013 |
� | +0.013 |
wered | +0.012 |
scent | +0.011 |
Neg logit contributions | |
v | -0.009 |
b | -0.009 |
spac | -0.008 |
else | -0.008 |
trapped | -0.008 |
Token | whistle |
Token ID | 16121 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
ck | +0.006 |
v | +0.005 |
wrapped | +0.005 |
spac | +0.005 |
b | +0.005 |
Neg logit contributions | |
temptation | -0.007 |
anish | -0.007 |
consequences | -0.007 |
aroma | -0.007 |
Tears | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
temptation | +0.009 |
risk | +0.008 |
� | +0.008 |
anish | +0.008 |
aroma | +0.008 |
Neg logit contributions | |
v | -0.007 |
spac | -0.007 |
aky | -0.007 |
b | -0.006 |
Tw | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
risk | +0.013 |
temptation | +0.013 |
anish | +0.012 |
consequences | +0.012 |
lot | +0.012 |
Neg logit contributions | |
v | -0.005 |
spac | -0.005 |
aky | -0.004 |
ents | -0.004 |
says | -0.004 |
Token | my |
Token ID | 1820 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
ang | +0.004 |
ev | +0.004 |
Tw | +0.004 |
Neg logit contributions | |
temptation | -0.006 |
anish | -0.005 |
risk | -0.005 |
consequences | -0.005 |
lot | -0.005 |
Token | whist |
Token ID | 32262 |
Feature activation | +5.08e-03 |
Pos logit contributions | |
lot | +0.011 |
temptation | +0.011 |
anish | +0.011 |
risk | +0.011 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.012 |
spac | -0.012 |
ang | -0.011 |
aky | -0.011 |
ev | -0.011 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
b | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
lot | -0.001 |
anish | -0.001 |
risk | -0.001 |
� | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.012 |
anish | +0.012 |
lot | +0.012 |
consequences | +0.012 |
Neg logit contributions | |
v | -0.011 |
spac | -0.011 |
aky | -0.010 |
ev | -0.010 |
ang | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | -6.57e-03 |
Pos logit contributions | |
v | +0.004 |
azz | +0.004 |
ev | +0.004 |
spac | +0.004 |
Ar | +0.003 |
Neg logit contributions | |
lot | -0.003 |
temptation | -0.002 |
others | -0.002 |
Tears | -0.002 |
face | -0.002 |
Token | proud |
Token ID | 6613 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
ev | +0.008 |
v | +0.008 |
azz | +0.008 |
spac | +0.007 |
Pluto | +0.007 |
Neg logit contributions | |
temptation | -0.009 |
lot | -0.009 |
others | -0.008 |
face | -0.008 |
law | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
temptation | +0.006 |
risk | +0.006 |
lot | +0.006 |
anish | +0.006 |
consequences | +0.006 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.005 |
ev | -0.005 |
ang | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
risk | +0.016 |
temptation | +0.015 |
anish | +0.015 |
aroma | +0.015 |
deed | +0.015 |
Neg logit contributions | |
spac | -0.010 |
v | -0.010 |
aky | -0.009 |
ev | -0.009 |
Robo | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
anish | +0.001 |
temptation | +0.001 |
wered | +0.001 |
risk | +0.001 |
Enjoy | +0.001 |
Neg logit contributions | |
spac | -0.001 |
v | -0.001 |
aky | -0.001 |
wrapped | -0.001 |
says | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.012 |
risk | -0.011 |
anish | -0.011 |
lot | -0.011 |
consequences | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-04 |
Pos logit contributions | |
v | +0.016 |
spac | +0.016 |
wrapped | +0.016 |
z | +0.015 |
b | +0.015 |
Neg logit contributions | |
anish | -0.019 |
temptation | -0.019 |
risk | -0.018 |
� | -0.018 |
wered | -0.017 |
Token | cl |
Token ID | 537 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
spac | +0.000 |
v | +0.000 |
wrapped | +0.000 |
aky | +0.000 |
ck | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
consequences | -0.000 |
� | -0.000 |
mons | -0.000 |
Token | ap |
Token ID | 499 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
spac | +0.018 |
v | +0.018 |
aky | +0.018 |
ev | +0.018 |
b | +0.017 |
Neg logit contributions | |
temptation | -0.008 |
anish | -0.007 |
risk | -0.007 |
lot | -0.006 |
� | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
temptation | +0.009 |
lot | +0.009 |
risk | +0.009 |
anish | +0.009 |
� | +0.008 |
Neg logit contributions | |
v | -0.007 |
spac | -0.006 |
aky | -0.006 |
ev | -0.006 |
ang | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
lot | +0.004 |
temptation | +0.003 |
risk | +0.003 |
pause | +0.003 |
Tears | +0.003 |
Neg logit contributions | |
v | -0.008 |
spac | -0.008 |
aky | -0.008 |
Ar | -0.008 |
Tw | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
aky | +0.015 |
v | +0.015 |
spac | +0.015 |
azz | +0.014 |
ang | +0.014 |
Neg logit contributions | |
lot | -0.007 |
temptation | -0.006 |
risk | -0.006 |
anish | -0.006 |
� | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
lot | +0.004 |
temptation | +0.004 |
risk | +0.003 |
consequences | +0.003 |
grapes | +0.003 |
Neg logit contributions | |
v | -0.007 |
spac | -0.007 |
b | -0.007 |
aky | -0.007 |
ang | -0.007 |
Token | farmer |
Token ID | 18739 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
v | +0.003 |
spac | +0.003 |
aky | +0.003 |
ev | +0.003 |
b | +0.003 |
Neg logit contributions | |
temptation | -0.002 |
lot | -0.002 |
risk | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
temptation | +0.017 |
risk | +0.016 |
lot | +0.016 |
anish | +0.016 |
consequences | +0.016 |
Neg logit contributions | |
v | -0.017 |
spac | -0.016 |
aky | -0.016 |
ev | -0.016 |
ang | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
temptation | +0.005 |
anish | +0.005 |
risk | +0.005 |
consequences | +0.005 |
� | +0.005 |
Neg logit contributions | |
spac | -0.004 |
v | -0.004 |
aky | -0.004 |
polar | -0.004 |
ev | -0.004 |
Token | horse |
Token ID | 8223 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
temptation | +0.002 |
anish | +0.002 |
consequences | +0.002 |
risk | +0.002 |
wered | +0.002 |
Neg logit contributions | |
spac | -0.002 |
v | -0.002 |
aky | -0.002 |
ang | -0.001 |
ev | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
temptation | +0.020 |
anish | +0.018 |
consequences | +0.018 |
risk | +0.018 |
aroma | +0.018 |
Neg logit contributions | |
v | -0.012 |
spac | -0.011 |
aky | -0.011 |
ang | -0.011 |
polar | -0.010 |
Token | The |
Token ID | 383 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
temptation | +0.006 |
lot | +0.005 |
risk | +0.005 |
anish | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.007 |
aky | -0.007 |
spac | -0.007 |
ev | -0.006 |
b | -0.006 |
Token | farmer |
Token ID | 18739 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
temptation | +0.021 |
anish | +0.020 |
risk | +0.020 |
� | +0.019 |
consequences | +0.019 |
Neg logit contributions | |
spac | -0.013 |
v | -0.013 |
aky | -0.013 |
ev | -0.011 |
ang | -0.011 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
v | +0.021 |
aky | +0.020 |
spac | +0.020 |
ang | +0.018 |
ev | +0.018 |
Neg logit contributions | |
temptation | -0.021 |
lot | -0.020 |
risk | -0.019 |
pause | -0.019 |
top | -0.018 |
Token | did |
Token ID | 750 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
v | +0.013 |
spac | +0.013 |
aky | +0.012 |
ev | +0.012 |
ang | +0.012 |
Neg logit contributions | |
temptation | -0.012 |
risk | -0.011 |
lot | -0.011 |
anish | -0.010 |
consequences | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
anish | +0.003 |
aroma | +0.002 |
environment | +0.002 |
� | +0.002 |
deed | +0.002 |
Neg logit contributions | |
Robo | -0.002 |
ck | -0.002 |
b | -0.002 |
else | -0.002 |
says | -0.002 |
Token | listen |
Token ID | 6004 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
temptation | +0.003 |
� | +0.003 |
anish | +0.003 |
lot | +0.003 |
risk | +0.003 |
Neg logit contributions | |
v | -0.008 |
aky | -0.007 |
spac | -0.007 |
ev | -0.007 |
b | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
anish | +0.021 |
temptation | +0.020 |
� | +0.020 |
risk | +0.020 |
wered | +0.020 |
Neg logit contributions | |
v | -0.015 |
aky | -0.013 |
spac | -0.013 |
b | -0.013 |
said | -0.012 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
v | +0.010 |
spac | +0.010 |
aky | +0.009 |
ev | +0.009 |
polar | +0.008 |
Neg logit contributions | |
temptation | -0.017 |
anish | -0.016 |
risk | -0.016 |
consequences | -0.016 |
lot | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
ev | +0.008 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
risk | -0.008 |
anish | -0.008 |
lot | -0.008 |
consequences | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
temptation | +0.008 |
risk | +0.007 |
lot | +0.007 |
anish | +0.007 |
consequences | +0.007 |
Neg logit contributions | |
v | -0.006 |
spac | -0.005 |
aky | -0.005 |
ev | -0.005 |
ang | -0.005 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.30e-04 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -8.11e-04 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
lot | -0.001 |
anish | -0.001 |
consequences | -0.001 |
Token | chain |
Token ID | 6333 |
Feature activation | +1.75e-04 |
Pos logit contributions | |
v | +0.001 |
b | +0.001 |
spac | +0.001 |
aky | +0.001 |
says | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
Enjoy | -0.001 |
� | -0.001 |
anish | -0.001 |
aroma | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
spac | +0.014 |
v | +0.014 |
ang | +0.014 |
aky | +0.014 |
b | +0.013 |
Neg logit contributions | |
temptation | -0.007 |
lot | -0.007 |
risk | -0.006 |
deed | -0.006 |
consequences | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
temptation | +0.006 |
risk | +0.005 |
lot | +0.005 |
anish | +0.005 |
consequences | +0.005 |
Neg logit contributions | |
v | -0.006 |
spac | -0.006 |
aky | -0.006 |
ev | -0.005 |
ang | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.35e-05 |
Pos logit contributions | |
lot | +0.009 |
temptation | +0.009 |
risk | +0.008 |
consequences | +0.008 |
anish | +0.008 |
Neg logit contributions | |
spac | -0.017 |
v | -0.017 |
ang | -0.016 |
aky | -0.016 |
azz | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
v | +0.000 |
spac | +0.000 |
ev | +0.000 |
Tw | +0.000 |
wrapped | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
anish | -0.000 |
risk | -0.000 |
� | -0.000 |
consequences | -0.000 |
Token | decor |
Token ID | 11705 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
consequences | +0.004 |
anish | +0.004 |
temptation | +0.004 |
Tears | +0.003 |
consequence | +0.003 |
Neg logit contributions | |
spac | -0.003 |
v | -0.003 |
wrapped | -0.002 |
z | -0.002 |
inery | -0.002 |
Token | ate |
Token ID | 378 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
lot | +0.004 |
others | +0.004 |
temptation | +0.004 |
foods | +0.004 |
top | +0.004 |
Neg logit contributions | |
azz | -0.007 |
spac | -0.007 |
polar | -0.007 |
aky | -0.007 |
orse | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.57e-03 |
Pos logit contributions | |
v | +0.015 |
spac | +0.014 |
aky | +0.014 |
ev | +0.014 |
b | +0.013 |
Neg logit contributions | |
temptation | -0.016 |
risk | -0.015 |
anish | -0.015 |
consequences | -0.015 |
� | -0.014 |
Token | room |
Token ID | 2119 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
v | +0.002 |
aky | +0.002 |
azz | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
lot | -0.002 |
temptation | -0.002 |
top | -0.002 |
fruits | -0.002 |
job | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
anish | +0.020 |
temptation | +0.019 |
risk | +0.019 |
consequences | +0.019 |
Dogs | +0.018 |
Neg logit contributions | |
v | -0.011 |
wrapped | -0.010 |
spac | -0.009 |
aky | -0.009 |
b | -0.008 |
Token | pretty |
Token ID | 2495 |
Feature activation | -9.86e-04 |
Pos logit contributions | |
v | +0.004 |
spac | +0.004 |
aky | +0.004 |
ev | +0.004 |
b | +0.004 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
anish | -0.005 |
consequences | -0.004 |
lot | -0.004 |
Token | pictures |
Token ID | 5986 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
b | +0.001 |
ev | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
anish | -0.001 |
� | -0.001 |
consequences | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
aky | +0.004 |
ang | +0.004 |
b | +0.004 |
Neg logit contributions | |
temptation | -0.006 |
lot | -0.006 |
risk | -0.006 |
consequences | -0.006 |
anish | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
temptation | +0.015 |
consequences | +0.014 |
anish | +0.014 |
risk | +0.013 |
aroma | +0.013 |
Neg logit contributions | |
v | -0.014 |
spac | -0.014 |
aky | -0.013 |
wrapped | -0.013 |
ev | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
risk | +0.002 |
temptation | +0.002 |
lot | +0.002 |
� | +0.002 |
Enjoy | +0.002 |
Neg logit contributions | |
spac | -0.003 |
aky | -0.003 |
v | -0.003 |
ev | -0.003 |
Tw | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
temptation | +0.013 |
risk | +0.013 |
lot | +0.013 |
consequences | +0.012 |
top | +0.012 |
Neg logit contributions | |
aky | -0.018 |
v | -0.017 |
ang | -0.017 |
spac | -0.017 |
b | -0.016 |
Token | slide |
Token ID | 10649 |
Feature activation | -3.31e-04 |
Pos logit contributions | |
temptation | +0.003 |
anish | +0.003 |
deed | +0.003 |
Enjoy | +0.003 |
aroma | +0.002 |
Neg logit contributions | |
spac | -0.003 |
v | -0.003 |
wrapped | -0.003 |
aky | -0.002 |
ev | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
spac | +0.000 |
aky | +0.000 |
polar | +0.000 |
Pluto | +0.000 |
ev | +0.000 |
Neg logit contributions | |
lot | -0.000 |
risk | -0.000 |
temptation | -0.000 |
top | -0.000 |
rules | -0.000 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
v | +0.022 |
aky | +0.021 |
b | +0.020 |
spac | +0.019 |
ang | +0.018 |
Neg logit contributions | |
temptation | -0.017 |
lot | -0.017 |
risk | -0.015 |
stomach | -0.015 |
� | -0.015 |
Token | says |
Token ID | 1139 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
aky | +0.022 |
spac | +0.019 |
ev | +0.019 |
b | +0.018 |
ang | +0.018 |
Neg logit contributions | |
temptation | -0.041 |
grapes | -0.039 |
rules | -0.039 |
lot | -0.039 |
exercises | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
lot | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
v | +0.012 |
b | +0.012 |
ck | +0.011 |
aky | +0.011 |
ev | +0.011 |
Neg logit contributions | |
lot | -0.011 |
temptation | -0.010 |
� | -0.010 |
anish | -0.009 |
All | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
spac | +0.004 |
v | +0.004 |
aky | +0.004 |
b | +0.004 |
eighty | +0.004 |
Neg logit contributions | |
lot | -0.003 |
temptation | -0.002 |
rules | -0.002 |
top | -0.002 |
Enjoy | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
lot | +0.002 |
temptation | +0.002 |
� | +0.002 |
Dogs | +0.002 |
All | +0.002 |
Neg logit contributions | |
ck | -0.003 |
v | -0.003 |
b | -0.003 |
aky | -0.003 |
ang | -0.003 |
Token | loved |
Token ID | 6151 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
temptation | +0.003 |
lot | +0.003 |
risk | +0.003 |
anish | +0.003 |
consequences | +0.003 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
ev | -0.003 |
ang | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +7.89e-04 |
Pos logit contributions | |
v | +0.006 |
spac | +0.006 |
ev | +0.006 |
aky | +0.006 |
polar | +0.006 |
Neg logit contributions | |
temptation | -0.005 |
anish | -0.005 |
risk | -0.005 |
� | -0.004 |
consequences | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
temptation | +0.001 |
consequences | +0.001 |
anish | +0.001 |
risk | +0.001 |
Tears | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
polar | -0.001 |
wrapped | -0.001 |
aky | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | +8.25e-04 |
Pos logit contributions | |
temptation | +0.002 |
lot | +0.002 |
risk | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ev | -0.001 |
ang | -0.001 |
Token | every |
Token ID | 790 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
temptation | +0.001 |
risk | +0.001 |
consequences | +0.001 |
anish | +0.001 |
aroma | +0.001 |
Neg logit contributions | |
v | -0.001 |
spac | -0.001 |
aky | -0.001 |
ang | -0.001 |
Tw | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
v | +0.024 |
spac | +0.023 |
aky | +0.023 |
ev | +0.022 |
ang | +0.021 |
Neg logit contributions | |
temptation | -0.026 |
anish | -0.024 |
risk | -0.024 |
consequences | -0.024 |
lot | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
temptation | +0.015 |
lot | +0.014 |
risk | +0.014 |
anish | +0.013 |
consequences | +0.013 |
Neg logit contributions | |
v | -0.019 |
spac | -0.019 |
aky | -0.019 |
ev | -0.018 |
ang | -0.018 |
Token | One |
Token ID | 1881 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
lot | +0.004 |
� | +0.003 |
temptation | +0.003 |
Dogs | +0.003 |
All | +0.003 |
Neg logit contributions | |
v | -0.006 |
aky | -0.006 |
ck | -0.006 |
b | -0.006 |
ang | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.006 |
lot | -0.005 |
risk | -0.005 |
deed | -0.005 |
anish | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
temptation | +0.007 |
consequences | +0.006 |
risk | +0.006 |
wered | +0.006 |
anish | +0.006 |
Neg logit contributions | |
spac | -0.003 |
v | -0.003 |
ev | -0.003 |
aky | -0.003 |
ang | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
anish | +0.002 |
lot | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | ran |
Token ID | 4966 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
temptation | +0.007 |
consequences | +0.007 |
anish | +0.006 |
lot | +0.006 |
risk | +0.006 |
Neg logit contributions | |
spac | -0.005 |
v | -0.005 |
ev | -0.005 |
says | -0.005 |
wrapped | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
ev | +0.008 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.008 |
anish | -0.008 |
risk | -0.008 |
lot | -0.008 |
consequences | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
temptation | +0.012 |
risk | +0.011 |
lot | +0.011 |
anish | +0.011 |
consequences | +0.010 |
Neg logit contributions | |
v | -0.014 |
spac | -0.014 |
aky | -0.014 |
ev | -0.013 |
ang | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
v | +0.007 |
aky | +0.007 |
spac | +0.006 |
ang | +0.006 |
ev | +0.006 |
Neg logit contributions | |
temptation | -0.006 |
risk | -0.006 |
lot | -0.006 |
anish | -0.005 |
consequences | -0.005 |
Token | store |
Token ID | 3650 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
temptation | +0.002 |
anish | +0.002 |
risk | +0.002 |
consequences | +0.002 |
� | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
b | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -7.47e-04 |
Pos logit contributions | |
v | +0.016 |
spac | +0.015 |
aky | +0.015 |
ev | +0.014 |
ang | +0.014 |
Neg logit contributions | |
temptation | -0.018 |
anish | -0.017 |
risk | -0.017 |
lot | -0.016 |
consequences | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | -9.87e-04 |
Pos logit contributions | |
spac | +0.001 |
v | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
anish | -0.001 |
consequences | -0.001 |
risk | -0.001 |
lot | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
v | +0.001 |
spac | +0.001 |
aky | +0.001 |
ev | +0.001 |
ang | +0.001 |
Neg logit contributions | |
temptation | -0.001 |
risk | -0.001 |
anish | -0.001 |
consequences | -0.001 |
lot | -0.001 |
Token | garden |
Token ID | 11376 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
anish | +0.008 |
eways | +0.007 |
temptation | +0.007 |
risk | +0.007 |
mons | +0.007 |
Neg logit contributions | |
spac | -0.005 |
aky | -0.005 |
v | -0.005 |
wrapped | -0.005 |
polar | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
temptation | +0.006 |
risk | +0.006 |
anish | +0.006 |
consequences | +0.006 |
wered | +0.006 |
Neg logit contributions | |
v | -0.004 |
spac | -0.004 |
aky | -0.004 |
wrapped | -0.004 |
ang | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
v | +0.005 |
spac | +0.005 |
aky | +0.005 |
ev | +0.005 |
ang | +0.005 |
Neg logit contributions | |
temptation | -0.005 |
risk | -0.005 |
lot | -0.005 |
anish | -0.005 |
consequences | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.008 |
aky | +0.008 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.006 |
lot | -0.006 |
anish | -0.006 |
consequences | -0.006 |
Token | walk |
Token ID | 2513 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
v | +0.013 |
spac | +0.012 |
aky | +0.012 |
ang | +0.012 |
ev | +0.012 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.006 |
lot | -0.006 |
anish | -0.005 |
consequences | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
ev | +0.006 |
ang | +0.006 |
Neg logit contributions | |
temptation | -0.007 |
risk | -0.006 |
lot | -0.006 |
anish | -0.006 |
consequences | -0.006 |
Token | cheer |
Token ID | 14042 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
v | +0.002 |
spac | +0.002 |
aky | +0.002 |
ev | +0.002 |
ang | +0.002 |
Neg logit contributions | |
temptation | -0.002 |
risk | -0.002 |
lot | -0.002 |
anish | -0.002 |
consequences | -0.002 |
Token | himself |
Token ID | 2241 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
v | +0.007 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
b | +0.006 |
Neg logit contributions | |
� | -0.010 |
temptation | -0.010 |
risk | -0.010 |
anish | -0.010 |
lot | -0.009 |
Token | up |
Token ID | 510 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
v | +0.017 |
spac | +0.016 |
aky | +0.016 |
ev | +0.015 |
ang | +0.015 |
Neg logit contributions | |
temptation | -0.015 |
risk | -0.014 |
lot | -0.014 |
anish | -0.014 |
consequences | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-04 |
Pos logit contributions | |
temptation | +0.002 |
risk | +0.002 |
lot | +0.002 |
anish | +0.002 |
consequences | +0.002 |
Neg logit contributions | |
v | -0.002 |
spac | -0.002 |
aky | -0.002 |
ev | -0.002 |
ang | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
v | +0.000 |
aky | +0.000 |
spac | +0.000 |
b | +0.000 |
ck | +0.000 |
Neg logit contributions | |
temptation | -0.000 |
lot | -0.000 |
� | -0.000 |
risk | -0.000 |
Tears | -0.000 |
Token | walked |
Token ID | 6807 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
lot | +0.002 |
pause | +0.002 |
temptation | +0.002 |
risk | +0.002 |
top | +0.002 |
Neg logit contributions | |
v | -0.003 |
spac | -0.003 |
aky | -0.003 |
eddy | -0.003 |
ang | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
v | +0.008 |
spac | +0.007 |
aky | +0.007 |
ev | +0.007 |
ang | +0.007 |
Neg logit contributions | |
temptation | -0.007 |
lot | -0.007 |
risk | -0.006 |
top | -0.006 |
anish | -0.006 |