TOP ACTIVATIONS
MAX = 0.077

. She used a m itt to take out the pan
. She loved her m ittens a lot .
started numbering all her m ittens . She found her lost
. Sue loved her m ittens very much . She wore
, sauce , cheese and topp ings . She showed them
to number all her m ittens so that she wouldn 't
of cheese and sauce and topp ings . The people who
She always forgot her m ittens and now that Daddy had
They were very pretty m ittens . She loved her m
She took off her m ittens and put them down on
she always numbered her m ittens and never lost them again
. They used their m ittens to make snow balls .
Sam . They had many bruises and cuts . They also
ostr ich pen . Ost ric hes are big birds with
. They were called ost ric hes . Lily and Ben
ostr ich pen . Ost ric hes are big birds with
ongo loved to eat av oc ados . One day ,
old and she loved m ittens . One day she was
All the children had m ittens to keep their hands warm
ie . Unlike other ost ric hes , his feathers gl

MIN ACTIVATIONS
MIN = -0.041

I did not see your trophy . Please tell me what
us , Lily ," the dancer says . " You are
" Follow me ," the sun flower says . He bends
fishing . <|endoftext|> On a bright and sunny day , Jimmy
forever . <|endoftext|> On a sunny day , a mom my
hair , Anna ?" the bar ber asked .
together . <|endoftext|> On a sunny day , Joe decided he
again . <|endoftext|> On a bright and sunny day , a
nic est jazz in the whole town . Her jazz was
happy ! <|endoftext|> On a sunny day , a little girl
worm who lived in his cozy home near a me adow
else to wear her favorite bl ouse . Sarah got angry
sur fer . Whenever the sur fer balanced on the board
a little mouse in her cozy little hole in the wall
, we do ," the dancer says . " It is
but she liked watching the sur fer . Whenever the sur
At the end of the day , they said
At the end of the day , Ad eline
best friends forever . <|endoftext|> On a sunny day , a
Tim and Mia ," the comet said . " I am

INTERVAL 0.047 - 0.077
CONTAINS 0.000%

to number all her m ittens so that she wouldn 't
started numbering all her m ittens . She found her lost
. She loved her m ittens a lot .
. Sue loved her m ittens very much . She wore
. She used a m itt to take out the pan

INTERVAL 0.018 - 0.047
CONTAINS 1.043%

went into the woods collecting berries and nuts . One day
time , a little girl named Lily went to camp with
saw Tim trying to climb out of his crib . "
loved to fly around all day . One day , Twe
excited that she spl ashed everywhere ! The water felt so

INTERVAL -0.012 - 0.018
CONTAINS 93.789%

" Yes , Ben , we are . But I am
his dad teaching him how to whistle . Tim my whist
Everyone was very proud of her and started to cl ap
Once there was a farmer and a horse . The farmer
Tom did not listen to Lily . He thought the chain

INTERVAL -0.041 - -0.012
CONTAINS 5.168%

. She loved to decor ate her room with pretty pictures
's go on the slide !" Ben says .
They loved to play together every day . One day ,
and ran out of the store , into the garden .
for a walk to cheer himself up . He walked around
Token.
Token ID13
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 ID1375
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 ID973
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 ID257
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 ID285
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
Tokenitt
Token ID715
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 ID284
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 ID1011
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 ID503
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 ID262
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 ID3425
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 ID13
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 ID1375
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 ID6151
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID257
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 ID1256
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 ID13
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 ID198
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 ID198
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 ID2067
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 ID47622
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 ID477
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID13
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 ID1375
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 ID1043
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 ID607
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 ID2626
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 ID13
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 ID26089
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 ID6151
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 ID607
Feature activation-4.05e-04

Feature not active on prev token;
no predictions were affected.
Token m
Token ID285
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
Tokenittens
Token ID34978
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 ID845
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 ID881
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 ID13
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 ID1375
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 ID12408
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 ID11
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 ID10746
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 ID11
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 ID9891
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 ID290
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 ID23126
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
Tokenings
Token ID654
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 ID13
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 ID1375
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 ID3751
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 ID606
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 ID284
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 ID1271
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 ID477
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID523
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 ID326
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 ID673
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 ID3636
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 ID470
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 ID286
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 ID9891
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 ID290
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 ID10746
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 ID290
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 ID23126
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
Tokenings
Token ID654
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 ID13
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 ID383
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 ID661
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 ID508
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 ID1375
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 ID1464
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 ID16453
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID290
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 ID783
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 ID326
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 ID26926
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 ID550
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 ID1119
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 ID547
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 ID845
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 ID2495
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 ID285
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
Tokenittens
Token ID34978
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 ID13
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 ID1375
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 ID6151
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 ID607
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 ID285
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 ID1375
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 ID1718
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 ID572
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID290
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 ID1234
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 ID606
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 ID866
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 ID319
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 ID673
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 ID1464
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 ID25840
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID290
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 ID1239
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 ID2626
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 ID606
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 ID757
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 ID13
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 ID1119
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 ID973
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 ID511
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 ID285
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
Tokenittens
Token ID34978
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 ID284
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 ID787
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 ID6729
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
Tokenballs
Token ID21591
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 ID13
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 ID3409
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 ID13
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 ID1119
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 ID550
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 ID867
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 ID42232
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 ID290
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 ID6630
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 ID13
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 ID1119
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 ID635
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 ID42387
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
Tokenich
Token ID488
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 ID3112
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 ID13
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 ID38919
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
Tokenric
Token ID1173
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
Tokenhes
Token ID956
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 ID389
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 ID1263
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 ID10087
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 ID351
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 ID13
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 ID1119
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 ID547
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 ID1444
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 ID23619
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
Tokenric
Token ID1173
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
Tokenhes
Token ID956
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 ID13
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 ID20037
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 ID290
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 ID3932
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 ID42387
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
Tokenich
Token ID488
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 ID3112
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 ID13
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 ID38919
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
Tokenric
Token ID1173
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
Tokenhes
Token ID956
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 ID389
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 ID1263
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 ID10087
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 ID351
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
Tokenongo
Token ID25162
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 ID6151
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 ID284
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 ID4483
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 ID1196
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
Tokenoc
Token ID420
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
Tokenados
Token ID22484
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 ID13
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 ID1881
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 ID1110
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 ID11
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 ID1468
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 ID290
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 ID673
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 ID6151
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 ID285
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
Tokenittens
Token ID34978
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 ID13
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 ID1881
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 ID1110
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 ID673
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 ID373
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 ID1439
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 ID262
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 ID1751
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 ID550
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 ID285
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
Tokenittens
Token ID34978
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 ID284
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 ID1394
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 ID511
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 ID2832
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 ID5814
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
Tokenie
Token ID494
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 ID13
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 ID12101
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 ID584
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 ID23619
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
Tokenric
Token ID1173
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
Tokenhes
Token ID956
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 ID11
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 ID465
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 ID27400
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 ID1278
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 ID314
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 ID750
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 ID407
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 ID766
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 ID534
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 ID16383
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 ID13
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 ID4222
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 ID1560
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 ID502
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 ID644
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 ID514
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 ID11
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 ID20037
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 ID553
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 ID262
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 ID38619
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 ID1139
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 ID13
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 ID366
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
TokenYou
Token ID1639
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 ID389
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 ID1
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
TokenFollow
Token ID7155
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 ID502
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 ID553
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 ID262
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 ID4252
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
Tokenflower
Token ID25547
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 ID1139
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 ID13
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 ID679
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 ID44370
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 ID12478
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 ID13
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID6016
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 ID290
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 ID27737
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 ID1110
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 ID11
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 ID12963
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 ID8097
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 ID13
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID27737
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 ID1110
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 ID11
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 ID257
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 ID1995
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
Tokenmy
Token ID1820
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 ID4190
Feature activation+6.38e-03

Feature not active on prev token;
no predictions were affected.
Token,
Token ID11
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 ID11735
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 ID1701
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 ID262
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 ID2318
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
Tokenber
Token ID527
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 ID1965
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 ID13
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 ID198
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 ID198
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 ID1978
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 ID13
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID27737
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 ID1110
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 ID11
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 ID5689
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 ID3066
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 ID339
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 ID757
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 ID13
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID6016
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 ID290
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 ID27737
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 ID1110
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 ID11
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 ID257
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 ID9200
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
Tokenest
Token ID395
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 ID21274
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 ID287
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 ID262
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 ID2187
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 ID3240
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 ID13
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 ID2332
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 ID21274
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 ID373
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 ID3772
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 ID0
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID27737
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 ID1110
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 ID11
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 ID257
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 ID1310
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 ID2576
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
Tokenworm
Token ID25323
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 ID508
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 ID5615
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 ID287
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 ID465
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 ID37438
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 ID1363
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 ID1474
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 ID257
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 ID502
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
Tokenadow
Token ID4584
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 ID2073
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 ID284
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 ID5806
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 ID607
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 ID4004
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 ID698
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
Tokenouse
Token ID1076
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 ID13
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 ID10490
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 ID1392
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 ID7954
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 ID969
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
Tokenfer
Token ID2232
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 ID13
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 ID21326
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 ID262
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 ID969
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
Tokenfer
Token ID2232
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 ID12974
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 ID319
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 ID262
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 ID3096
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 ID257
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 ID1310
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 ID10211
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 ID287
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 ID607
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 ID37438
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 ID1310
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 ID7604
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 ID287
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 ID262
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 ID3355
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 ID11
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 ID356
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 ID466
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 ID553
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 ID262
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 ID38619
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 ID1139
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 ID13
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 ID366
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
TokenIt
Token ID1026
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 ID318
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 ID475
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 ID673
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 ID8288
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 ID4964
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 ID262
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 ID969
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
Tokenfer
Token ID2232
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 ID13
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 ID21326
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 ID262
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 ID969
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 ID198
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 ID198
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
TokenAt
Token ID2953
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 ID262
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 ID886
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 ID286
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 ID262
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 ID1110
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 ID11
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 ID484
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 ID531
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 ID220
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 ID198
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
TokenAt
Token ID2953
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 ID262
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 ID886
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 ID286
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 ID262
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 ID1110
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 ID11
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 ID1215
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
Tokeneline
Token ID4470
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 ID1266
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 ID2460
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 ID8097
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 ID13
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 ID50256
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
TokenOn
Token ID2202
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 ID257
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 ID27737
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 ID1110
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 ID11
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 ID257
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 ID5045
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 ID290
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 ID32189
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 ID553
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 ID262
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 ID31733
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 ID531
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 ID13
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 ID366
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
TokenI
Token ID40
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 ID716
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 ID284
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 ID1271
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 ID477
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID523
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 ID326
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 ID673
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 ID3636
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 ID470
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 ID2067
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 ID47622
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 ID477
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID13
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 ID1375
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 ID1043
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 ID607
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 ID2626
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 ID13
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 ID1375
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 ID6151
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 ID607
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 ID285
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
Tokenittens
Token ID34978
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 ID257
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 ID1256
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 ID13
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 ID198
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 ID198
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 ID13
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 ID26089
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 ID6151
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 ID607
Feature activation-4.05e-04

Feature not active on prev token;
no predictions were affected.
Token m
Token ID285
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
Tokenittens
Token ID34978
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 ID845
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 ID881
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 ID13
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 ID1375
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 ID12408
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 ID13
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 ID1375
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 ID973
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 ID257
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 ID285
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
Tokenitt
Token ID715
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 ID284
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 ID1011
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 ID503
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 ID262
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 ID3425
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 ID1816
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 ID656
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 ID262
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 ID16479
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 ID13157
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 ID36322
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 ID290
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 ID14380
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 ID13
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 ID1881
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 ID1110
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 ID640
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 ID11
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 ID257
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 ID1310
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 ID2576
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 ID3706
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 ID20037
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 ID1816
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 ID284
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 ID1413
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 ID351
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 ID2497
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 ID5045
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 ID2111
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 ID284
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 ID12080
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 ID503
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 ID286
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 ID465
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 ID48083
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 ID13
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 ID366
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 ID6151
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 ID284
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 ID6129
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 ID1088
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 ID477
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 ID1110
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 ID13
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 ID1881
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 ID1110
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 ID11
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 ID24205
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 ID6568
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 ID326
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 ID673
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 ID4328
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
Tokenashed
Token ID5263
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 ID8347
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 ID0
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 ID383
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 ID1660
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 ID2936
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 ID523
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 ID1
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
TokenYes
Token ID5297
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 ID11
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 ID3932
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 ID11
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 ID356
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 ID389
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 ID13
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 ID887
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 ID314
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 ID716
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 ID465
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 ID9955
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 ID7743
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 ID683
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 ID703
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 ID284
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 ID16121
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 ID13
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 ID5045
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
Tokenmy
Token ID1820
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 ID32262
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 ID11075
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 ID373
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 ID845
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 ID6613
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 ID286
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 ID607
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 ID290
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 ID2067
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 ID284
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 ID537
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
Tokenap
Token ID499
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
TokenOnce
Token ID7454
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 ID612
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 ID373
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 ID257
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 ID18739
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 ID290
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 ID257
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 ID8223
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 ID13
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 ID383
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 ID18739
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 ID4186
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 ID750
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 ID407
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 ID6004
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 ID284
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 ID20037
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 ID13
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 ID679
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 ID1807
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 ID262
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 ID6333
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 ID13
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 ID1375
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 ID6151
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 ID284
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 ID11705
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
Tokenate
Token ID378
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 ID607
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 ID2119
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 ID351
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 ID2495
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 ID5986
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 ID338
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 ID467
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 ID319
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 ID262
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 ID10649
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 ID2474
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 ID3932
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 ID1139
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 ID13
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 ID198
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 ID198
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 ID1119
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 ID6151
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 ID284
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 ID711
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 ID1978
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 ID790
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 ID1110
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 ID13
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 ID1881
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 ID1110
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 ID11
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 ID290
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 ID4966
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 ID503
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 ID286
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 ID262
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 ID3650
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 ID11
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 ID656
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 ID262
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 ID11376
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 ID13
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 ID329
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 ID257
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 ID2513
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 ID284
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 ID14042
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 ID2241
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 ID510
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 ID13
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 ID679
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 ID6807
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 ID1088
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