TOP ACTIVATIONS
MAX = 0.094

a big box of ch ocol ates . It was so
away . " Ap olog ize to Anna right
as he opened the ch ocol ates and started eating them
was a box of ch ocol ates . Lily loved ch
, cup cakes and ch ocol ates .
was a box of ch ocol ates . " For me
and try again . <|endoftext|> Wal ter was feeling very sleepy
reward . It was ch ocol ates and sweets !
The King said , " Ap ology accepted . From now
ates . Lily loved ch ocol ates . She thanked Ben
a large selection of ch ocol ates . Ell a picked
find a box of ch ocol ates . "
he ate all the ch ocol ates and sweets . Then
and started eating the ch ocol ates . The shop keeper
a big box of ch ocol ates to share with the
a big box of ch ocol ates !
there was a huge hipp opot amus . He was feeling
make the waiter drop the pizz as . They said sorry
giving him too many ch ocol ates ." The king learned
Everyday he would take the av oc ados and scatter them

MIN ACTIVATIONS
MIN = -0.076

a triangle . It has three sides and three points .
's fork . It has three teeth and a pink handle
a triangle . It has three sides and three corners .
, who said that her toe was broken . Lily felt
It has three sides and three points . I can make
four cars and I have three . You can 't have
only three and like all three - year - olds ,
that has three sides and three corners . She says ,
them a block that has three sides and three corners .
" My car has three wheels . It is light
few days , that her three year old daughter 's stomach
was tough , like all three year olds . One day
� € � � Usually three eggs , but this time
It has three sides and three corners . Can you make
looks like the brick weighs three pounds ," Lucy said .
is a special tool with three points , like a star
marked it quite like the three year old . She marked
. It is more than three . It is like three
happy and it used all three wings to fly around the
had flown as far as three days of walking . Everyone

INTERVAL 0.052 - 0.094
CONTAINS 0.012%

what he did ! <|endoftext|> Mrs Jones had a big problem
They put the pizz as in the oven and
wanted them both to get uniforms that were very , very
paint !" her mom sc olded . But Lily didn 't
Together , they filled the boxes on the truck . Jake

INTERVAL 0.009 - 0.052
CONTAINS 22.688%

outside . They had many toys , but their favorite was
The cell was very grateful that Reg ret had come
. <|endoftext|> Once upon a time , there was a little
day . Billy had been waiting all week for his special
to raise their spirits and lend a helping hand . <|endoftext|>

INTERVAL -0.034 - 0.009
CONTAINS 76.861%

saw that she was hurt . " Oh no , Lily
you Sarah , don 't worry . Witches don 't belong
while he was playing his piano , he noticed something strange
on , let 's bake a cake ." L
and tried to splash the fish away . But the fish

INTERVAL -0.076 - -0.034
CONTAINS 0.438%

son . No matter how hot it is outside , if
and it made Rob by feel sad . But
the window and felt how cold it was . He gigg
a long drive . M abel was tired but she tried
in the arm chair , feeling so cozy and happy .
Token a
Token ID257
Feature activation+6.38e-03

Pos logit contributions
 minutes+0.020
pill+0.019
storms+0.019
 pic+0.019
 showers+0.017
Neg logit contributions
 captain-0.017
ole-0.016
hips-0.016
rave-0.015
ble-0.015
Token big
Token ID1263
Feature activation+9.08e-03

Pos logit contributions
hips+0.011
 captain+0.010
rave+0.010
ole+0.010
ble+0.010
Neg logit contributions
 minutes-0.009
 pic-0.008
pill-0.008
storms-0.008
 spilled-0.008
Token box
Token ID3091
Feature activation+3.68e-02

Pos logit contributions
hips+0.015
rave+0.015
 captain+0.015
ole+0.014
ble+0.014
Neg logit contributions
 minutes-0.013
 pic-0.012
 spilled-0.011
storms-0.011
pill-0.011
Token of
Token ID286
Feature activation+3.63e-03

Pos logit contributions
rave+0.068
 captain+0.067
roc+0.067
hips+0.065
ole+0.064
Neg logit contributions
 minutes-0.046
 spilled-0.039
storms-0.039
 pic-0.038
pill-0.036
Token ch
Token ID442
Feature activation-1.07e-02

Pos logit contributions
 captain+0.006
rave+0.006
ole+0.006
hips+0.006
ble+0.006
Neg logit contributions
 minutes-0.005
 pic-0.005
pill-0.005
 spilled-0.005
 showers-0.005
Tokenocol
Token ID4668
Feature activation+9.06e-02

Pos logit contributions
 minutes+0.018
pill+0.017
 pic+0.017
storms+0.016
 showers+0.016
Neg logit contributions
 captain-0.016
rave-0.015
hips-0.015
ole-0.014
ble-0.014
Tokenates
Token ID689
Feature activation+2.04e-02

Pos logit contributions
 captain+0.097
hips+0.088
ole+0.086
rave+0.084
ble+0.076
Neg logit contributions
 minutes-0.186
pill-0.178
 pic-0.176
storms-0.174
 showers-0.163
Token.
Token ID13
Feature activation+6.32e-04

Pos logit contributions
 captain+0.041
rave+0.040
hips+0.039
ole+0.038
roc+0.038
Neg logit contributions
 minutes-0.022
storms-0.020
pill-0.020
 pic-0.019
 spilled-0.019
Token It
Token ID632
Feature activation+4.77e-03

Pos logit contributions
 captain+0.001
ole+0.001
rave+0.001
hips+0.001
ble+0.001
Neg logit contributions
 minutes-0.001
 pic-0.001
storms-0.001
pill-0.001
 spilled-0.001
Token was
Token ID373
Feature activation-1.23e-02

Pos logit contributions
 captain+0.009
ole+0.009
rave+0.009
hips+0.009
ble+0.008
Neg logit contributions
 minutes-0.006
 pic-0.005
pill-0.005
storms-0.005
 showers-0.005
Token so
Token ID523
Feature activation-1.50e-02

Pos logit contributions
 minutes+0.018
 pic+0.016
pill+0.016
storms+0.015
 spilled+0.015
Neg logit contributions
 captain-0.020
hips-0.020
rave-0.020
ole-0.020
ble-0.019
Token away
Token ID1497
Feature activation+1.73e-02

Pos logit contributions
 minutes+0.017
 pic+0.015
storms+0.015
pill+0.015
 spilled+0.014
Neg logit contributions
 captain-0.024
rave-0.023
hips-0.023
ole-0.022
ble-0.021
Token.
Token ID13
Feature activation-9.59e-04

Pos logit contributions
 captain+0.036
hips+0.035
rave+0.035
ole+0.034
roc+0.033
Neg logit contributions
 minutes-0.018
storms-0.015
 pic-0.015
pill-0.014
 spilled-0.014
Token
Token ID198
Feature activation-9.15e-03

Pos logit contributions
 minutes+0.002
pill+0.002
 pic+0.002
storms+0.002
zed+0.002
Neg logit contributions
 captain-0.001
hips-0.001
rave-0.001
 sir-0.001
 himself-0.001
Token
Token ID198
Feature activation-2.89e-03

Pos logit contributions
 minutes+0.012
storms+0.011
pill+0.011
 pic+0.010
 showers+0.010
Neg logit contributions
hips-0.016
 captain-0.016
rave-0.016
ole-0.015
ble-0.015
Token"
Token ID1
Feature activation-1.64e-03

Pos logit contributions
 minutes+0.005
pill+0.004
 pic+0.004
storms+0.004
 showers+0.004
Neg logit contributions
 captain-0.005
ole-0.004
hips-0.004
rave-0.004
ble-0.004
TokenAp
Token ID25189
Feature activation+8.80e-02

Pos logit contributions
 minutes+0.002
pill+0.002
storms+0.002
 pic+0.002
 showers+0.002
Neg logit contributions
 captain-0.003
hips-0.003
ole-0.003
rave-0.003
ble-0.003
Tokenolog
Token ID928
Feature activation+4.74e-02

Pos logit contributions
 captain+0.133
ble+0.128
 luck+0.123
 compass+0.123
ole+0.122
Neg logit contributions
 knocks-0.115
storms-0.107
zed-0.104
â„¢-0.103
 minutes-0.101
Tokenize
Token ID1096
Feature activation+1.82e-02

Pos logit contributions
 captain+0.084
 compass+0.074
hips+0.074
 spear+0.072
 luck+0.072
Neg logit contributions
 minutes-0.062
zed-0.059
 pic-0.054
 knocks-0.052
storms-0.052
Token to
Token ID284
Feature activation+5.06e-03

Pos logit contributions
hips+0.034
 captain+0.032
rave+0.031
ble+0.030
ole+0.029
Neg logit contributions
 minutes-0.022
 showers-0.019
storms-0.018
zed-0.018
 pic-0.018
Token Anna
Token ID11735
Feature activation+3.38e-03

Pos logit contributions
 captain+0.009
ole+0.008
hips+0.008
rave+0.008
ble+0.008
Neg logit contributions
 minutes-0.007
pill-0.007
storms-0.007
 pic-0.006
 spilled-0.006
Token right
Token ID826
Feature activation+1.44e-02

Pos logit contributions
hips+0.006
 captain+0.006
rave+0.006
ole+0.006
ble+0.006
Neg logit contributions
 minutes-0.004
storms-0.003
 pic-0.003
 spilled-0.003
pill-0.003
Token as
Token ID355
Feature activation+2.18e-02

Pos logit contributions
 captain+0.023
hips+0.022
ole+0.022
rave+0.021
ble+0.020
Neg logit contributions
 minutes-0.019
pill-0.019
 pic-0.018
storms-0.018
 showers-0.017
Token he
Token ID339
Feature activation-7.53e-03

Pos logit contributions
 captain+0.036
ole+0.035
hips+0.035
rave+0.034
ble+0.032
Neg logit contributions
 minutes-0.031
 pic-0.029
pill-0.029
storms-0.029
 showers-0.027
Token opened
Token ID4721
Feature activation+1.09e-02

Pos logit contributions
 minutes+0.011
pill+0.010
 showers+0.010
storms+0.010
 pic+0.010
Neg logit contributions
 captain-0.013
rave-0.011
hips-0.011
ole-0.011
cher-0.011
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
 captain+0.016
hips+0.015
ole+0.015
rave+0.015
ble+0.014
Neg logit contributions
 minutes-0.018
 pic-0.017
storms-0.016
pill-0.016
 showers-0.015
Token ch
Token ID442
Feature activation-6.13e-03

Pos logit contributions
 captain+0.018
hips+0.017
ole+0.017
rave+0.017
ble+0.016
Neg logit contributions
 minutes-0.023
 pic-0.022
pill-0.021
storms-0.021
 showers-0.020
Tokenocol
Token ID4668
Feature activation+8.79e-02

Pos logit contributions
 minutes+0.011
 pic+0.011
storms+0.011
pill+0.011
 showers+0.010
Neg logit contributions
 captain-0.008
ole-0.007
hips-0.007
rave-0.007
ble-0.007
Tokenates
Token ID689
Feature activation+2.34e-02

Pos logit contributions
 captain+0.085
hips+0.078
ole+0.077
rave+0.075
ble+0.068
Neg logit contributions
 minutes-0.188
pill-0.180
 pic-0.178
storms-0.177
 showers-0.168
Token and
Token ID290
Feature activation+7.51e-04

Pos logit contributions
 captain+0.042
rave+0.040
hips+0.040
ole+0.040
roc+0.037
Neg logit contributions
 minutes-0.030
storms-0.028
 pic-0.028
pill-0.027
 spilled-0.025
Token started
Token ID2067
Feature activation-2.72e-02

Pos logit contributions
 captain+0.001
hips+0.001
ole+0.001
rave+0.001
ble+0.001
Neg logit contributions
 minutes-0.001
pill-0.001
storms-0.001
 pic-0.001
 showers-0.001
Token eating
Token ID6600
Feature activation-2.96e-02

Pos logit contributions
 minutes+0.044
pill+0.042
storms+0.041
 pic+0.040
 showers+0.037
Neg logit contributions
 captain-0.041
rave-0.038
ole-0.037
hips-0.036
ble-0.035
Token them
Token ID606
Feature activation-4.01e-03

Pos logit contributions
 minutes+0.047
pill+0.045
storms+0.045
 pic+0.043
 showers+0.041
Neg logit contributions
 captain-0.044
ole-0.043
hips-0.042
rave-0.041
ble-0.039
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.006
rave+0.006
ble+0.005
Neg logit contributions
 minutes-0.003
pill-0.003
 pic-0.003
storms-0.003
 showers-0.002
Token a
Token ID257
Feature activation+1.03e-02

Pos logit contributions
 minutes+0.022
 pic+0.019
 spilled+0.018
 time+0.016
 knocks+0.016
Neg logit contributions
rave-0.026
ole-0.025
 captain-0.025
roc-0.025
hips-0.025
Token box
Token ID3091
Feature activation+3.84e-02

Pos logit contributions
rave+0.015
hips+0.015
 captain+0.015
ole+0.015
ble+0.014
Neg logit contributions
 minutes-0.016
 pic-0.015
 spilled-0.014
pill-0.014
storms-0.014
Token of
Token ID286
Feature activation+5.19e-03

Pos logit contributions
rave+0.066
 captain+0.065
roc+0.064
ole+0.063
hips+0.062
Neg logit contributions
 minutes-0.052
storms-0.046
 pic-0.045
 spilled-0.043
pill-0.043
Token ch
Token ID442
Feature activation-1.25e-02

Pos logit contributions
rave+0.009
ole+0.009
 captain+0.009
hips+0.009
ble+0.009
Neg logit contributions
 minutes-0.007
 pic-0.007
pill-0.006
 spilled-0.006
 showers-0.006
Tokenocol
Token ID4668
Feature activation+8.73e-02

Pos logit contributions
 minutes+0.022
pill+0.021
 pic+0.020
storms+0.020
 showers+0.019
Neg logit contributions
 captain-0.018
rave-0.016
hips-0.016
ole-0.016
ble-0.015
Tokenates
Token ID689
Feature activation+1.86e-02

Pos logit contributions
 captain+0.100
hips+0.090
ole+0.087
rave+0.085
ble+0.078
Neg logit contributions
 minutes-0.174
pill-0.167
 pic-0.163
storms-0.160
 spilled-0.149
Token.
Token ID13
Feature activation+4.45e-03

Pos logit contributions
 captain+0.035
rave+0.034
hips+0.034
ole+0.033
roc+0.032
Neg logit contributions
 minutes-0.022
storms-0.020
 pic-0.020
pill-0.020
 spilled-0.019
Token Lily
Token ID20037
Feature activation-1.17e-02

Pos logit contributions
 captain+0.006
ole+0.005
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.008
storms-0.008
pill-0.008
 pic-0.008
 spilled-0.008
Token loved
Token ID6151
Feature activation-1.41e-02

Pos logit contributions
 minutes+0.016
storms+0.016
 showers+0.015
pill+0.015
 pic+0.015
Neg logit contributions
 captain-0.020
rave-0.018
hips-0.017
ole-0.017
bles-0.017
Token ch
Token ID442
Feature activation-9.40e-03

Pos logit contributions
 minutes+0.025
storms+0.024
pill+0.023
zed+0.022
 spilled+0.022
Neg logit contributions
 captain-0.019
rave-0.016
ole-0.016
hips-0.016
 himself-0.015
Token,
Token ID11
Feature activation+5.42e-05

Pos logit contributions
 captain+0.044
hips+0.042
ole+0.042
rave+0.042
ble+0.039
Neg logit contributions
 minutes-0.033
pill-0.031
 pic-0.031
storms-0.031
 showers-0.028
Token cup
Token ID6508
Feature activation-1.25e-02

Pos logit contributions
 captain+0.000
ole+0.000
hips+0.000
rave+0.000
ble+0.000
Neg logit contributions
 minutes-0.000
storms-0.000
pill-0.000
 pic-0.000
 showers-0.000
Tokencakes
Token ID37263
Feature activation+4.21e-03

Pos logit contributions
 minutes+0.019
 pic+0.018
pill+0.018
storms+0.017
 showers+0.016
Neg logit contributions
 captain-0.020
ole-0.019
hips-0.019
rave-0.018
ble-0.018
Token and
Token ID290
Feature activation-9.09e-03

Pos logit contributions
ole+0.005
 captain+0.005
hips+0.005
rave+0.005
nut+0.004
Neg logit contributions
 minutes-0.008
pill-0.007
storms-0.007
 pic-0.007
 showers-0.007
Token ch
Token ID442
Feature activation-1.74e-02

Pos logit contributions
 minutes+0.013
storms+0.013
pill+0.012
 pic+0.012
 showers+0.011
Neg logit contributions
 captain-0.015
ole-0.014
hips-0.013
rave-0.013
ble-0.012
Tokenocol
Token ID4668
Feature activation+8.14e-02

Pos logit contributions
 minutes+0.034
storms+0.033
 pic+0.033
pill+0.032
 showers+0.030
Neg logit contributions
ole-0.020
 captain-0.019
hips-0.019
rave-0.018
bles-0.017
Tokenates
Token ID689
Feature activation+3.99e-03

Pos logit contributions
 captain+0.089
hips+0.080
ole+0.077
rave+0.075
ble+0.069
Neg logit contributions
 minutes-0.166
pill-0.160
 pic-0.158
storms-0.156
 showers-0.146
Token.
Token ID13
Feature activation-2.04e-03

Pos logit contributions
 captain+0.007
rave+0.007
hips+0.007
ole+0.007
roc+0.007
Neg logit contributions
 minutes-0.005
storms-0.004
pill-0.004
 pic-0.004
 spilled-0.004
Token
Token ID220
Feature activation+1.43e-02

Pos logit contributions
 minutes+0.003
storms+0.003
pill+0.003
 pic+0.003
 spilled+0.003
Neg logit contributions
 captain-0.003
ole-0.003
hips-0.003
rave-0.003
 Elliot-0.003
Token
Token ID198
Feature activation-9.49e-03

Pos logit contributions
ole+0.028
hips+0.028
 captain+0.028
rave+0.028
ble+0.027
Neg logit contributions
 minutes-0.017
 pic-0.015
storms-0.014
pill-0.014
 showers-0.013
Token
Token ID198
Feature activation-3.59e-03

Pos logit contributions
 minutes+0.010
storms+0.009
pill+0.009
 pic+0.009
 showers+0.008
Neg logit contributions
 captain-0.020
ole-0.020
hips-0.019
rave-0.019
ble-0.018
Token was
Token ID373
Feature activation-7.90e-03

Pos logit contributions
 captain+0.018
ole+0.017
hips+0.017
rave+0.016
ble+0.016
Neg logit contributions
 minutes-0.015
 pic-0.014
pill-0.014
storms-0.014
 showers-0.013
Token a
Token ID257
Feature activation+5.13e-03

Pos logit contributions
 minutes+0.013
pill+0.013
storms+0.012
 pic+0.012
 showers+0.012
Neg logit contributions
 captain-0.011
hips-0.011
ole-0.011
rave-0.010
ble-0.010
Token box
Token ID3091
Feature activation+3.64e-02

Pos logit contributions
 captain+0.008
hips+0.008
ole+0.008
rave+0.008
ble+0.008
Neg logit contributions
 minutes-0.007
 pic-0.007
pill-0.007
storms-0.007
 showers-0.006
Token of
Token ID286
Feature activation+4.55e-03

Pos logit contributions
rave+0.064
 captain+0.064
roc+0.063
ole+0.061
hips+0.061
Neg logit contributions
 minutes-0.047
storms-0.041
 spilled-0.040
 pic-0.040
pill-0.039
Token ch
Token ID442
Feature activation-1.46e-02

Pos logit contributions
 captain+0.008
ole+0.008
hips+0.008
rave+0.008
ble+0.007
Neg logit contributions
 minutes-0.006
 pic-0.006
pill-0.006
 showers-0.005
 spilled-0.005
Tokenocol
Token ID4668
Feature activation+8.11e-02

Pos logit contributions
 minutes+0.027
 pic+0.025
pill+0.025
storms+0.025
 showers+0.024
Neg logit contributions
 captain-0.019
ole-0.018
hips-0.018
rave-0.017
ble-0.016
Tokenates
Token ID689
Feature activation+1.89e-02

Pos logit contributions
 captain+0.084
hips+0.077
ole+0.077
rave+0.075
ble+0.069
Neg logit contributions
 minutes-0.168
pill-0.161
 pic-0.160
storms-0.159
 showers-0.151
Token.
Token ID13
Feature activation-3.89e-03

Pos logit contributions
 captain+0.034
rave+0.033
hips+0.033
ole+0.032
roc+0.031
Neg logit contributions
 minutes-0.024
storms-0.022
pill-0.022
 pic-0.022
 spilled-0.021
Token "
Token ID366
Feature activation-9.05e-03

Pos logit contributions
 minutes+0.006
 pic+0.005
storms+0.005
 spilled+0.005
pill+0.005
Neg logit contributions
 captain-0.006
ole-0.006
rave-0.006
hips-0.006
 Elliot-0.005
TokenFor
Token ID1890
Feature activation-1.48e-02

Pos logit contributions
 minutes+0.013
storms+0.012
 pic+0.012
pill+0.011
 showers+0.011
Neg logit contributions
 captain-0.015
ole-0.015
rave-0.015
hips-0.014
ble-0.013
Token me
Token ID502
Feature activation-1.78e-02

Pos logit contributions
storms+0.028
pill+0.028
 minutes+0.027
 pic+0.025
 spilled+0.025
Neg logit contributions
 captain-0.019
hips-0.017
rave-0.016
ole-0.016
 ourselves-0.015
Token and
Token ID290
Feature activation-1.78e-02

Pos logit contributions
 captain+0.007
ole+0.006
hips+0.006
rave+0.006
ble+0.006
Neg logit contributions
 minutes-0.007
pill-0.007
storms-0.007
 pic-0.007
 showers-0.007
Token try
Token ID1949
Feature activation-9.63e-03

Pos logit contributions
 minutes+0.033
pill+0.032
storms+0.031
 pic+0.031
 showers+0.029
Neg logit contributions
 captain-0.022
hips-0.021
ole-0.020
rave-0.020
ble-0.019
Token again
Token ID757
Feature activation-1.42e-02

Pos logit contributions
 minutes+0.015
pill+0.014
storms+0.014
 pic+0.014
 showers+0.013
Neg logit contributions
 captain-0.015
hips-0.014
ole-0.014
rave-0.014
ble-0.013
Token.
Token ID13
Feature activation-3.68e-03

Pos logit contributions
pill+0.023
storms+0.022
 minutes+0.022
 pic+0.022
 showers+0.021
Neg logit contributions
 captain-0.020
ole-0.019
ble-0.018
rave-0.018
 ourselves-0.018
Token<|endoftext|>
Token ID50256
Feature activation-1.31e-02

Pos logit contributions
 minutes+0.005
 spilled+0.005
storms+0.005
 pic+0.004
 showers+0.004
Neg logit contributions
rave-0.006
ole-0.006
 captain-0.006
hips-0.006
 ourselves-0.006
TokenWal
Token ID21902
Feature activation+8.02e-02

Pos logit contributions
 minutes+0.018
storms+0.016
 showers+0.016
 pic+0.016
pill+0.016
Neg logit contributions
ole-0.021
rave-0.021
 captain-0.020
hips-0.020
ble-0.020
Tokenter
Token ID353
Feature activation+1.50e-02

Pos logit contributions
hips+0.126
 captain+0.115
 mercy+0.108
rave+0.107
ole+0.106
Neg logit contributions
pill-0.123
 minutes-0.118
storms-0.111
 pic-0.110
 spilled-0.103
Token was
Token ID373
Feature activation+4.27e-04

Pos logit contributions
 captain+0.025
ole+0.023
rave+0.022
ble+0.021
hips+0.021
Neg logit contributions
 minutes-0.023
pill-0.021
storms-0.020
 pic-0.020
 showers-0.020
Token feeling
Token ID4203
Feature activation-2.96e-02

Pos logit contributions
 captain+0.001
ole+0.001
rave+0.001
ble+0.001
hips+0.001
Neg logit contributions
pill-0.001
 minutes-0.001
storms-0.001
 pic-0.001
 showers-0.001
Token very
Token ID845
Feature activation-1.88e-02

Pos logit contributions
 minutes+0.049
 pic+0.049
storms+0.049
pill+0.048
 knocks+0.041
Neg logit contributions
 captain-0.042
ole-0.039
ble-0.037
hips-0.037
rave-0.037
Token sleepy
Token ID42023
Feature activation-4.98e-03

Pos logit contributions
pill+0.033
storms+0.033
 minutes+0.032
 pic+0.031
 spilled+0.027
Neg logit contributions
 captain-0.026
ole-0.024
ble-0.024
rave-0.022
hips-0.022
Token reward
Token ID6721
Feature activation+2.56e-02

Pos logit contributions
 captain+0.004
ole+0.003
hips+0.003
rave+0.003
ble+0.003
Neg logit contributions
 minutes-0.004
pill-0.004
 pic-0.004
storms-0.004
 showers-0.003
Token.
Token ID13
Feature activation-3.46e-03

Pos logit contributions
 captain+0.039
ole+0.037
hips+0.037
rave+0.036
ble+0.035
Neg logit contributions
 minutes-0.040
pill-0.038
 pic-0.038
storms-0.037
 showers-0.035
Token It
Token ID632
Feature activation+1.03e-03

Pos logit contributions
 minutes+0.005
 pic+0.004
storms+0.004
pill+0.004
 spilled+0.004
Neg logit contributions
 captain-0.006
ole-0.006
hips-0.006
rave-0.006
ble-0.005
Token was
Token ID373
Feature activation-1.21e-02

Pos logit contributions
 captain+0.002
rave+0.002
hips+0.002
ole+0.002
ble+0.002
Neg logit contributions
 minutes-0.001
 pic-0.001
storms-0.001
 showers-0.001
pill-0.001
Token ch
Token ID442
Feature activation-1.21e-02

Pos logit contributions
 minutes+0.019
pill+0.018
storms+0.018
 pic+0.018
 showers+0.017
Neg logit contributions
 captain-0.018
ole-0.017
hips-0.017
rave-0.017
ble-0.016
Tokenocol
Token ID4668
Feature activation+7.97e-02

Pos logit contributions
 minutes+0.023
pill+0.022
storms+0.021
 pic+0.021
 showers+0.020
Neg logit contributions
 captain-0.015
hips-0.014
ole-0.014
rave-0.014
ble-0.013
Tokenates
Token ID689
Feature activation+1.62e-02

Pos logit contributions
 captain+0.088
hips+0.081
ole+0.077
rave+0.075
ble+0.067
Neg logit contributions
 minutes-0.161
pill-0.156
 pic-0.151
storms-0.150
 showers-0.139
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
 captain+0.026
hips+0.025
rave+0.025
ole+0.025
ble+0.023
Neg logit contributions
 minutes-0.024
pill-0.023
storms-0.023
 pic-0.022
 spilled-0.020
Token sweets
Token ID42402
Feature activation+1.43e-03

Pos logit contributions
 minutes+0.031
pill+0.029
storms+0.029
 pic+0.028
 showers+0.027
Neg logit contributions
 captain-0.033
hips-0.031
ole-0.030
rave-0.030
ble-0.029
Token!
Token ID0
Feature activation-2.93e-03

Pos logit contributions
 captain+0.002
ole+0.002
hips+0.002
rave+0.002
ble+0.002
Neg logit contributions
 minutes-0.002
pill-0.002
 pic-0.002
storms-0.002
 showers-0.002
Token
Token ID198
Feature activation-1.11e-02

Pos logit contributions
 minutes+0.004
 pic+0.004
storms+0.004
pill+0.004
 spilled+0.004
Neg logit contributions
 captain-0.005
ole-0.005
hips-0.005
rave-0.005
ble-0.004
TokenThe
Token ID464
Feature activation+8.96e-04

Pos logit contributions
 captain+0.013
hips+0.012
ole+0.012
rave+0.012
ble+0.011
Neg logit contributions
 minutes-0.012
pill-0.011
 pic-0.011
storms-0.011
 showers-0.010
Token King
Token ID2677
Feature activation+6.43e-03

Pos logit contributions
hips+0.001
rave+0.001
ole+0.001
 captain+0.001
ble+0.001
Neg logit contributions
 minutes-0.002
pill-0.002
 pic-0.001
storms-0.001
 showers-0.001
Token said
Token ID531
Feature activation-5.07e-03

Pos logit contributions
hips+0.012
 captain+0.012
rave+0.011
ole+0.011
ble+0.011
Neg logit contributions
 minutes-0.008
pill-0.007
storms-0.007
 pic-0.007
 spilled-0.007
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
 minutes+0.007
storms+0.007
 showers+0.006
pill+0.006
 pic+0.006
Neg logit contributions
 captain-0.008
hips-0.008
rave-0.008
ole-0.008
ble-0.007
Token "
Token ID366
Feature activation-1.74e-02

Pos logit contributions
 minutes+0.017
 pic+0.017
pill+0.017
storms+0.016
 showers+0.015
Neg logit contributions
 captain-0.019
rave-0.018
ole-0.017
hips-0.017
ble-0.017
TokenAp
Token ID25189
Feature activation+7.92e-02

Pos logit contributions
 minutes+0.026
 pic+0.025
storms+0.024
pill+0.023
 showers+0.023
Neg logit contributions
 captain-0.029
rave-0.027
ole-0.027
hips-0.026
ble-0.026
Tokenology
Token ID1435
Feature activation+4.39e-02

Pos logit contributions
ble+0.116
 captain+0.114
 attention+0.107
 compass+0.106
 luck+0.105
Neg logit contributions
storms-0.098
zed-0.096
 knocks-0.093
â„¢-0.092
pill-0.090
Token accepted
Token ID6292
Feature activation+1.64e-02

Pos logit contributions
ble+0.069
hips+0.066
ole+0.064
 captain+0.063
roc+0.062
Neg logit contributions
 minutes-0.059
zed-0.055
 happens-0.052
 woke-0.050
 reached-0.047
Token.
Token ID13
Feature activation-8.31e-03

Pos logit contributions
 captain+0.029
hips+0.028
rave+0.027
ole+0.027
ble+0.026
Neg logit contributions
 minutes-0.022
 pic-0.020
storms-0.020
pill-0.019
 showers-0.019
Token From
Token ID3574
Feature activation+8.72e-03

Pos logit contributions
 minutes+0.011
pill+0.010
 pic+0.010
storms+0.010
 showers+0.009
Neg logit contributions
 captain-0.015
ole-0.014
hips-0.014
rave-0.014
ble-0.014
Token now
Token ID783
Feature activation+1.25e-02

Pos logit contributions
 captain+0.016
hips+0.015
ole+0.015
rave+0.015
ble+0.014
Neg logit contributions
 minutes-0.011
 pic-0.010
storms-0.010
pill-0.009
 showers-0.009
Tokenates
Token ID689
Feature activation+1.86e-02

Pos logit contributions
 captain+0.100
hips+0.090
ole+0.087
rave+0.085
ble+0.078
Neg logit contributions
 minutes-0.174
pill-0.167
 pic-0.163
storms-0.160
 spilled-0.149
Token.
Token ID13
Feature activation+4.45e-03

Pos logit contributions
 captain+0.035
rave+0.034
hips+0.034
ole+0.033
roc+0.032
Neg logit contributions
 minutes-0.022
storms-0.020
 pic-0.020
pill-0.020
 spilled-0.019
Token Lily
Token ID20037
Feature activation-1.17e-02

Pos logit contributions
 captain+0.006
ole+0.005
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.008
storms-0.008
pill-0.008
 pic-0.008
 spilled-0.008
Token loved
Token ID6151
Feature activation-1.41e-02

Pos logit contributions
 minutes+0.016
storms+0.016
 showers+0.015
pill+0.015
 pic+0.015
Neg logit contributions
 captain-0.020
rave-0.018
hips-0.017
ole-0.017
bles-0.017
Token ch
Token ID442
Feature activation-9.40e-03

Pos logit contributions
 minutes+0.025
storms+0.024
pill+0.023
zed+0.022
 spilled+0.022
Neg logit contributions
 captain-0.019
rave-0.016
ole-0.016
hips-0.016
 himself-0.015
Tokenocol
Token ID4668
Feature activation+7.89e-02

Pos logit contributions
 minutes+0.018
 pic+0.017
pill+0.017
storms+0.017
 showers+0.016
Neg logit contributions
 captain-0.012
ole-0.011
hips-0.011
rave-0.011
ble-0.010
Tokenates
Token ID689
Feature activation+2.45e-02

Pos logit contributions
 captain+0.090
hips+0.081
ole+0.078
rave+0.076
ble+0.069
Neg logit contributions
 minutes-0.156
pill-0.152
 pic-0.147
storms-0.146
 showers-0.135
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
rave+0.053
 captain+0.053
hips+0.051
roc+0.050
ole+0.050
Neg logit contributions
 minutes-0.021
pill-0.020
storms-0.020
 pic-0.019
 spilled-0.018
Token She
Token ID1375
Feature activation+9.98e-03

Pos logit contributions
 captain+0.018
hips+0.017
rave+0.017
ole+0.016
ble+0.016
Neg logit contributions
 minutes-0.023
zed-0.020
 pic-0.019
 spilled-0.019
storms-0.019
Token thanked
Token ID26280
Feature activation+2.34e-02

Pos logit contributions
 captain+0.017
rave+0.014
bles+0.013
ole+0.013
hips+0.013
Neg logit contributions
storms-0.015
 minutes-0.014
 showers-0.014
pill-0.014
 pic-0.013
Token Ben
Token ID3932
Feature activation+1.77e-02

Pos logit contributions
 captain+0.041
hips+0.040
ole+0.040
rave+0.039
ble+0.037
Neg logit contributions
 minutes-0.031
 pic-0.030
pill-0.029
storms-0.029
 showers-0.027
Token a
Token ID257
Feature activation-8.57e-03

Pos logit contributions
 minutes+0.000
storms+0.000
pill+0.000
 pic+0.000
 showers+0.000
Neg logit contributions
 captain-0.000
hips-0.000
ole-0.000
rave-0.000
ble-0.000
Token large
Token ID1588
Feature activation-8.54e-03

Pos logit contributions
 minutes+0.011
 pic+0.011
 spilled+0.010
pill+0.010
 showers+0.010
Neg logit contributions
 captain-0.015
hips-0.015
rave-0.015
ole-0.014
ble-0.014
Token selection
Token ID6356
Feature activation+1.84e-02

Pos logit contributions
 minutes+0.012
 pic+0.011
 spilled+0.011
 showers+0.010
pill+0.010
Neg logit contributions
hips-0.014
 captain-0.014
rave-0.014
ole-0.013
ble-0.013
Token of
Token ID286
Feature activation-1.67e-02

Pos logit contributions
 captain+0.033
rave+0.031
hips+0.031
ole+0.030
ble+0.029
Neg logit contributions
 minutes-0.025
pill-0.023
 pic-0.022
storms-0.022
 spilled-0.021
Token ch
Token ID442
Feature activation-2.69e-02

Pos logit contributions
 minutes+0.026
 pic+0.025
pill+0.025
 showers+0.023
storms+0.023
Neg logit contributions
 captain-0.026
hips-0.025
ole-0.025
ble-0.024
rave-0.024
Tokenocol
Token ID4668
Feature activation+7.75e-02

Pos logit contributions
 minutes+0.052
storms+0.051
 pic+0.051
pill+0.049
 showers+0.047
Neg logit contributions
 captain-0.030
ole-0.030
hips-0.029
rave-0.028
ble-0.026
Tokenates
Token ID689
Feature activation+9.95e-03

Pos logit contributions
 captain+0.081
hips+0.073
ole+0.071
rave+0.069
ble+0.064
Neg logit contributions
 minutes-0.161
pill-0.156
 pic-0.153
storms-0.151
 showers-0.143
Token.
Token ID13
Feature activation-5.56e-03

Pos logit contributions
 captain+0.019
hips+0.018
rave+0.018
ole+0.018
ble+0.017
Neg logit contributions
 minutes-0.012
pill-0.011
storms-0.011
 pic-0.011
 showers-0.010
Token Ell
Token ID7122
Feature activation+7.65e-03

Pos logit contributions
 minutes+0.009
storms+0.008
 happens+0.008
pill+0.008
zed+0.008
Neg logit contributions
ole-0.007
rave-0.007
hips-0.007
 captain-0.007
 Elliot-0.007
Tokena
Token ID64
Feature activation-2.21e-02

Pos logit contributions
 captain+0.010
ole+0.009
hips+0.009
rave+0.009
ble+0.008
Neg logit contributions
 minutes-0.014
pill-0.014
 pic-0.014
storms-0.013
 showers-0.013
Token picked
Token ID6497
Feature activation+1.22e-02

Pos logit contributions
storms+0.031
 minutes+0.031
 showers+0.030
 pic+0.030
pill+0.030
Neg logit contributions
 captain-0.036
rave-0.034
ole-0.033
eka-0.030
bles-0.030
Token find
Token ID1064
Feature activation-5.33e-03

Pos logit contributions
ole+0.008
rave+0.007
 captain+0.007
ble+0.007
roc+0.006
Neg logit contributions
 minutes-0.006
 spilled-0.006
 knocks-0.006
 pic-0.006
 cou-0.005
Token a
Token ID257
Feature activation-2.35e-03

Pos logit contributions
 minutes+0.008
pill+0.008
storms+0.008
 pic+0.008
 showers+0.007
Neg logit contributions
 captain-0.008
hips-0.008
ole-0.008
rave-0.007
ble-0.007
Token box
Token ID3091
Feature activation+3.13e-02

Pos logit contributions
 minutes+0.003
 pic+0.003
 spilled+0.003
 tea+0.003
pill+0.003
Neg logit contributions
rave-0.004
hips-0.004
ole-0.004
 captain-0.004
ble-0.004
Token of
Token ID286
Feature activation+1.53e-04

Pos logit contributions
rave+0.055
 captain+0.055
roc+0.054
ole+0.053
hips+0.052
Neg logit contributions
 minutes-0.042
 spilled-0.035
 pic-0.034
storms-0.034
 knocks-0.032
Token ch
Token ID442
Feature activation-1.11e-02

Pos logit contributions
ole+0.000
rave+0.000
ble+0.000
 captain+0.000
hips+0.000
Neg logit contributions
 minutes-0.000
 pic-0.000
pill-0.000
 showers-0.000
 spilled-0.000
Tokenocol
Token ID4668
Feature activation+7.70e-02

Pos logit contributions
 minutes+0.019
pill+0.017
 pic+0.017
storms+0.017
 showers+0.016
Neg logit contributions
 captain-0.016
rave-0.015
ole-0.015
hips-0.015
ble-0.014
Tokenates
Token ID689
Feature activation+1.42e-02

Pos logit contributions
 captain+0.088
hips+0.079
ole+0.077
rave+0.076
ble+0.070
Neg logit contributions
 minutes-0.153
pill-0.146
 pic-0.144
storms-0.142
 showers-0.132
Token.
Token ID13
Feature activation+4.04e-03

Pos logit contributions
 captain+0.029
rave+0.028
ole+0.027
hips+0.027
roc+0.027
Neg logit contributions
 minutes-0.015
storms-0.013
 spilled-0.013
pill-0.013
 pic-0.013
Token
Token ID198
Feature activation+6.07e-04

Pos logit contributions
 captain+0.006
hips+0.006
ole+0.005
rave+0.005
 sir+0.005
Neg logit contributions
pill-0.006
 minutes-0.006
storms-0.006
zed-0.006
 spilled-0.006
Token
Token ID198
Feature activation+3.46e-03

Pos logit contributions
 captain+0.001
hips+0.001
ole+0.001
ble+0.001
rave+0.001
Neg logit contributions
storms-0.001
 minutes-0.001
pill-0.001
 pic-0.001
 showers-0.001
Token"
Token ID1
Feature activation-4.97e-03

Pos logit contributions
 captain+0.005
hips+0.005
rave+0.005
ole+0.005
ble+0.005
Neg logit contributions
 minutes-0.006
 pic-0.005
pill-0.005
 showers-0.004
storms-0.004
Token he
Token ID339
Feature activation+1.25e-02

Pos logit contributions
 captain+0.026
hips+0.026
rave+0.026
ole+0.025
ble+0.024
Neg logit contributions
 minutes-0.028
 pic-0.026
storms-0.025
pill-0.025
 showers-0.024
Token ate
Token ID15063
Feature activation-1.37e-02

Pos logit contributions
 captain+0.023
ole+0.021
rave+0.021
hips+0.021
ble+0.020
Neg logit contributions
 minutes-0.016
pill-0.015
storms-0.015
 pic-0.015
 showers-0.014
Token all
Token ID477
Feature activation+3.99e-03

Pos logit contributions
 minutes+0.025
pill+0.024
storms+0.024
 pic+0.023
 showers+0.022
Neg logit contributions
 captain-0.018
ole-0.017
hips-0.016
rave-0.016
ble-0.016
Token the
Token ID262
Feature activation-2.81e-03

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.007
storms-0.006
pill-0.006
 pic-0.006
 showers-0.006
Token ch
Token ID442
Feature activation-1.67e-02

Pos logit contributions
 minutes+0.005
storms+0.004
pill+0.004
 pic+0.004
 showers+0.004
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.004
rave-0.004
ble-0.004
Tokenocol
Token ID4668
Feature activation+7.68e-02

Pos logit contributions
 minutes+0.034
 pic+0.033
storms+0.033
pill+0.032
 showers+0.031
Neg logit contributions
ole-0.017
 captain-0.017
hips-0.016
rave-0.016
ble-0.015
Tokenates
Token ID689
Feature activation+2.33e-02

Pos logit contributions
 captain+0.070
ole+0.065
hips+0.064
rave+0.062
ble+0.057
Neg logit contributions
 minutes-0.168
pill-0.161
 pic-0.161
storms-0.160
 showers-0.153
Token and
Token ID290
Feature activation-8.30e-03

Pos logit contributions
 captain+0.042
hips+0.041
rave+0.040
roc+0.038
ole+0.038
Neg logit contributions
 minutes-0.029
 pic-0.028
pill-0.027
storms-0.027
 spilled-0.026
Token sweets
Token ID42402
Feature activation+7.09e-03

Pos logit contributions
 minutes+0.011
pill+0.011
storms+0.011
 pic+0.010
 showers+0.010
Neg logit contributions
 captain-0.014
rave-0.013
ole-0.013
ble-0.013
hips-0.013
Token.
Token ID13
Feature activation+2.66e-03

Pos logit contributions
 captain+0.012
hips+0.012
ole+0.012
rave+0.012
ble+0.011
Neg logit contributions
 minutes-0.010
 pic-0.009
storms-0.009
pill-0.009
 spilled-0.008
Token Then
Token ID3244
Feature activation-1.26e-02

Pos logit contributions
 captain+0.003
rave+0.003
ole+0.002
hips+0.002
 himself+0.002
Neg logit contributions
 minutes-0.006
 pic-0.005
pill-0.005
storms-0.005
 spilled-0.005
Token and
Token ID290
Feature activation+9.77e-03

Pos logit contributions
 captain+0.047
hips+0.045
rave+0.045
ole+0.045
ble+0.043
Neg logit contributions
 minutes-0.034
 pic-0.030
storms-0.030
pill-0.029
 spilled-0.027
Token started
Token ID2067
Feature activation-3.06e-02

Pos logit contributions
 captain+0.018
hips+0.018
ole+0.018
rave+0.017
ble+0.017
Neg logit contributions
 minutes-0.012
pill-0.011
 pic-0.011
storms-0.011
 showers-0.010
Token eating
Token ID6600
Feature activation-3.15e-02

Pos logit contributions
storms+0.049
pill+0.049
 minutes+0.049
 pic+0.046
 showers+0.043
Neg logit contributions
 captain-0.044
rave-0.042
ole-0.040
hips-0.039
ble-0.038
Token the
Token ID262
Feature activation-8.19e-03

Pos logit contributions
 minutes+0.047
pill+0.044
 pic+0.043
storms+0.043
 showers+0.040
Neg logit contributions
 captain-0.051
ole-0.049
hips-0.049
rave-0.048
ble-0.046
Token ch
Token ID442
Feature activation-2.20e-02

Pos logit contributions
 minutes+0.012
 pic+0.011
pill+0.011
storms+0.010
 spilled+0.010
Neg logit contributions
 captain-0.014
hips-0.014
ole-0.013
rave-0.013
ble-0.013
Tokenocol
Token ID4668
Feature activation+7.60e-02

Pos logit contributions
 minutes+0.040
pill+0.038
 pic+0.038
storms+0.038
 showers+0.036
Neg logit contributions
 captain-0.028
hips-0.026
ole-0.026
rave-0.026
ble-0.024
Tokenates
Token ID689
Feature activation+2.69e-03

Pos logit contributions
 captain+0.075
hips+0.069
ole+0.068
rave+0.066
ble+0.061
Neg logit contributions
 minutes-0.161
pill-0.154
 pic-0.153
storms-0.153
 showers-0.145
Token.
Token ID13
Feature activation-5.26e-04

Pos logit contributions
 captain+0.005
hips+0.005
rave+0.005
ole+0.005
ble+0.004
Neg logit contributions
 minutes-0.003
pill-0.003
 pic-0.003
storms-0.003
 showers-0.003
Token The
Token ID383
Feature activation-4.67e-04

Pos logit contributions
 minutes+0.001
storms+0.001
pill+0.001
 pic+0.001
 spilled+0.001
Neg logit contributions
 captain-0.001
rave-0.001
ole-0.001
 himself-0.000
hips-0.000
Token shop
Token ID6128
Feature activation+1.72e-02

Pos logit contributions
 minutes+0.001
pill+0.001
 pic+0.001
storms+0.001
 showers+0.001
Neg logit contributions
 captain-0.001
hips-0.001
ole-0.001
rave-0.001
ble-0.001
Tokenkeeper
Token ID13884
Feature activation+6.84e-03

Pos logit contributions
hips+0.024
 captain+0.023
rave+0.022
ole+0.022
ble+0.021
Neg logit contributions
 minutes-0.029
 spilled-0.027
storms-0.026
pill-0.026
 pic-0.026
Token a
Token ID257
Feature activation+5.50e-03

Pos logit contributions
hips+0.023
 captain+0.023
rave+0.021
ole+0.021
ble+0.021
Neg logit contributions
 minutes-0.033
 pic-0.032
storms-0.030
pill-0.030
 showers-0.030
Token big
Token ID1263
Feature activation+4.64e-03

Pos logit contributions
hips+0.009
 captain+0.009
rave+0.009
ole+0.009
ble+0.009
Neg logit contributions
 minutes-0.008
 pic-0.007
pill-0.007
 spilled-0.007
storms-0.007
Token box
Token ID3091
Feature activation+3.78e-02

Pos logit contributions
hips+0.007
rave+0.007
ble+0.007
 captain+0.007
ole+0.007
Neg logit contributions
 minutes-0.007
 pic-0.007
 spilled-0.006
pill-0.006
 tea-0.006
Token of
Token ID286
Feature activation+4.07e-03

Pos logit contributions
rave+0.071
roc+0.070
 captain+0.070
hips+0.068
ble+0.067
Neg logit contributions
 minutes-0.043
storms-0.037
 pic-0.036
 spilled-0.036
pill-0.033
Token ch
Token ID442
Feature activation-1.34e-02

Pos logit contributions
hips+0.006
rave+0.006
 captain+0.006
ole+0.005
ble+0.005
Neg logit contributions
 minutes-0.007
 pic-0.007
pill-0.006
 showers-0.006
 tea-0.006
Tokenocol
Token ID4668
Feature activation+7.57e-02

Pos logit contributions
 minutes+0.023
pill+0.022
 pic+0.022
storms+0.021
 showers+0.020
Neg logit contributions
 captain-0.019
hips-0.018
rave-0.017
ole-0.017
ble-0.016
Tokenates
Token ID689
Feature activation+2.19e-02

Pos logit contributions
 captain+0.080
hips+0.073
ole+0.073
rave+0.071
ble+0.066
Neg logit contributions
 minutes-0.155
pill-0.148
 pic-0.148
storms-0.147
 showers-0.139
Token to
Token ID284
Feature activation+8.94e-03

Pos logit contributions
rave+0.045
roc+0.044
 captain+0.044
hips+0.044
ole+0.041
Neg logit contributions
 minutes-0.019
 spilled-0.019
storms-0.019
 pic-0.016
pill-0.016
Token share
Token ID2648
Feature activation+5.89e-03

Pos logit contributions
 captain+0.013
ole+0.013
rave+0.013
hips+0.013
ble+0.012
Neg logit contributions
 minutes-0.014
 pic-0.014
pill-0.013
storms-0.013
 showers-0.013
Token with
Token ID351
Feature activation+6.16e-03

Pos logit contributions
 captain+0.011
hips+0.010
rave+0.010
ole+0.010
ble+0.010
Neg logit contributions
 minutes-0.008
 pic-0.007
pill-0.007
storms-0.007
 showers-0.006
Token the
Token ID262
Feature activation-3.68e-03

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.013
pill-0.013
storms-0.013
 pic-0.013
 spilled-0.012
Token a
Token ID257
Feature activation+3.20e-03

Pos logit contributions
 minutes+0.005
 pic+0.005
pill+0.005
storms+0.005
 showers+0.005
Neg logit contributions
 captain-0.006
ole-0.006
hips-0.006
rave-0.006
ble-0.006
Token big
Token ID1263
Feature activation+9.66e-04

Pos logit contributions
hips+0.005
 captain+0.005
ole+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.005
 pic-0.004
pill-0.004
 spilled-0.004
storms-0.004
Token box
Token ID3091
Feature activation+2.22e-02

Pos logit contributions
hips+0.002
rave+0.002
 captain+0.002
ole+0.001
ble+0.001
Neg logit contributions
 minutes-0.001
 pic-0.001
 spilled-0.001
 knocks-0.001
storms-0.001
Token of
Token ID286
Feature activation-4.93e-04

Pos logit contributions
 captain+0.036
rave+0.034
ole+0.034
hips+0.034
ble+0.032
Neg logit contributions
 minutes-0.034
 pic-0.031
storms-0.031
pill-0.030
 spilled-0.029
Token ch
Token ID442
Feature activation-1.85e-02

Pos logit contributions
 minutes+0.001
 pic+0.001
 spilled+0.001
pill+0.001
 showers+0.001
Neg logit contributions
 captain-0.001
ole-0.001
rave-0.001
ble-0.001
hips-0.001
Tokenocol
Token ID4668
Feature activation+7.53e-02

Pos logit contributions
 minutes+0.034
pill+0.032
 pic+0.031
storms+0.031
 showers+0.030
Neg logit contributions
 captain-0.025
hips-0.023
ole-0.023
rave-0.023
ble-0.021
Tokenates
Token ID689
Feature activation+8.59e-03

Pos logit contributions
 captain+0.080
hips+0.073
ole+0.073
rave+0.071
ble+0.065
Neg logit contributions
 minutes-0.155
pill-0.148
 pic-0.147
storms-0.146
 showers-0.138
Token!
Token ID0
Feature activation-1.96e-03

Pos logit contributions
 captain+0.015
rave+0.014
hips+0.014
ole+0.014
roc+0.013
Neg logit contributions
 minutes-0.012
storms-0.011
pill-0.011
 pic-0.011
 spilled-0.011
Token
Token ID220
Feature activation+1.17e-02

Pos logit contributions
 minutes+0.003
 pic+0.003
storms+0.003
 spilled+0.003
pill+0.003
Neg logit contributions
rave-0.002
 captain-0.002
ole-0.002
hips-0.002
 Elliot-0.002
Token
Token ID198
Feature activation-1.07e-02

Pos logit contributions
hips+0.021
rave+0.021
ole+0.021
ble+0.020
 captain+0.020
Neg logit contributions
 minutes-0.016
storms-0.014
 pic-0.014
pill-0.014
 showers-0.013
Token
Token ID198
Feature activation-5.65e-03

Pos logit contributions
 minutes+0.015
storms+0.014
pill+0.013
 pic+0.013
 showers+0.012
Neg logit contributions
rave-0.018
hips-0.018
ole-0.018
 captain-0.017
ble-0.017
Token there
Token ID612
Feature activation+2.43e-04

Pos logit contributions
 captain+0.040
ole+0.038
hips+0.038
rave+0.037
ble+0.035
Neg logit contributions
 minutes-0.053
pill-0.050
 pic-0.050
storms-0.050
 showers-0.046
Token was
Token ID373
Feature activation-2.37e-03

Pos logit contributions
 captain+0.000
ble+0.000
ole+0.000
rave+0.000
hips+0.000
Neg logit contributions
 minutes-0.000
pill-0.000
storms-0.000
 pic-0.000
 showers-0.000
Token a
Token ID257
Feature activation+6.15e-03

Pos logit contributions
storms+0.004
 minutes+0.004
pill+0.004
 pic+0.004
 knocks+0.004
Neg logit contributions
 captain-0.003
ole-0.003
ble-0.002
rave-0.002
hips-0.002
Token huge
Token ID3236
Feature activation+4.75e-03

Pos logit contributions
 captain+0.011
ole+0.010
hips+0.010
rave+0.010
ble+0.010
Neg logit contributions
 minutes-0.008
pill-0.008
 pic-0.008
storms-0.008
 showers-0.007
Token hipp
Token ID18568
Feature activation+2.82e-02

Pos logit contributions
 captain+0.007
hips+0.007
ole+0.007
rave+0.007
ble+0.006
Neg logit contributions
 minutes-0.008
 pic-0.007
pill-0.007
storms-0.007
 showers-0.007
Tokenopot
Token ID43372
Feature activation+7.51e-02

Pos logit contributions
 captain+0.038
ole+0.036
hips+0.036
rave+0.035
ble+0.033
Neg logit contributions
 minutes-0.050
 pic-0.047
pill-0.047
storms-0.047
 showers-0.044
Tokenamus
Token ID25509
Feature activation+1.20e-02

Pos logit contributions
bek+0.058
cher+0.055
 promise+0.051
rave+0.051
cer+0.050
Neg logit contributions
storms-0.146
pill-0.142
 ow-0.140
 pic-0.138
 minutes-0.135
Token.
Token ID13
Feature activation-1.93e-03

Pos logit contributions
 captain+0.017
ble+0.016
ole+0.015
boat+0.014
ter+0.014
Neg logit contributions
 pic-0.021
 minutes-0.021
pill-0.020
 showers-0.020
storms-0.019
Token He
Token ID679
Feature activation+2.15e-02

Pos logit contributions
 minutes+0.002
storms+0.002
pill+0.002
 pic+0.002
 showers+0.002
Neg logit contributions
 captain-0.004
hips-0.003
ole-0.003
rave-0.003
ble-0.003
Token was
Token ID373
Feature activation-7.46e-03

Pos logit contributions
 captain+0.034
ole+0.031
rave+0.030
hips+0.029
ble+0.029
Neg logit contributions
 minutes-0.034
pill-0.032
 pic-0.032
storms-0.032
 showers-0.030
Token feeling
Token ID4203
Feature activation-3.65e-02

Pos logit contributions
 minutes+0.010
 pic+0.009
pill+0.009
storms+0.009
 showers+0.009
Neg logit contributions
hips-0.013
 captain-0.013
ole-0.013
rave-0.012
ble-0.012
Token make
Token ID787
Feature activation-6.58e-03

Pos logit contributions
 minutes+0.035
 pic+0.033
storms+0.033
pill+0.032
 showers+0.032
Neg logit contributions
 captain-0.037
rave-0.036
hips-0.035
ole-0.035
ble-0.033
Token the
Token ID262
Feature activation-5.34e-03

Pos logit contributions
 minutes+0.011
pill+0.010
storms+0.010
 pic+0.010
zed+0.009
Neg logit contributions
 captain-0.010
ole-0.010
hips-0.009
ble-0.009
rave-0.009
Token waiter
Token ID46612
Feature activation+1.49e-02

Pos logit contributions
 minutes+0.008
pill+0.008
 pic+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.008
ole-0.008
hips-0.008
rave-0.008
ble-0.007
Token drop
Token ID4268
Feature activation-8.14e-03

Pos logit contributions
 captain+0.026
rave+0.026
hips+0.025
ole+0.025
ble+0.023
Neg logit contributions
 minutes-0.020
storms-0.018
 spilled-0.017
 pic-0.017
pill-0.017
Token the
Token ID262
Feature activation+1.52e-03

Pos logit contributions
 minutes+0.013
pill+0.012
 pic+0.012
storms+0.012
 showers+0.011
Neg logit contributions
 captain-0.013
ole-0.012
hips-0.012
rave-0.012
ble-0.011
Token pizz
Token ID38748
Feature activation+7.50e-02

Pos logit contributions
 captain+0.003
hips+0.003
ole+0.003
rave+0.003
ble+0.002
Neg logit contributions
 minutes-0.002
 pic-0.002
pill-0.002
storms-0.002
 spilled-0.002
Tokenas
Token ID292
Feature activation+1.12e-02

Pos logit contributions
 captain+0.116
 Elliot+0.115
rave+0.114
 avail+0.109
lynn+0.107
Neg logit contributions
 minutes-0.094
pill-0.088
storms-0.087
pler-0.086
 spilled-0.084
Token.
Token ID13
Feature activation+5.58e-03

Pos logit contributions
 captain+0.021
rave+0.021
hips+0.020
ole+0.020
ble+0.019
Neg logit contributions
 minutes-0.013
storms-0.012
 pic-0.012
pill-0.012
 spilled-0.012
Token They
Token ID1119
Feature activation+1.02e-02

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.006
rave+0.005
 ourselves+0.005
Neg logit contributions
 minutes-0.011
pill-0.010
zed-0.010
 pic-0.010
 spilled-0.010
Token said
Token ID531
Feature activation-5.84e-03

Pos logit contributions
 captain+0.019
ole+0.019
hips+0.018
rave+0.018
ble+0.017
Neg logit contributions
 minutes-0.012
pill-0.011
 pic-0.011
storms-0.011
 showers-0.010
Token sorry
Token ID7926
Feature activation+9.24e-03

Pos logit contributions
 minutes+0.009
pill+0.009
 pic+0.009
storms+0.009
 showers+0.008
Neg logit contributions
 captain-0.009
ole-0.009
hips-0.008
rave-0.008
ble-0.008
Token giving
Token ID3501
Feature activation+4.56e-03

Pos logit contributions
 captain+0.016
ole+0.016
ble+0.016
rave+0.015
hips+0.015
Neg logit contributions
 minutes-0.021
storms-0.021
pill-0.021
 pic-0.020
 showers-0.019
Token him
Token ID683
Feature activation-1.18e-02

Pos logit contributions
 captain+0.007
ole+0.007
rave+0.007
hips+0.007
ble+0.006
Neg logit contributions
 minutes-0.007
storms-0.006
pill-0.006
 pic-0.006
 showers-0.006
Token too
Token ID1165
Feature activation-1.31e-02

Pos logit contributions
 minutes+0.017
 pic+0.016
pill+0.016
storms+0.015
 showers+0.015
Neg logit contributions
 captain-0.019
hips-0.019
rave-0.018
ole-0.018
ble-0.017
Token many
Token ID867
Feature activation-2.46e-02

Pos logit contributions
 minutes+0.016
pill+0.015
storms+0.015
 pic+0.015
 showers+0.013
Neg logit contributions
ole-0.024
 captain-0.024
hips-0.023
rave-0.023
ble-0.022
Token ch
Token ID442
Feature activation-2.29e-02

Pos logit contributions
storms+0.041
 minutes+0.039
pill+0.039
 pic+0.038
zed+0.036
Neg logit contributions
 captain-0.034
ole-0.032
hips-0.031
rave-0.029
ble-0.028
Tokenocol
Token ID4668
Feature activation+7.50e-02

Pos logit contributions
 minutes+0.047
storms+0.046
 pic+0.046
pill+0.044
 spilled+0.043
Neg logit contributions
ole-0.025
 captain-0.024
hips-0.022
rave-0.021
ble-0.021
Tokenates
Token ID689
Feature activation+6.18e-03

Pos logit contributions
 captain+0.080
hips+0.073
ole+0.069
rave+0.069
ble+0.062
Neg logit contributions
 minutes-0.153
pill-0.148
 pic-0.146
storms-0.144
 showers-0.135
Token."
Token ID526
Feature activation-9.77e-03

Pos logit contributions
 captain+0.011
hips+0.010
ole+0.010
rave+0.010
ble+0.009
Neg logit contributions
 minutes-0.008
pill-0.008
 pic-0.008
storms-0.008
 showers-0.007
Token The
Token ID383
Feature activation+4.01e-03

Pos logit contributions
 minutes+0.013
 pic+0.011
pill+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.018
ole-0.017
rave-0.017
hips-0.016
ble-0.016
Token king
Token ID5822
Feature activation-1.46e-02

Pos logit contributions
hips+0.005
rave+0.005
 captain+0.005
ole+0.005
ble+0.005
Neg logit contributions
 minutes-0.007
pill-0.006
 pic-0.006
storms-0.006
 spilled-0.006
Token learned
Token ID4499
Feature activation+2.37e-02

Pos logit contributions
 minutes+0.020
pill+0.019
storms+0.019
 pic+0.019
 showers+0.017
Neg logit contributions
 captain-0.025
hips-0.024
ole-0.024
rave-0.023
ble-0.022
Token Everyday
Token ID48154
Feature activation+1.53e-04

Pos logit contributions
 captain+0.020
hips+0.019
ole+0.018
rave+0.018
ble+0.017
Neg logit contributions
 minutes-0.017
pill-0.016
 pic-0.016
storms-0.015
 showers-0.014
Token he
Token ID339
Feature activation+3.32e-03

Pos logit contributions
 captain+0.000
ole+0.000
hips+0.000
rave+0.000
ble+0.000
Neg logit contributions
 minutes-0.000
pill-0.000
storms-0.000
 pic-0.000
 showers-0.000
Token would
Token ID561
Feature activation+5.64e-03

Pos logit contributions
 captain+0.006
ole+0.005
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
 minutes-0.005
pill-0.004
 pic-0.004
storms-0.004
 showers-0.004
Token take
Token ID1011
Feature activation-3.14e-03

Pos logit contributions
 captain+0.007
hips+0.007
ole+0.007
rave+0.007
ble+0.006
Neg logit contributions
 minutes-0.010
pill-0.010
 pic-0.009
storms-0.009
 showers-0.009
Token the
Token ID262
Feature activation+9.46e-03

Pos logit contributions
pill+0.006
 minutes+0.006
storms+0.006
 pic+0.005
 spilled+0.005
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.003
rave-0.003
 himself-0.003
Token av
Token ID1196
Feature activation+7.50e-02

Pos logit contributions
 captain+0.014
ole+0.013
hips+0.013
rave+0.013
ble+0.012
Neg logit contributions
 minutes-0.015
pill-0.015
 pic-0.015
storms-0.014
 showers-0.014
Tokenoc
Token ID420
Feature activation+4.79e-02

Pos logit contributions
 captain+0.121
hips+0.116
ble+0.109
rave+0.109
ole+0.107
Neg logit contributions
 minutes-0.111
pill-0.111
 pic-0.106
storms-0.104
 mornings-0.093
Tokenados
Token ID22484
Feature activation+4.84e-02

Pos logit contributions
 captain+0.069
hips+0.066
ole+0.062
rave+0.061
ble+0.060
Neg logit contributions
pill-0.077
 minutes-0.076
storms-0.074
 pic-0.072
 showers-0.066
Token and
Token ID290
Feature activation-4.58e-03

Pos logit contributions
 captain+0.079
hips+0.075
ole+0.075
rave+0.074
ble+0.071
Neg logit contributions
 minutes-0.071
pill-0.066
 pic-0.066
storms-0.066
 showers-0.061
Token scatter
Token ID41058
Feature activation-2.33e-02

Pos logit contributions
 minutes+0.007
pill+0.007
storms+0.007
 pic+0.007
 showers+0.006
Neg logit contributions
 captain-0.007
ole-0.006
hips-0.006
rave-0.006
ble-0.006
Token them
Token ID606
Feature activation+3.36e-03

Pos logit contributions
 minutes+0.036
storms+0.034
pill+0.034
 pic+0.033
zed+0.032
Neg logit contributions
ole-0.037
 captain-0.036
hips-0.035
rave-0.033
ble-0.031
Token a
Token ID257
Feature activation-3.09e-03

Pos logit contributions
 captain+0.002
hips+0.002
ole+0.002
rave+0.002
ble+0.002
Neg logit contributions
 minutes-0.002
 pic-0.002
pill-0.002
storms-0.002
 showers-0.002
Token triangle
Token ID22950
Feature activation-7.00e-03

Pos logit contributions
 minutes+0.005
pill+0.004
storms+0.004
 pic+0.004
 showers+0.004
Neg logit contributions
 captain-0.005
ole-0.005
hips-0.005
rave-0.005
ble-0.004
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 minutes+0.011
 pic+0.011
pill+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.010
ole-0.010
hips-0.010
ble-0.009
rave-0.009
Token It
Token ID632
Feature activation-4.55e-03

Pos logit contributions
 minutes+0.018
pill+0.017
storms+0.017
 pic+0.016
 showers+0.015
Neg logit contributions
 captain-0.028
ole-0.027
hips-0.027
rave-0.026
ble-0.025
Token has
Token ID468
Feature activation-7.12e-03

Pos logit contributions
 minutes+0.007
 pic+0.006
storms+0.006
pill+0.006
 showers+0.006
Neg logit contributions
 captain-0.008
hips-0.007
rave-0.007
ole-0.007
ble-0.007
Token three
Token ID1115
Feature activation-7.62e-02

Pos logit contributions
storms+0.012
 minutes+0.012
 pic+0.012
pill+0.012
zed+0.011
Neg logit contributions
 captain-0.010
hips-0.009
ole-0.009
rave-0.009
ble-0.008
Token sides
Token ID5389
Feature activation-1.98e-02

Pos logit contributions
storms+0.142
 pic+0.134
zed+0.127
pill+0.127
 showers+0.125
Neg logit contributions
ole-0.089
 captain-0.089
bles-0.086
ble-0.081
oy-0.079
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
 pic+0.031
 minutes+0.031
storms+0.030
pill+0.030
zed+0.028
Neg logit contributions
 captain-0.030
hips-0.029
ole-0.028
rave-0.027
ble-0.027
Token three
Token ID1115
Feature activation-7.30e-02

Pos logit contributions
 minutes+0.034
 pic+0.034
storms+0.034
pill+0.032
zed+0.032
Neg logit contributions
 captain-0.030
hips-0.027
rave-0.026
ole-0.025
ble-0.025
Token points
Token ID2173
Feature activation-6.21e-03

Pos logit contributions
storms+0.131
 pic+0.130
pill+0.122
zed+0.117
 showers+0.116
Neg logit contributions
 captain-0.092
ole-0.088
bles-0.088
hips-0.083
ble-0.082
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 minutes+0.009
pill+0.008
 pic+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.011
ole-0.010
hips-0.010
rave-0.010
ble-0.010
Token's
Token ID338
Feature activation-1.56e-02

Pos logit contributions
 minutes+0.046
 pic+0.044
pill+0.043
storms+0.042
 showers+0.042
Neg logit contributions
ole-0.053
 captain-0.053
hips-0.051
rave-0.051
pper-0.048
Token fork
Token ID15563
Feature activation-1.06e-02

Pos logit contributions
pill+0.026
storms+0.025
 pic+0.025
 minutes+0.024
 showers+0.023
Neg logit contributions
 captain-0.023
ole-0.022
ble-0.020
rave-0.020
hips-0.020
Token.
Token ID13
Feature activation-3.91e-03

Pos logit contributions
 minutes+0.015
pill+0.015
 pic+0.015
storms+0.014
 showers+0.014
Neg logit contributions
 captain-0.017
ole-0.017
hips-0.016
ble-0.016
rave-0.016
Token It
Token ID632
Feature activation-6.72e-03

Pos logit contributions
pill+0.006
storms+0.006
 minutes+0.006
 spilled+0.006
 pic+0.006
Neg logit contributions
 captain-0.005
 himself-0.005
hips-0.005
rave-0.005
ole-0.005
Token has
Token ID468
Feature activation-8.81e-03

Pos logit contributions
 minutes+0.010
 pic+0.010
storms+0.009
 showers+0.009
pill+0.009
Neg logit contributions
 captain-0.010
rave-0.010
hips-0.010
ole-0.009
ble-0.009
Token three
Token ID1115
Feature activation-7.55e-02

Pos logit contributions
storms+0.016
 minutes+0.015
pill+0.015
 pic+0.015
 showers+0.014
Neg logit contributions
 captain-0.011
hips-0.010
ole-0.010
 luck-0.010
rave-0.009
Token teeth
Token ID9941
Feature activation-1.76e-02

Pos logit contributions
storms+0.129
 pic+0.123
pill+0.120
 showers+0.115
storm+0.109
Neg logit contributions
 captain-0.096
ole-0.096
bles-0.092
ble-0.091
 himself-0.089
Token and
Token ID290
Feature activation-2.41e-02

Pos logit contributions
 pic+0.030
 minutes+0.029
pill+0.028
storms+0.027
 showers+0.027
Neg logit contributions
hips-0.024
 captain-0.024
ble-0.023
ole-0.023
rave-0.022
Token a
Token ID257
Feature activation-2.02e-03

Pos logit contributions
storms+0.042
 pic+0.039
pill+0.038
 minutes+0.038
 showers+0.037
Neg logit contributions
 captain-0.032
ble-0.029
rave-0.028
hips-0.028
 luck-0.028
Token pink
Token ID11398
Feature activation-1.60e-02

Pos logit contributions
 minutes+0.003
pill+0.003
storms+0.003
 pic+0.003
 showers+0.003
Neg logit contributions
 captain-0.003
ole-0.003
hips-0.003
rave-0.003
ble-0.003
Token handle
Token ID5412
Feature activation-4.17e-03

Pos logit contributions
 minutes+0.024
pill+0.023
 pic+0.023
storms+0.022
 showers+0.021
Neg logit contributions
 captain-0.025
hips-0.024
ole-0.024
rave-0.024
ble-0.023
Token a
Token ID257
Feature activation+4.08e-03

Pos logit contributions
 minutes+0.001
 pic+0.001
storms+0.001
pill+0.001
 showers+0.001
Neg logit contributions
 captain-0.001
hips-0.001
ole-0.001
rave-0.001
ble-0.001
Token triangle
Token ID22950
Feature activation-5.61e-03

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.005
rave+0.005
ble+0.005
Neg logit contributions
pill-0.007
storms-0.007
 minutes-0.007
 pic-0.006
 showers-0.006
Token.
Token ID13
Feature activation-1.79e-02

Pos logit contributions
 minutes+0.010
 pic+0.009
pill+0.009
storms+0.009
 showers+0.009
Neg logit contributions
 captain-0.008
ole-0.007
hips-0.007
rave-0.007
ble-0.007
Token It
Token ID632
Feature activation-2.66e-03

Pos logit contributions
 minutes+0.026
 pic+0.024
storms+0.023
pill+0.023
 spilled+0.022
Neg logit contributions
 captain-0.030
hips-0.029
ole-0.028
rave-0.028
ble-0.027
Token has
Token ID468
Feature activation-1.24e-02

Pos logit contributions
 minutes+0.004
 pic+0.004
storms+0.003
pill+0.003
 showers+0.003
Neg logit contributions
 captain-0.004
hips-0.004
rave-0.004
ole-0.004
ble-0.004
Token three
Token ID1115
Feature activation-7.46e-02

Pos logit contributions
storms+0.023
 minutes+0.022
 pic+0.022
pill+0.021
zed+0.021
Neg logit contributions
 captain-0.016
hips-0.015
ole-0.014
rave-0.013
 luck-0.013
Token sides
Token ID5389
Feature activation-1.86e-02

Pos logit contributions
storms+0.138
 pic+0.129
zed+0.123
pill+0.122
 showers+0.122
Neg logit contributions
ole-0.091
 captain-0.088
bles-0.084
ble-0.081
oy-0.079
Token and
Token ID290
Feature activation-1.98e-02

Pos logit contributions
 minutes+0.029
 pic+0.028
pill+0.028
storms+0.028
 showers+0.026
Neg logit contributions
 captain-0.028
hips-0.027
ole-0.027
rave-0.026
ble-0.025
Token three
Token ID1115
Feature activation-6.94e-02

Pos logit contributions
storms+0.033
 pic+0.033
 minutes+0.033
zed+0.031
pill+0.031
Neg logit contributions
 captain-0.027
hips-0.025
rave-0.024
ble-0.024
 ourselves-0.023
Token corners
Token ID14371
Feature activation-1.28e-02

Pos logit contributions
storms+0.121
 pic+0.119
pill+0.111
zed+0.108
 showers+0.107
Neg logit contributions
 captain-0.090
ole-0.090
bles-0.084
hips-0.083
ble-0.081
Token.
Token ID13
Feature activation-9.27e-03

Pos logit contributions
 minutes+0.018
 pic+0.017
pill+0.016
storms+0.016
 showers+0.015
Neg logit contributions
 captain-0.022
hips-0.021
ole-0.021
rave-0.021
ble-0.020
Token,
Token ID11
Feature activation+1.77e-03

Pos logit contributions
 captain+0.002
ole+0.002
rave+0.002
hips+0.002
 promise+0.002
Neg logit contributions
pill-0.002
 minutes-0.002
 pic-0.002
storms-0.002
 showers-0.002
Token who
Token ID508
Feature activation+3.23e-04

Pos logit contributions
 captain+0.003
ole+0.003
hips+0.003
rave+0.003
ble+0.002
Neg logit contributions
pill-0.003
 minutes-0.003
storms-0.003
 pic-0.003
 showers-0.002
Token said
Token ID531
Feature activation-2.07e-02

Pos logit contributions
 captain+0.001
ole+0.001
rave+0.001
hips+0.001
ble+0.001
Neg logit contributions
 minutes-0.000
 pic-0.000
pill-0.000
storms-0.000
 showers-0.000
Token that
Token ID326
Feature activation-5.62e-03

Pos logit contributions
 minutes+0.032
pill+0.030
 pic+0.030
storms+0.030
 showers+0.027
Neg logit contributions
 captain-0.033
ole-0.031
hips-0.031
rave-0.030
ble-0.029
Token her
Token ID607
Feature activation-3.21e-02

Pos logit contributions
 minutes+0.009
pill+0.008
storms+0.008
 pic+0.008
 showers+0.007
Neg logit contributions
 captain-0.009
ole-0.008
rave-0.008
hips-0.008
ble-0.008
Token toe
Token ID21189
Feature activation-7.38e-02

Pos logit contributions
 minutes+0.057
pill+0.055
storms+0.055
 pic+0.054
 showers+0.049
Neg logit contributions
 captain-0.044
ole-0.040
rave-0.040
hips-0.039
ble-0.038
Token was
Token ID373
Feature activation-2.81e-02

Pos logit contributions
 minutes+0.108
 pic+0.104
pill+0.100
storms+0.094
 showers+0.089
Neg logit contributions
 captain-0.120
ble-0.113
ole-0.111
rave-0.110
hips-0.109
Token broken
Token ID5445
Feature activation+1.50e-02

Pos logit contributions
pill+0.051
 minutes+0.047
 pic+0.047
storms+0.047
 showers+0.042
Neg logit contributions
 captain-0.038
ole-0.034
ble-0.034
hips-0.033
rave-0.032
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 captain+0.023
ole+0.023
hips+0.022
ble+0.021
rave+0.021
Neg logit contributions
pill-0.023
 minutes-0.023
 pic-0.022
storms-0.021
 showers-0.020
Token Lily
Token ID20037
Feature activation-1.53e-02

Pos logit contributions
 minutes+0.018
 spills+0.016
 pic+0.016
 spilled+0.016
pill+0.016
Neg logit contributions
 captain-0.015
ole-0.015
rave-0.015
 sir-0.014
 Elliot-0.014
Token felt
Token ID2936
Feature activation-2.87e-02

Pos logit contributions
 minutes+0.022
 pic+0.021
pill+0.021
storms+0.020
 showers+0.019
Neg logit contributions
 captain-0.026
rave-0.025
ole-0.024
ble-0.023
 promise-0.023
Token It
Token ID632
Feature activation-4.55e-03

Pos logit contributions
 minutes+0.018
pill+0.017
storms+0.017
 pic+0.016
 showers+0.015
Neg logit contributions
 captain-0.028
ole-0.027
hips-0.027
rave-0.026
ble-0.025
Token has
Token ID468
Feature activation-7.12e-03

Pos logit contributions
 minutes+0.007
 pic+0.006
storms+0.006
pill+0.006
 showers+0.006
Neg logit contributions
 captain-0.008
hips-0.007
rave-0.007
ole-0.007
ble-0.007
Token three
Token ID1115
Feature activation-7.62e-02

Pos logit contributions
storms+0.012
 minutes+0.012
 pic+0.012
pill+0.012
zed+0.011
Neg logit contributions
 captain-0.010
hips-0.009
ole-0.009
rave-0.009
ble-0.008
Token sides
Token ID5389
Feature activation-1.98e-02

Pos logit contributions
storms+0.142
 pic+0.134
zed+0.127
pill+0.127
 showers+0.125
Neg logit contributions
ole-0.089
 captain-0.089
bles-0.086
ble-0.081
oy-0.079
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
 pic+0.031
 minutes+0.031
storms+0.030
pill+0.030
zed+0.028
Neg logit contributions
 captain-0.030
hips-0.029
ole-0.028
rave-0.027
ble-0.027
Token three
Token ID1115
Feature activation-7.30e-02

Pos logit contributions
 minutes+0.034
 pic+0.034
storms+0.034
pill+0.032
zed+0.032
Neg logit contributions
 captain-0.030
hips-0.027
rave-0.026
ole-0.025
ble-0.025
Token points
Token ID2173
Feature activation-6.21e-03

Pos logit contributions
storms+0.131
 pic+0.130
pill+0.122
zed+0.117
 showers+0.116
Neg logit contributions
 captain-0.092
ole-0.088
bles-0.088
hips-0.083
ble-0.082
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 minutes+0.009
pill+0.008
 pic+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.011
ole-0.010
hips-0.010
rave-0.010
ble-0.010
Token I
Token ID314
Feature activation-6.74e-03

Pos logit contributions
 minutes+0.022
 pic+0.020
storms+0.020
pill+0.020
 spilled+0.019
Neg logit contributions
 captain-0.025
hips-0.024
rave-0.023
ole-0.023
ble-0.022
Token can
Token ID460
Feature activation+1.24e-02

Pos logit contributions
 minutes+0.013
pill+0.012
 pic+0.012
storms+0.012
 showers+0.012
Neg logit contributions
 captain-0.008
hips-0.008
rave-0.008
ole-0.007
ble-0.007
Token make
Token ID787
Feature activation-1.27e-02

Pos logit contributions
ole+0.020
rave+0.019
bek+0.019
hips+0.018
 captain+0.018
Neg logit contributions
 minutes-0.016
storms-0.016
pill-0.016
 spilled-0.016
 knocks-0.015
Token four
Token ID1440
Feature activation-4.37e-02

Pos logit contributions
storms+0.018
pill+0.018
 minutes+0.017
 pic+0.017
zed+0.016
Neg logit contributions
 captain-0.011
ole-0.010
hips-0.009
 ours-0.009
rave-0.009
Token cars
Token ID5006
Feature activation+4.76e-03

Pos logit contributions
 minutes+0.069
storms+0.068
pill+0.067
 pic+0.067
 showers+0.062
Neg logit contributions
 captain-0.065
ole-0.062
hips-0.062
rave-0.060
ble-0.057
Token and
Token ID290
Feature activation-2.41e-02

Pos logit contributions
 captain+0.008
ole+0.008
hips+0.008
rave+0.008
ble+0.007
Neg logit contributions
 minutes-0.007
pill-0.006
 pic-0.006
storms-0.006
 showers-0.006
Token I
Token ID314
Feature activation-2.04e-02

Pos logit contributions
 minutes+0.041
storms+0.039
pill+0.039
 pic+0.039
 showers+0.036
Neg logit contributions
 captain-0.034
hips-0.032
ole-0.031
rave-0.031
ble-0.029
Token have
Token ID423
Feature activation-1.47e-02

Pos logit contributions
 minutes+0.035
 pic+0.033
pill+0.033
storms+0.032
 spilled+0.031
Neg logit contributions
 captain-0.028
hips-0.027
ole-0.027
rave-0.026
ble-0.025
Token three
Token ID1115
Feature activation-7.29e-02

Pos logit contributions
storms+0.027
pill+0.026
 pic+0.025
 minutes+0.025
zed+0.024
Neg logit contributions
 captain-0.020
hips-0.018
ole-0.018
rave-0.016
 ours-0.016
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
storms+0.131
pill+0.125
 pic+0.123
zed+0.115
 spilled+0.114
Neg logit contributions
 captain-0.094
ole-0.094
hips-0.088
bles-0.081
rave-0.079
Token You
Token ID921
Feature activation-5.14e-03

Pos logit contributions
 minutes+0.022
 pic+0.021
pill+0.021
storms+0.021
 spilled+0.019
Neg logit contributions
 captain-0.024
hips-0.023
ole-0.023
rave-0.023
ble-0.021
Token can
Token ID460
Feature activation+1.02e-03

Pos logit contributions
 minutes+0.007
 spilled+0.006
pill+0.006
 pic+0.006
storms+0.006
Neg logit contributions
 captain-0.008
ole-0.008
rave-0.008
ble-0.008
hips-0.008
Token't
Token ID470
Feature activation+6.55e-03

Pos logit contributions
rave+0.002
ole+0.002
 captain+0.002
bek+0.002
roc+0.001
Neg logit contributions
 knocks-0.001
 minutes-0.001
 spilled-0.001
 pic-0.001
storms-0.001
Token have
Token ID423
Feature activation-1.45e-02

Pos logit contributions
 captain+0.009
rave+0.009
hips+0.009
ole+0.009
ble+0.008
Neg logit contributions
 minutes-0.011
 pic-0.010
storms-0.010
pill-0.009
 showers-0.009
Token only
Token ID691
Feature activation+1.94e-02

Pos logit contributions
 minutes+0.003
pill+0.003
 pic+0.003
storms+0.003
 showers+0.003
Neg logit contributions
 captain-0.003
ole-0.003
hips-0.003
rave-0.003
ble-0.003
Token three
Token ID1115
Feature activation-5.08e-02

Pos logit contributions
hips+0.035
ole+0.032
rave+0.031
 captain+0.031
ble+0.030
Neg logit contributions
 minutes-0.027
pill-0.024
 showers-0.024
 pic-0.023
storms-0.023
Token and
Token ID290
Feature activation-2.26e-02

Pos logit contributions
storms+0.083
pill+0.079
 pic+0.077
 minutes+0.076
zed+0.076
Neg logit contributions
ole-0.069
 captain-0.066
roc-0.058
 guard-0.058
bles-0.058
Token like
Token ID588
Feature activation-2.05e-02

Pos logit contributions
 minutes+0.030
pill+0.029
 pic+0.029
storms+0.028
 showers+0.026
Neg logit contributions
 captain-0.040
hips-0.038
ole-0.038
rave-0.037
ble-0.036
Token all
Token ID477
Feature activation-1.15e-02

Pos logit contributions
 minutes+0.034
pill+0.032
 pic+0.031
storms+0.031
 showers+0.029
Neg logit contributions
 captain-0.031
hips-0.028
ole-0.028
rave-0.028
ble-0.027
Token three
Token ID1115
Feature activation-7.17e-02

Pos logit contributions
 minutes+0.022
pill+0.021
 pic+0.021
storms+0.021
zed+0.019
Neg logit contributions
 captain-0.013
ole-0.012
hips-0.012
rave-0.011
jack-0.011
Token-
Token ID12
Feature activation-1.68e-02

Pos logit contributions
storms+0.123
zed+0.116
 drifted+0.115
 stub+0.115
pill+0.115
Neg logit contributions
ole-0.087
 captain-0.077
bles-0.073
oy-0.072
roc-0.070
Tokenyear
Token ID1941
Feature activation-2.43e-02

Pos logit contributions
 minutes+0.029
 pic+0.027
storms+0.027
pill+0.027
 showers+0.025
Neg logit contributions
 captain-0.024
ole-0.023
hips-0.022
rave-0.022
ble-0.020
Token-
Token ID12
Feature activation-1.35e-02

Pos logit contributions
 minutes+0.037
pill+0.035
 pic+0.035
storms+0.034
 showers+0.032
Neg logit contributions
 captain-0.039
hips-0.037
ole-0.036
rave-0.036
ble-0.035
Tokenolds
Token ID10119
Feature activation+1.75e-02

Pos logit contributions
 minutes+0.021
 pic+0.019
storms+0.019
pill+0.019
 showers+0.018
Neg logit contributions
 captain-0.021
ole-0.021
hips-0.020
rave-0.020
ble-0.018
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
 captain+0.028
ole+0.027
hips+0.027
rave+0.026
ble+0.025
Neg logit contributions
 minutes-0.026
 pic-0.025
pill-0.024
storms-0.024
zed-0.022
Token that
Token ID326
Feature activation+4.23e-03

Pos logit contributions
 pic+0.015
pill+0.015
 minutes+0.015
storms+0.014
 showers+0.014
Neg logit contributions
 captain-0.014
ole-0.014
hips-0.014
rave-0.013
ble-0.012
Token has
Token ID468
Feature activation-4.62e-03

Pos logit contributions
hips+0.006
 captain+0.005
rave+0.005
 guide+0.005
 ring+0.005
Neg logit contributions
 minutes-0.008
 sudden-0.007
storms-0.007
pill-0.007
zed-0.007
Token three
Token ID1115
Feature activation-7.15e-02

Pos logit contributions
storms+0.008
 pic+0.008
 minutes+0.008
pill+0.008
 showers+0.008
Neg logit contributions
 captain-0.006
hips-0.006
ole-0.005
rave-0.005
ble-0.005
Token sides
Token ID5389
Feature activation-2.12e-02

Pos logit contributions
storms+0.124
 pic+0.123
pill+0.114
 showers+0.112
zed+0.108
Neg logit contributions
ole-0.094
 captain-0.091
ble-0.087
bles-0.087
hips-0.084
Token and
Token ID290
Feature activation-1.99e-02

Pos logit contributions
 pic+0.037
 minutes+0.034
pill+0.034
storms+0.034
 showers+0.032
Neg logit contributions
hips-0.031
 captain-0.029
ole-0.028
ble-0.028
rave-0.027
Token three
Token ID1115
Feature activation-7.15e-02

Pos logit contributions
storms+0.034
 pic+0.034
 minutes+0.033
zed+0.032
pill+0.032
Neg logit contributions
 captain-0.025
hips-0.024
rave-0.023
ble-0.021
 ourselves-0.021
Token corners
Token ID14371
Feature activation-1.81e-02

Pos logit contributions
 pic+0.125
storms+0.119
pill+0.109
 showers+0.107
 mornings+0.107
Neg logit contributions
ole-0.093
 captain-0.091
bles-0.090
hips-0.088
rave-0.085
Token.
Token ID13
Feature activation-1.03e-03

Pos logit contributions
 pic+0.030
 minutes+0.028
pill+0.028
storms+0.026
 showers+0.025
Neg logit contributions
hips-0.028
 captain-0.027
ole-0.026
rave-0.026
ble-0.025
Token She
Token ID1375
Feature activation-2.15e-03

Pos logit contributions
 minutes+0.002
pill+0.002
zed+0.002
 pic+0.002
 spilled+0.002
Neg logit contributions
hips-0.001
rave-0.001
 captain-0.001
ole-0.001
 Elliot-0.001
Token says
Token ID1139
Feature activation-5.01e-03

Pos logit contributions
 minutes+0.003
storms+0.003
 pic+0.003
pill+0.003
 showers+0.003
Neg logit contributions
 captain-0.004
hips-0.003
rave-0.003
ole-0.003
ble-0.003
Token,
Token ID11
Feature activation-1.91e-02

Pos logit contributions
 minutes+0.009
pill+0.008
 pic+0.008
storms+0.008
 showers+0.008
Neg logit contributions
 captain-0.007
ole-0.007
hips-0.006
rave-0.006
ble-0.006
Token them
Token ID606
Feature activation-5.36e-03

Pos logit contributions
 captain+0.015
hips+0.015
ole+0.014
rave+0.014
ble+0.013
Neg logit contributions
 minutes-0.014
pill-0.014
 pic-0.013
storms-0.013
 showers-0.012
Token a
Token ID257
Feature activation-5.49e-03

Pos logit contributions
 minutes+0.008
 pic+0.008
pill+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.008
hips-0.008
ole-0.008
rave-0.008
ble-0.007
Token block
Token ID2512
Feature activation-9.43e-03

Pos logit contributions
 minutes+0.009
pill+0.008
 pic+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.009
ole-0.008
hips-0.008
rave-0.008
ble-0.008
Token that
Token ID326
Feature activation+4.23e-03

Pos logit contributions
 pic+0.015
pill+0.015
 minutes+0.015
storms+0.014
 showers+0.014
Neg logit contributions
 captain-0.014
ole-0.014
hips-0.014
rave-0.013
ble-0.012
Token has
Token ID468
Feature activation-4.62e-03

Pos logit contributions
hips+0.006
 captain+0.005
rave+0.005
 guide+0.005
 ring+0.005
Neg logit contributions
 minutes-0.008
 sudden-0.007
storms-0.007
pill-0.007
zed-0.007
Token three
Token ID1115
Feature activation-7.15e-02

Pos logit contributions
storms+0.008
 pic+0.008
 minutes+0.008
pill+0.008
 showers+0.008
Neg logit contributions
 captain-0.006
hips-0.006
ole-0.005
rave-0.005
ble-0.005
Token sides
Token ID5389
Feature activation-2.12e-02

Pos logit contributions
storms+0.124
 pic+0.123
pill+0.114
 showers+0.112
zed+0.108
Neg logit contributions
ole-0.094
 captain-0.091
ble-0.087
bles-0.087
hips-0.084
Token and
Token ID290
Feature activation-1.99e-02

Pos logit contributions
 pic+0.037
 minutes+0.034
pill+0.034
storms+0.034
 showers+0.032
Neg logit contributions
hips-0.031
 captain-0.029
ole-0.028
ble-0.028
rave-0.027
Token three
Token ID1115
Feature activation-7.15e-02

Pos logit contributions
storms+0.034
 pic+0.034
 minutes+0.033
zed+0.032
pill+0.032
Neg logit contributions
 captain-0.025
hips-0.024
rave-0.023
ble-0.021
 ourselves-0.021
Token corners
Token ID14371
Feature activation-1.81e-02

Pos logit contributions
 pic+0.125
storms+0.119
pill+0.109
 showers+0.107
 mornings+0.107
Neg logit contributions
ole-0.093
 captain-0.091
bles-0.090
hips-0.088
rave-0.085
Token.
Token ID13
Feature activation-1.03e-03

Pos logit contributions
 pic+0.030
 minutes+0.028
pill+0.028
storms+0.026
 showers+0.025
Neg logit contributions
hips-0.028
 captain-0.027
ole-0.026
rave-0.026
ble-0.025
Token
Token ID198
Feature activation+4.13e-03

Pos logit contributions
 captain+0.003
ole+0.003
hips+0.003
rave+0.003
ble+0.003
Neg logit contributions
storms-0.002
 minutes-0.002
pill-0.002
 pic-0.002
 showers-0.001
Token"
Token ID1
Feature activation+1.13e-03

Pos logit contributions
hips+0.007
rave+0.007
 captain+0.007
ole+0.006
ble+0.006
Neg logit contributions
 minutes-0.006
pill-0.005
 pic-0.005
 showers-0.005
storms-0.005
TokenMy
Token ID3666
Feature activation-1.39e-02

Pos logit contributions
 captain+0.002
rave+0.002
hips+0.002
ole+0.001
ble+0.001
Neg logit contributions
 minutes-0.002
 pic-0.002
storms-0.002
pill-0.002
zed-0.002
Token car
Token ID1097
Feature activation-7.51e-03

Pos logit contributions
 minutes+0.019
 pic+0.017
storms+0.017
 showers+0.017
pill+0.016
Neg logit contributions
ole-0.023
rave-0.022
hips-0.022
 captain-0.022
ble-0.021
Token has
Token ID468
Feature activation-3.40e-03

Pos logit contributions
 minutes+0.008
storms+0.007
pill+0.007
 pic+0.007
 knocks+0.007
Neg logit contributions
 captain-0.015
ole-0.015
hips-0.014
rave-0.014
ble-0.014
Token three
Token ID1115
Feature activation-7.07e-02

Pos logit contributions
 minutes+0.006
storms+0.006
pill+0.006
 pic+0.005
 showers+0.005
Neg logit contributions
 captain-0.005
hips-0.005
ole-0.004
rave-0.004
ble-0.004
Token wheels
Token ID13666
Feature activation+2.25e-02

Pos logit contributions
storms+0.129
pill+0.122
 pic+0.121
zed+0.111
 minutes+0.110
Neg logit contributions
 captain-0.092
ole-0.088
hips-0.082
bles-0.079
oy-0.077
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
 captain+0.041
ole+0.039
rave+0.039
hips+0.038
roc+0.037
Neg logit contributions
 minutes-0.028
storms-0.025
pill-0.025
 spilled-0.024
 pic-0.023
Token It
Token ID632
Feature activation-7.02e-03

Pos logit contributions
 minutes+0.014
pill+0.013
storms+0.012
 pic+0.012
 showers+0.012
Neg logit contributions
 captain-0.023
ole-0.023
hips-0.022
rave-0.022
ble-0.021
Token is
Token ID318
Feature activation-8.37e-03

Pos logit contributions
 minutes+0.009
pill+0.008
storms+0.008
 pic+0.008
 showers+0.007
Neg logit contributions
 captain-0.013
ole-0.012
hips-0.012
rave-0.012
ble-0.012
Token light
Token ID1657
Feature activation-4.15e-03

Pos logit contributions
 minutes+0.012
 pic+0.011
storms+0.011
pill+0.011
 showers+0.010
Neg logit contributions
 captain-0.014
ole-0.013
rave-0.013
hips-0.013
ble-0.012
Token few
Token ID1178
Feature activation-3.18e-02

Pos logit contributions
 minutes+0.027
storms+0.025
 pic+0.025
pill+0.025
 showers+0.024
Neg logit contributions
ole-0.020
 captain-0.019
hips-0.019
rave-0.019
ble-0.018
Token days
Token ID1528
Feature activation-9.69e-03

Pos logit contributions
storms+0.051
 stub+0.044
pill+0.044
 pic+0.043
iche+0.043
Neg logit contributions
ole-0.041
 captain-0.039
 guard-0.038
 luck-0.038
 prisoners-0.037
Token,
Token ID11
Feature activation-4.69e-03

Pos logit contributions
 minutes+0.016
pill+0.016
 pic+0.016
storms+0.016
 showers+0.016
Neg logit contributions
ole-0.012
hips-0.012
 captain-0.012
ble-0.011
rave-0.011
Token that
Token ID326
Feature activation+5.17e-03

Pos logit contributions
storms+0.008
pill+0.008
 minutes+0.007
 pic+0.007
zed+0.007
Neg logit contributions
 captain-0.006
hips-0.006
rave-0.006
ole-0.006
 himself-0.005
Token her
Token ID607
Feature activation-2.46e-02

Pos logit contributions
 captain+0.008
hips+0.007
rave+0.007
ble+0.007
ole+0.007
Neg logit contributions
 minutes-0.008
pill-0.007
storms-0.007
 pic-0.007
ud-0.006
Token three
Token ID1115
Feature activation-7.05e-02

Pos logit contributions
 minutes+0.042
pill+0.042
storms+0.041
 pic+0.039
 showers+0.037
Neg logit contributions
 captain-0.034
ole-0.032
rave-0.031
hips-0.030
ble-0.030
Token year
Token ID614
Feature activation-1.63e-02

Pos logit contributions
storms+0.126
pill+0.119
 pic+0.117
 Grad+0.112
 showers+0.108
Neg logit contributions
ole-0.093
 captain-0.078
oy-0.074
 promise-0.073
 guard-0.072
Token old
Token ID1468
Feature activation+6.13e-03

Pos logit contributions
 minutes+0.029
 pic+0.027
pill+0.027
storms+0.027
 showers+0.025
Neg logit contributions
 captain-0.022
ole-0.021
hips-0.021
rave-0.020
ble-0.019
Token daughter
Token ID4957
Feature activation-3.12e-02

Pos logit contributions
 captain+0.011
ole+0.010
rave+0.010
hips+0.010
ble+0.009
Neg logit contributions
 minutes-0.008
pill-0.008
 pic-0.008
storms-0.008
 showers-0.007
Token's
Token ID338
Feature activation-9.90e-03

Pos logit contributions
 minutes+0.046
pill+0.044
 pic+0.044
storms+0.043
 showers+0.041
Neg logit contributions
 captain-0.050
ole-0.047
hips-0.045
rave-0.045
 chest-0.042
Token stomach
Token ID11384
Feature activation-2.53e-02

Pos logit contributions
 minutes+0.017
pill+0.017
 pic+0.017
storms+0.017
 showers+0.015
Neg logit contributions
 captain-0.013
ole-0.013
hips-0.012
rave-0.012
ble-0.011
Token was
Token ID373
Feature activation-4.14e-03

Pos logit contributions
 minutes+0.026
pill+0.024
storms+0.023
 pic+0.023
 showers+0.022
Neg logit contributions
 captain-0.016
ole-0.016
hips-0.015
ble-0.015
rave-0.015
Token tough
Token ID5802
Feature activation+1.61e-02

Pos logit contributions
 minutes+0.007
storms+0.007
pill+0.007
 pic+0.007
 showers+0.006
Neg logit contributions
 captain-0.006
ole-0.006
hips-0.005
rave-0.005
ble-0.005
Token,
Token ID11
Feature activation-7.14e-03

Pos logit contributions
 captain+0.021
ole+0.019
rave+0.019
hips+0.018
ble+0.017
Neg logit contributions
 minutes-0.027
pill-0.027
zed-0.026
 pic-0.026
storms-0.026
Token like
Token ID588
Feature activation-1.39e-02

Pos logit contributions
pill+0.013
 minutes+0.013
storms+0.012
 spills+0.012
 happens+0.012
Neg logit contributions
 captain-0.008
ble-0.007
hips-0.007
rave-0.007
ole-0.007
Token all
Token ID477
Feature activation-9.47e-03

Pos logit contributions
 minutes+0.024
pill+0.022
storms+0.022
ud+0.021
 pic+0.021
Neg logit contributions
 captain-0.019
rave-0.017
hips-0.016
ter-0.015
 himself-0.015
Token three
Token ID1115
Feature activation-6.98e-02

Pos logit contributions
 minutes+0.018
 sudden+0.017
 pic+0.017
storms+0.017
pill+0.016
Neg logit contributions
ole-0.010
 captain-0.009
hips-0.009
rave-0.009
jack-0.008
Token year
Token ID614
Feature activation-2.00e-02

Pos logit contributions
storms+0.132
 Grad+0.125
storm+0.125
zed+0.125
 drifted+0.122
Neg logit contributions
ole-0.070
bles-0.065
ies-0.065
oy-0.059
 captain-0.059
Token olds
Token ID44979
Feature activation-3.05e-05

Pos logit contributions
 minutes+0.036
 pic+0.035
storms+0.035
pill+0.034
zed+0.032
Neg logit contributions
ole-0.025
 captain-0.025
hips-0.024
rave-0.023
ble-0.021
Token.
Token ID13
Feature activation-5.53e-03

Pos logit contributions
 minutes+0.000
 pic+0.000
pill+0.000
storms+0.000
zed+0.000
Neg logit contributions
 captain-0.000
hips-0.000
ole-0.000
rave-0.000
ble-0.000
Token One
Token ID1881
Feature activation-1.15e-02

Pos logit contributions
 minutes+0.009
zed+0.008
 spilled+0.008
 pic+0.008
pill+0.008
Neg logit contributions
hips-0.008
ole-0.008
 captain-0.008
rave-0.007
 Elliot-0.007
Token day
Token ID1110
Feature activation-1.74e-03

Pos logit contributions
pill+0.017
storms+0.016
 minutes+0.016
 pic+0.015
 knocks+0.013
Neg logit contributions
 captain-0.019
ole-0.019
ble-0.017
rave-0.017
 promise-0.016
Token�
Token ID95
Feature activation+2.26e-02

Pos logit contributions
 captain+0.030
ole+0.028
hips+0.028
rave+0.028
ble+0.026
Neg logit contributions
 minutes-0.033
 pic-0.030
pill-0.030
storms-0.030
 showers-0.028
Token€
Token ID26391
Feature activation+3.41e-03

Pos logit contributions
 captain+0.033
rave+0.032
ole+0.031
hips+0.031
ble+0.029
Neg logit contributions
 minutes-0.036
 pic-0.035
pill-0.034
storms-0.034
 spilled-0.033
Token�
Token ID129
Feature activation-1.41e-03

Pos logit contributions
 captain+0.005
rave+0.005
hips+0.005
ole+0.005
oy+0.005
Neg logit contributions
 minutes-0.005
pill-0.004
 spilled-0.004
 showers-0.004
 pic-0.004
Token�
Token ID241
Feature activation+1.30e-02

Pos logit contributions
 minutes+0.002
pill+0.002
 pic+0.002
storms+0.002
 spilled+0.002
Neg logit contributions
 captain-0.002
hips-0.002
rave-0.002
ole-0.002
ble-0.002
TokenUsually
Token ID37887
Feature activation-2.14e-03

Pos logit contributions
 captain+0.020
ole+0.019
rave+0.019
ble+0.019
hips+0.019
Neg logit contributions
 minutes-0.019
storms-0.018
 pic-0.018
pill-0.017
 spilled-0.017
Token three
Token ID1115
Feature activation-6.97e-02

Pos logit contributions
 minutes+0.004
storms+0.004
 pic+0.004
pill+0.004
 showers+0.003
Neg logit contributions
 captain-0.003
hips-0.003
ole-0.003
rave-0.003
ble-0.003
Token eggs
Token ID9653
Feature activation+1.23e-02

Pos logit contributions
storms+0.126
 stub+0.112
 spilled+0.111
 pic+0.110
pill+0.108
Neg logit contributions
ole-0.089
 captain-0.082
oy-0.073
bles-0.072
hips-0.071
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
 captain+0.017
hips+0.016
ole+0.016
rave+0.016
ble+0.015
Neg logit contributions
 minutes-0.021
 pic-0.020
pill-0.020
storms-0.020
 showers-0.019
Token but
Token ID475
Feature activation+1.47e-02

Pos logit contributions
 minutes+0.021
storms+0.020
pill+0.020
 pic+0.020
 spilled+0.018
Neg logit contributions
 captain-0.020
hips-0.019
ole-0.018
rave-0.018
ble-0.017
Token this
Token ID428
Feature activation-2.08e-02

Pos logit contributions
 captain+0.022
ole+0.021
hips+0.021
rave+0.021
ble+0.020
Neg logit contributions
 minutes-0.023
 pic-0.022
pill-0.022
storms-0.022
 showers-0.020
Token time
Token ID640
Feature activation+4.28e-03

Pos logit contributions
storms+0.036
pill+0.035
 showers+0.033
 minutes+0.031
 pic+0.031
Neg logit contributions
 captain-0.026
ole-0.026
 promise-0.026
 luck-0.023
rave-0.023
Token It
Token ID632
Feature activation-2.66e-03

Pos logit contributions
 minutes+0.026
 pic+0.024
storms+0.023
pill+0.023
 spilled+0.022
Neg logit contributions
 captain-0.030
hips-0.029
ole-0.028
rave-0.028
ble-0.027
Token has
Token ID468
Feature activation-1.24e-02

Pos logit contributions
 minutes+0.004
 pic+0.004
storms+0.003
pill+0.003
 showers+0.003
Neg logit contributions
 captain-0.004
hips-0.004
rave-0.004
ole-0.004
ble-0.004
Token three
Token ID1115
Feature activation-7.46e-02

Pos logit contributions
storms+0.023
 minutes+0.022
 pic+0.022
pill+0.021
zed+0.021
Neg logit contributions
 captain-0.016
hips-0.015
ole-0.014
rave-0.013
 luck-0.013
Token sides
Token ID5389
Feature activation-1.86e-02

Pos logit contributions
storms+0.138
 pic+0.129
zed+0.123
pill+0.122
 showers+0.122
Neg logit contributions
ole-0.091
 captain-0.088
bles-0.084
ble-0.081
oy-0.079
Token and
Token ID290
Feature activation-1.98e-02

Pos logit contributions
 minutes+0.029
 pic+0.028
pill+0.028
storms+0.028
 showers+0.026
Neg logit contributions
 captain-0.028
hips-0.027
ole-0.027
rave-0.026
ble-0.025
Token three
Token ID1115
Feature activation-6.94e-02

Pos logit contributions
storms+0.033
 pic+0.033
 minutes+0.033
zed+0.031
pill+0.031
Neg logit contributions
 captain-0.027
hips-0.025
rave-0.024
ble-0.024
 ourselves-0.023
Token corners
Token ID14371
Feature activation-1.28e-02

Pos logit contributions
storms+0.121
 pic+0.119
pill+0.111
zed+0.108
 showers+0.107
Neg logit contributions
 captain-0.090
ole-0.090
bles-0.084
hips-0.083
ble-0.081
Token.
Token ID13
Feature activation-9.27e-03

Pos logit contributions
 minutes+0.018
 pic+0.017
pill+0.016
storms+0.016
 showers+0.015
Neg logit contributions
 captain-0.022
hips-0.021
ole-0.021
rave-0.021
ble-0.020
Token Can
Token ID1680
Feature activation-4.54e-03

Pos logit contributions
 minutes+0.014
 pic+0.013
storms+0.013
pill+0.013
 spilled+0.012
Neg logit contributions
 captain-0.015
hips-0.015
rave-0.014
ole-0.014
ble-0.013
Token you
Token ID345
Feature activation+1.54e-02

Pos logit contributions
 minutes+0.005
pill+0.005
storms+0.005
 pic+0.005
 showers+0.005
Neg logit contributions
 captain-0.008
ole-0.008
hips-0.008
rave-0.008
ble-0.008
Token make
Token ID787
Feature activation-9.31e-04

Pos logit contributions
ole+0.024
rave+0.023
hips+0.023
 captain+0.022
bles+0.021
Neg logit contributions
 minutes-0.021
 mixes-0.018
 pic-0.018
 spilled-0.018
 time-0.018
Token looks
Token ID3073
Feature activation-3.41e-03

Pos logit contributions
 minutes+0.001
 pic+0.001
pill+0.001
storms+0.001
 showers+0.001
Neg logit contributions
 captain-0.001
ole-0.001
hips-0.001
rave-0.001
ble-0.001
Token like
Token ID588
Feature activation-1.08e-02

Pos logit contributions
 minutes+0.005
 pic+0.005
storms+0.005
pill+0.005
 showers+0.004
Neg logit contributions
 captain-0.006
hips-0.005
ole-0.005
rave-0.005
ble-0.005
Token the
Token ID262
Feature activation-5.71e-03

Pos logit contributions
 minutes+0.018
storms+0.018
pill+0.018
 pic+0.017
zed+0.017
Neg logit contributions
 captain-0.015
hips-0.013
ole-0.013
rave-0.013
ble-0.012
Token brick
Token ID17214
Feature activation-1.79e-02

Pos logit contributions
 minutes+0.009
 pic+0.008
storms+0.008
pill+0.008
 showers+0.008
Neg logit contributions
 captain-0.008
hips-0.008
ole-0.008
rave-0.008
ble-0.008
Token weighs
Token ID24034
Feature activation-5.45e-03

Pos logit contributions
 minutes+0.031
 pic+0.030
pill+0.029
storms+0.029
 showers+0.028
Neg logit contributions
 captain-0.024
ole-0.023
hips-0.023
rave-0.022
ble-0.021
Token three
Token ID1115
Feature activation-6.91e-02

Pos logit contributions
 minutes+0.010
pill+0.009
 pic+0.009
storms+0.009
 showers+0.008
Neg logit contributions
 captain-0.007
hips-0.007
ole-0.007
rave-0.007
ble-0.006
Token pounds
Token ID8059
Feature activation+3.39e-05

Pos logit contributions
storms+0.124
pill+0.116
 pic+0.115
 spilled+0.111
 showers+0.111
Neg logit contributions
ole-0.091
 captain-0.086
hips-0.077
rave-0.077
ble-0.077
Token,"
Token ID553
Feature activation-1.69e-02

Pos logit contributions
 captain+0.000
hips+0.000
rave+0.000
ole+0.000
ble+0.000
Neg logit contributions
 minutes-0.000
pill-0.000
storms-0.000
 pic-0.000
 showers-0.000
Token Lucy
Token ID22162
Feature activation-1.14e-02

Pos logit contributions
 minutes+0.022
 pic+0.020
pill+0.020
storms+0.020
 showers+0.018
Neg logit contributions
 captain-0.030
ole-0.029
rave-0.029
hips-0.029
ble-0.027
Token said
Token ID531
Feature activation+1.14e-02

Pos logit contributions
 minutes+0.015
pill+0.014
 pic+0.014
storms+0.014
 showers+0.013
Neg logit contributions
 captain-0.020
hips-0.020
ole-0.019
rave-0.019
ble-0.018
Token.
Token ID13
Feature activation+8.51e-03

Pos logit contributions
 captain+0.021
hips+0.021
ole+0.020
rave+0.020
ble+0.019
Neg logit contributions
 minutes-0.014
storms-0.013
pill-0.012
 pic-0.012
 showers-0.011
Token is
Token ID318
Feature activation+1.88e-03

Pos logit contributions
 minutes+0.012
pill+0.011
 pic+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.014
ole-0.013
hips-0.013
rave-0.013
ble-0.012
Token a
Token ID257
Feature activation+4.72e-03

Pos logit contributions
 captain+0.003
ole+0.003
rave+0.002
ble+0.002
hips+0.002
Neg logit contributions
 minutes-0.003
pill-0.003
storms-0.003
 pic-0.003
 showers-0.003
Token special
Token ID2041
Feature activation+1.31e-02

Pos logit contributions
 captain+0.007
ole+0.007
rave+0.006
hips+0.006
ble+0.006
Neg logit contributions
 minutes-0.008
pill-0.008
storms-0.007
 pic-0.007
 showers-0.007
Token tool
Token ID2891
Feature activation+2.30e-02

Pos logit contributions
 captain+0.021
ole+0.019
hips+0.019
rave+0.019
ble+0.018
Neg logit contributions
 minutes-0.020
pill-0.019
 pic-0.019
storms-0.019
 showers-0.018
Token with
Token ID351
Feature activation+5.76e-03

Pos logit contributions
 captain+0.034
ole+0.032
hips+0.031
rave+0.030
ble+0.030
Neg logit contributions
 minutes-0.038
pill-0.037
 pic-0.037
storms-0.036
 showers-0.034
Token three
Token ID1115
Feature activation-6.89e-02

Pos logit contributions
 captain+0.008
ole+0.008
hips+0.008
rave+0.007
ble+0.007
Neg logit contributions
storms-0.010
 minutes-0.009
pill-0.009
 pic-0.009
 showers-0.008
Token points
Token ID2173
Feature activation-1.10e-03

Pos logit contributions
storms+0.121
pill+0.111
 pic+0.111
 showers+0.100
 drifted+0.098
Neg logit contributions
ole-0.093
 captain-0.093
ble-0.084
rave-0.082
bles-0.081
Token,
Token ID11
Feature activation-8.13e-03

Pos logit contributions
 minutes+0.002
pill+0.002
 pic+0.002
storms+0.002
 showers+0.001
Neg logit contributions
 captain-0.002
ole-0.002
hips-0.002
rave-0.002
ble-0.002
Token like
Token ID588
Feature activation-1.64e-02

Pos logit contributions
 minutes+0.012
pill+0.011
storms+0.011
 pic+0.011
 showers+0.010
Neg logit contributions
 captain-0.013
ole-0.012
hips-0.012
rave-0.012
ble-0.012
Token a
Token ID257
Feature activation-1.09e-02

Pos logit contributions
storms+0.029
 minutes+0.028
pill+0.028
 pic+0.027
zed+0.026
Neg logit contributions
 captain-0.022
hips-0.019
rave-0.019
ble-0.019
ole-0.019
Token star
Token ID3491
Feature activation-2.09e-02

Pos logit contributions
 minutes+0.017
pill+0.017
storms+0.017
 pic+0.017
 showers+0.016
Neg logit contributions
 captain-0.017
ole-0.015
hips-0.015
rave-0.015
ble-0.015
Token marked
Token ID7498
Feature activation-1.84e-02

Pos logit contributions
pill+0.021
 pic+0.020
 showers+0.019
storms+0.018
 Grad+0.017
Neg logit contributions
 guard-0.014
 captain-0.014
 promise-0.013
jack-0.013
 hero-0.013
Token it
Token ID340
Feature activation-6.77e-03

Pos logit contributions
 minutes+0.030
pill+0.030
 pic+0.029
storms+0.029
 showers+0.027
Neg logit contributions
 captain-0.027
ole-0.026
hips-0.026
rave-0.025
ble-0.025
Token quite
Token ID2407
Feature activation-9.35e-03

Pos logit contributions
pill+0.012
 pic+0.012
 minutes+0.012
storms+0.011
 showers+0.011
Neg logit contributions
ole-0.009
hips-0.009
 captain-0.009
ble-0.009
rave-0.009
Token like
Token ID588
Feature activation-1.07e-02

Pos logit contributions
pill+0.016
 pic+0.015
 minutes+0.015
storms+0.015
 showers+0.014
Neg logit contributions
 captain-0.013
ole-0.013
hips-0.013
ble-0.013
rave-0.013
Token the
Token ID262
Feature activation+9.85e-04

Pos logit contributions
pill+0.019
 minutes+0.018
storms+0.018
 pic+0.017
zed+0.016
Neg logit contributions
 captain-0.015
hips-0.013
ole-0.012
ble-0.012
rave-0.012
Token three
Token ID1115
Feature activation-6.89e-02

Pos logit contributions
 captain+0.001
ole+0.001
hips+0.001
rave+0.001
ble+0.001
Neg logit contributions
 minutes-0.002
 pic-0.002
pill-0.002
storms-0.002
 showers-0.001
Token year
Token ID614
Feature activation-2.05e-02

Pos logit contributions
storms+0.130
pill+0.124
 pic+0.122
 Grad+0.110
 showers+0.108
Neg logit contributions
 captain-0.088
ole-0.085
ble-0.074
 guard-0.074
bles-0.071
Token old
Token ID1468
Feature activation-7.01e-03

Pos logit contributions
 minutes+0.036
 pic+0.036
pill+0.036
storms+0.035
 showers+0.033
Neg logit contributions
ole-0.026
 captain-0.026
hips-0.024
rave-0.024
ble-0.022
Token.
Token ID13
Feature activation-6.09e-03

Pos logit contributions
pill+0.010
 minutes+0.010
 pic+0.010
storms+0.009
 showers+0.009
Neg logit contributions
 captain-0.012
ole-0.011
hips-0.010
rave-0.010
ble-0.010
Token She
Token ID1375
Feature activation-2.30e-03

Pos logit contributions
 minutes+0.010
 pic+0.009
 spilled+0.009
pill+0.008
zed+0.008
Neg logit contributions
 captain-0.009
ole-0.009
hips-0.009
rave-0.009
roc-0.008
Token marked
Token ID7498
Feature activation-6.31e-03

Pos logit contributions
 minutes+0.004
 pic+0.003
pill+0.003
storms+0.003
 showers+0.003
Neg logit contributions
 captain-0.004
rave-0.003
ble-0.003
ole-0.003
 promise-0.003
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
 captain+0.007
hips+0.007
ole+0.007
rave+0.007
ble+0.007
Neg logit contributions
 minutes-0.006
pill-0.005
 pic-0.005
storms-0.005
 showers-0.005
Token It
Token ID632
Feature activation-4.80e-03

Pos logit contributions
 minutes+0.021
pill+0.020
 pic+0.020
storms+0.020
 showers+0.018
Neg logit contributions
 captain-0.029
ole-0.028
hips-0.027
rave-0.027
ble-0.026
Token is
Token ID318
Feature activation-1.03e-02

Pos logit contributions
 minutes+0.007
 pic+0.006
storms+0.006
pill+0.006
 showers+0.006
Neg logit contributions
 captain-0.008
hips-0.008
ole-0.008
rave-0.008
ble-0.007
Token more
Token ID517
Feature activation-7.56e-03

Pos logit contributions
 minutes+0.016
 pic+0.015
pill+0.014
storms+0.014
 showers+0.013
Neg logit contributions
 captain-0.016
ole-0.015
hips-0.015
rave-0.015
ble-0.014
Token than
Token ID621
Feature activation+1.54e-02

Pos logit contributions
 minutes+0.010
 pic+0.010
pill+0.009
storms+0.009
 showers+0.009
Neg logit contributions
 captain-0.013
ole-0.013
hips-0.013
rave-0.012
ble-0.012
Token three
Token ID1115
Feature activation-6.88e-02

Pos logit contributions
 captain+0.019
ole+0.018
hips+0.018
rave+0.017
ble+0.017
Neg logit contributions
 minutes-0.028
pill-0.028
storms-0.028
 pic-0.027
 showers-0.026
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
storms+0.126
 pic+0.118
zed+0.116
pill+0.112
 drifted+0.111
Neg logit contributions
ole-0.088
 captain-0.084
bles-0.079
hips-0.077
oy-0.075
Token It
Token ID632
Feature activation-3.27e-03

Pos logit contributions
 minutes+0.018
 pic+0.016
storms+0.016
pill+0.016
 spilled+0.016
Neg logit contributions
 captain-0.021
hips-0.020
rave-0.019
ole-0.019
ble-0.018
Token is
Token ID318
Feature activation-7.16e-03

Pos logit contributions
 minutes+0.005
 pic+0.004
storms+0.004
pill+0.004
 showers+0.004
Neg logit contributions
 captain-0.006
hips-0.005
rave-0.005
ole-0.005
ble-0.005
Token like
Token ID588
Feature activation-1.85e-02

Pos logit contributions
 minutes+0.011
 pic+0.010
pill+0.010
storms+0.010
 showers+0.009
Neg logit contributions
 captain-0.011
ole-0.011
hips-0.011
rave-0.011
ble-0.010
Token three
Token ID1115
Feature activation-6.49e-02

Pos logit contributions
 minutes+0.032
storms+0.032
pill+0.031
 pic+0.031
zed+0.029
Neg logit contributions
 captain-0.025
hips-0.023
ole-0.023
rave-0.023
ble-0.021
Token happy
Token ID3772
Feature activation+2.02e-02

Pos logit contributions
 minutes+0.011
 pic+0.010
pill+0.010
storms+0.010
 spilled+0.009
Neg logit contributions
 captain-0.012
hips-0.012
rave-0.012
ole-0.012
ble-0.011
Token and
Token ID290
Feature activation+3.61e-03

Pos logit contributions
 captain+0.028
ole+0.025
ble+0.025
rave+0.024
hips+0.024
Neg logit contributions
pill-0.034
 minutes-0.034
 pic-0.033
 showers-0.032
storms-0.031
Token it
Token ID340
Feature activation-2.23e-03

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.006
rave+0.006
ble+0.006
Neg logit contributions
 minutes-0.005
pill-0.005
storms-0.005
 pic-0.005
 showers-0.004
Token used
Token ID973
Feature activation+4.38e-04

Pos logit contributions
 minutes+0.004
 pic+0.003
 showers+0.003
pill+0.003
storms+0.003
Neg logit contributions
 captain-0.004
rave-0.003
ble-0.003
boat-0.003
ole-0.003
Token all
Token ID477
Feature activation-4.62e-03

Pos logit contributions
 captain+0.001
ole+0.001
hips+0.001
rave+0.001
ble+0.000
Neg logit contributions
 minutes-0.001
pill-0.001
storms-0.001
 pic-0.001
 showers-0.001
Token three
Token ID1115
Feature activation-6.88e-02

Pos logit contributions
 minutes+0.009
storms+0.009
 pic+0.008
pill+0.008
 showers+0.008
Neg logit contributions
ole-0.005
 captain-0.005
hips-0.005
rave-0.005
ble-0.004
Token wings
Token ID12098
Feature activation-1.34e-02

Pos logit contributions
storms+0.122
 pic+0.107
storm+0.106
 knocks+0.105
 minutes+0.104
Neg logit contributions
ole-0.089
 captain-0.075
rave-0.074
hips-0.074
bles-0.074
Token to
Token ID284
Feature activation-6.51e-03

Pos logit contributions
 minutes+0.020
 pic+0.019
pill+0.018
storms+0.018
 showers+0.017
Neg logit contributions
 captain-0.022
hips-0.021
ole-0.021
rave-0.021
ble-0.020
Token fly
Token ID6129
Feature activation-1.52e-03

Pos logit contributions
 minutes+0.012
 pic+0.011
pill+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.008
ole-0.008
hips-0.008
rave-0.008
ble-0.007
Token around
Token ID1088
Feature activation+4.80e-03

Pos logit contributions
 minutes+0.003
pill+0.002
 pic+0.002
storms+0.002
 showers+0.002
Neg logit contributions
 captain-0.002
ole-0.002
hips-0.002
rave-0.002
ble-0.002
Token the
Token ID262
Feature activation+6.70e-03

Pos logit contributions
 captain+0.006
ole+0.006
hips+0.006
rave+0.006
ble+0.005
Neg logit contributions
 minutes-0.009
pill-0.008
 pic-0.008
storms-0.008
 showers-0.008
Token had
Token ID550
Feature activation+7.83e-03

Pos logit contributions
 minutes+0.004
 showers+0.004
 pic+0.004
storms+0.004
pill+0.004
Neg logit contributions
 captain-0.005
rave-0.005
ole-0.005
ble-0.005
hips-0.005
Token flown
Token ID22371
Feature activation-2.27e-03

Pos logit contributions
 captain+0.012
rave+0.011
ole+0.011
hips+0.011
ble+0.010
Neg logit contributions
pill-0.012
storms-0.012
 minutes-0.012
 pic-0.011
 showers-0.011
Token as
Token ID355
Feature activation+2.75e-02

Pos logit contributions
 minutes+0.004
 pic+0.003
storms+0.003
pill+0.003
 showers+0.003
Neg logit contributions
 captain-0.003
hips-0.003
ole-0.003
rave-0.003
ble-0.003
Token far
Token ID1290
Feature activation+3.71e-03

Pos logit contributions
 captain+0.044
hips+0.042
ole+0.042
rave+0.041
ble+0.038
Neg logit contributions
 minutes-0.042
 pic-0.039
storms-0.038
pill-0.038
 showers-0.036
Token as
Token ID355
Feature activation+1.57e-02

Pos logit contributions
 captain+0.005
rave+0.005
hips+0.005
ole+0.005
ble+0.004
Neg logit contributions
 minutes-0.007
storms-0.006
 pic-0.006
pill-0.006
 showers-0.006
Token three
Token ID1115
Feature activation-6.87e-02

Pos logit contributions
 captain+0.023
ole+0.022
hips+0.022
rave+0.021
ble+0.020
Neg logit contributions
 minutes-0.026
pill-0.025
 pic-0.025
storms-0.024
 showers-0.023
Token days
Token ID1528
Feature activation-2.29e-02

Pos logit contributions
storms+0.102
iche+0.091
pill+0.090
 pic+0.088
 spilled+0.088
Neg logit contributions
 captain-0.102
oy-0.095
ole-0.093
 himself-0.092
 luck-0.091
Token of
Token ID286
Feature activation-1.86e-02

Pos logit contributions
 minutes+0.036
 pic+0.036
pill+0.035
storms+0.034
 showers+0.034
Neg logit contributions
 captain-0.032
ole-0.032
hips-0.031
rave-0.029
ble-0.029
Token walking
Token ID6155
Feature activation-2.43e-02

Pos logit contributions
storms+0.034
pill+0.033
 minutes+0.032
 pic+0.031
 spilled+0.030
Neg logit contributions
 captain-0.023
hips-0.021
ole-0.020
 himself-0.019
rave-0.019
Token.
Token ID13
Feature activation-2.37e-03

Pos logit contributions
 minutes+0.028
storms+0.026
 pic+0.025
pill+0.025
 showers+0.023
Neg logit contributions
 captain-0.047
rave-0.046
hips-0.045
ole-0.044
ble-0.043
Token Everyone
Token ID11075
Feature activation-9.29e-03

Pos logit contributions
 minutes+0.004
storms+0.003
 showers+0.003
 pic+0.003
pill+0.003
Neg logit contributions
 captain-0.004
ole-0.004
rave-0.004
hips-0.004
jack-0.003
Token what
Token ID644
Feature activation-8.71e-04

Pos logit contributions
 minutes+0.004
pill+0.004
 pic+0.004
storms+0.004
 showers+0.003
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.004
rave-0.003
ble-0.003
Token he
Token ID339
Feature activation+1.51e-02

Pos logit contributions
 minutes+0.002
pill+0.001
storms+0.001
 pic+0.001
 showers+0.001
Neg logit contributions
 captain-0.001
ole-0.001
hips-0.001
rave-0.001
ble-0.001
Token did
Token ID750
Feature activation+2.27e-02

Pos logit contributions
 captain+0.026
rave+0.024
ole+0.024
hips+0.023
ble+0.023
Neg logit contributions
 minutes-0.021
storms-0.020
pill-0.020
 pic-0.019
 showers-0.019
Token!
Token ID0
Feature activation-2.80e-03

Pos logit contributions
 captain+0.040
ole+0.038
hips+0.038
rave+0.037
ble+0.036
Neg logit contributions
 minutes-0.031
pill-0.029
 pic-0.029
storms-0.029
 showers-0.026
Token<|endoftext|>
Token ID50256
Feature activation-1.15e-02

Pos logit contributions
 minutes+0.004
 pic+0.004
storms+0.004
 spilled+0.004
pill+0.003
Neg logit contributions
 captain-0.005
ole-0.005
rave-0.004
hips-0.004
 Elliot-0.004
TokenMrs
Token ID27034
Feature activation+5.44e-02

Pos logit contributions
 minutes+0.016
storms+0.014
pill+0.014
 pic+0.013
 showers+0.013
Neg logit contributions
ole-0.019
rave-0.019
hips-0.019
 captain-0.018
ble-0.018
Token Jones
Token ID5437
Feature activation+1.54e-02

Pos logit contributions
 captain+0.113
hips+0.108
rave+0.107
ole+0.103
ble+0.099
Neg logit contributions
 minutes-0.056
 pic-0.056
storms-0.055
pill-0.055
 spilled-0.047
Token had
Token ID550
Feature activation+2.35e-02

Pos logit contributions
 captain+0.023
ole+0.021
hips+0.020
rave+0.020
 chest+0.019
Neg logit contributions
 minutes-0.025
 showers-0.023
pill-0.023
 pic-0.022
storms-0.022
Token a
Token ID257
Feature activation+1.42e-02

Pos logit contributions
 captain+0.028
ole+0.024
rave+0.024
hips+0.022
 luck+0.021
Neg logit contributions
storms-0.046
pill-0.045
 minutes-0.042
 showers-0.041
 pic-0.039
Token big
Token ID1263
Feature activation+1.47e-02

Pos logit contributions
 captain+0.022
ole+0.021
hips+0.020
rave+0.020
ble+0.019
Neg logit contributions
 minutes-0.022
storms-0.021
pill-0.021
 pic-0.020
 showers-0.019
Token problem
Token ID1917
Feature activation+4.09e-02

Pos logit contributions
hips+0.023
 captain+0.023
rave+0.022
ole+0.022
ble+0.022
Neg logit contributions
 minutes-0.023
 pic-0.021
pill-0.020
storms-0.020
 showers-0.020
Token
Token ID198
Feature activation+6.25e-03

Pos logit contributions
 sir+0.002
 captain+0.002
ole+0.002
 upon+0.002
 name+0.002
Neg logit contributions
zed-0.004
storms-0.003
 minutes-0.003
storm-0.003
 pic-0.003
Token
Token ID198
Feature activation+7.83e-03

Pos logit contributions
ble+0.010
ole+0.010
 captain+0.010
hips+0.010
rave+0.010
Neg logit contributions
storms-0.009
 minutes-0.009
pill-0.008
 pic-0.007
 showers-0.007
TokenThey
Token ID2990
Feature activation+1.40e-02

Pos logit contributions
 captain+0.015
hips+0.014
rave+0.014
ole+0.014
ble+0.013
Neg logit contributions
 minutes-0.010
 pic-0.009
pill-0.009
storms-0.008
 showers-0.008
Token put
Token ID1234
Feature activation-4.97e-03

Pos logit contributions
 captain+0.027
ole+0.025
rave+0.025
hips+0.025
ble+0.024
Neg logit contributions
pill-0.017
 minutes-0.017
storms-0.017
 pic-0.016
 showers-0.015
Token the
Token ID262
Feature activation+1.55e-03

Pos logit contributions
 minutes+0.008
pill+0.008
 pic+0.007
storms+0.007
 showers+0.007
Neg logit contributions
 captain-0.007
ole-0.007
hips-0.007
rave-0.007
ble-0.007
Token pizz
Token ID38748
Feature activation+7.22e-02

Pos logit contributions
 captain+0.003
hips+0.003
rave+0.003
ole+0.003
ble+0.003
Neg logit contributions
 minutes-0.002
 pic-0.002
pill-0.002
storms-0.002
 spilled-0.002
Tokenas
Token ID292
Feature activation+1.74e-02

Pos logit contributions
 avail+0.129
 Elliot+0.128
 captain+0.125
 rightful+0.122
 Crane+0.119
Neg logit contributions
 minutes-0.077
pill-0.067
pler-0.066
itt-0.063
hes-0.062
Token in
Token ID287
Feature activation+1.29e-03

Pos logit contributions
 captain+0.027
hips+0.027
roc+0.027
rave+0.026
ole+0.025
Neg logit contributions
 minutes-0.024
 spilled-0.022
 pic-0.021
storms-0.021
 showers-0.021
Token the
Token ID262
Feature activation+2.40e-03

Pos logit contributions
 captain+0.002
hips+0.002
rave+0.002
ole+0.002
ble+0.002
Neg logit contributions
 minutes-0.002
 pic-0.002
 spilled-0.001
pill-0.001
 showers-0.001
Token oven
Token ID14361
Feature activation+2.79e-02

Pos logit contributions
 captain+0.005
ole+0.005
hips+0.004
rave+0.004
 chest+0.004
Neg logit contributions
storms-0.003
pill-0.003
 minutes-0.003
 pic-0.003
 showers-0.002
Token and
Token ID290
Feature activation+5.74e-03

Pos logit contributions
 captain+0.034
ole+0.032
hips+0.032
 chest+0.030
rave+0.030
Neg logit contributions
pill-0.056
 pic-0.050
storms-0.049
 showers-0.049
 minutes-0.048
Token wanted
Token ID2227
Feature activation-6.38e-03

Pos logit contributions
 captain+0.022
rave+0.020
hips+0.020
ole+0.020
ble+0.019
Neg logit contributions
 minutes-0.016
storms-0.016
pill-0.016
 pic-0.015
 showers-0.015
Token them
Token ID606
Feature activation+1.09e-02

Pos logit contributions
pill+0.011
 minutes+0.011
storms+0.011
 pic+0.010
zed+0.010
Neg logit contributions
 captain-0.008
ole-0.008
hips-0.007
rave-0.007
 himself-0.007
Token both
Token ID1111
Feature activation-2.49e-03

Pos logit contributions
 captain+0.022
hips+0.021
rave+0.021
ole+0.021
roc+0.021
Neg logit contributions
 pic-0.010
 minutes-0.010
storms-0.009
 showers-0.009
 tea-0.008
Token to
Token ID284
Feature activation-1.01e-03

Pos logit contributions
 minutes+0.004
pill+0.003
 pic+0.003
storms+0.003
 showers+0.003
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.004
rave-0.004
ble-0.004
Token get
Token ID651
Feature activation-3.74e-03

Pos logit contributions
 minutes+0.002
 pic+0.002
storms+0.002
 showers+0.002
pill+0.002
Neg logit contributions
 captain-0.001
rave-0.001
ole-0.001
hips-0.001
ble-0.001
Token uniforms
Token ID22551
Feature activation+5.22e-02

Pos logit contributions
 minutes+0.005
 pic+0.005
pill+0.005
storms+0.005
 showers+0.005
Neg logit contributions
 captain-0.006
hips-0.006
rave-0.006
ole-0.006
ble-0.006
Token that
Token ID326
Feature activation+7.91e-03

Pos logit contributions
 captain+0.092
rave+0.090
ole+0.088
hips+0.087
roc+0.086
Neg logit contributions
 minutes-0.066
storms-0.062
 pic-0.060
pill-0.056
 spilled-0.056
Token were
Token ID547
Feature activation-1.72e-02

Pos logit contributions
 captain+0.013
hips+0.012
ole+0.012
boat+0.011
rave+0.011
Neg logit contributions
 minutes-0.012
pill-0.012
storms-0.011
 pic-0.011
ud-0.010
Token very
Token ID845
Feature activation-2.07e-02

Pos logit contributions
 minutes+0.026
 pic+0.025
pill+0.024
storms+0.024
 showers+0.023
Neg logit contributions
 captain-0.027
ole-0.026
hips-0.026
rave-0.026
ble-0.025
Token,
Token ID11
Feature activation-3.79e-03

Pos logit contributions
 minutes+0.031
 pic+0.029
pill+0.028
storms+0.028
 showers+0.027
Neg logit contributions
 captain-0.033
hips-0.032
rave-0.032
ole-0.031
ble-0.030
Token very
Token ID845
Feature activation-1.13e-02

Pos logit contributions
 minutes+0.006
pill+0.006
storms+0.005
 pic+0.005
 showers+0.005
Neg logit contributions
 captain-0.006
hips-0.006
ole-0.006
rave-0.005
ble-0.005
Token paint
Token ID7521
Feature activation-1.88e-02

Pos logit contributions
 minutes+0.015
pill+0.014
 pic+0.014
storms+0.014
 showers+0.013
Neg logit contributions
 captain-0.014
ole-0.013
hips-0.013
rave-0.013
ble-0.012
Token!"
Token ID2474
Feature activation-7.57e-03

Pos logit contributions
pill+0.031
 minutes+0.031
 pic+0.031
zed+0.030
storms+0.029
Neg logit contributions
ole-0.026
 captain-0.025
hips-0.024
rave-0.023
ble-0.023
Token her
Token ID607
Feature activation+6.47e-03

Pos logit contributions
pill+0.014
 pic+0.014
storms+0.013
 minutes+0.013
ud+0.013
Neg logit contributions
 captain-0.009
rave-0.008
 Elliot-0.008
ole-0.008
 himself-0.008
Token mom
Token ID1995
Feature activation-9.98e-03

Pos logit contributions
 captain+0.009
ole+0.008
hips+0.008
rave+0.008
ble+0.007
Neg logit contributions
 minutes-0.012
pill-0.011
 pic-0.011
storms-0.011
 showers-0.010
Token sc
Token ID629
Feature activation+3.66e-02

Pos logit contributions
 pic+0.015
 minutes+0.015
pill+0.015
storms+0.014
 showers+0.014
Neg logit contributions
 captain-0.016
ole-0.015
rave-0.015
ble-0.014
hips-0.014
Tokenolded
Token ID48959
Feature activation+5.29e-02

Pos logit contributions
 captain+0.071
ble+0.064
hips+0.063
ole+0.062
 ashore+0.060
Neg logit contributions
 minutes-0.042
pill-0.041
storms-0.036
 spilled-0.034
 knocks-0.033
Token.
Token ID13
Feature activation-2.56e-03

Pos logit contributions
 captain+0.114
hips+0.109
rave+0.107
ole+0.107
ble+0.103
Neg logit contributions
 minutes-0.053
storms-0.047
pill-0.046
 pic-0.046
 showers-0.044
Token But
Token ID887
Feature activation+2.14e-02

Pos logit contributions
 pic+0.005
 minutes+0.005
pill+0.005
growth+0.005
ud+0.005
Neg logit contributions
rave-0.002
ole-0.002
 Elliot-0.002
 captain-0.002
 himself-0.002
Token Lily
Token ID20037
Feature activation-1.72e-02

Pos logit contributions
 captain+0.041
ole+0.040
hips+0.039
rave+0.039
ble+0.038
Neg logit contributions
pill-0.025
 pic-0.024
 minutes-0.023
storms-0.023
 showers-0.019
Token didn
Token ID1422
Feature activation+2.02e-02

Pos logit contributions
 minutes+0.026
pill+0.025
 pic+0.025
storms+0.024
 showers+0.022
Neg logit contributions
 captain-0.028
rave-0.026
ole-0.026
ble-0.026
hips-0.025
Token't
Token ID470
Feature activation+2.83e-02

Pos logit contributions
 captain+0.031
ole+0.030
hips+0.029
rave+0.029
ble+0.027
Neg logit contributions
 minutes-0.031
pill-0.030
 pic-0.029
storms-0.029
 showers-0.028
TokenTogether
Token ID41631
Feature activation+2.48e-03

Pos logit contributions
 captain+0.004
ole+0.003
hips+0.003
rave+0.003
ble+0.003
Neg logit contributions
 minutes-0.004
pill-0.004
 pic-0.004
storms-0.004
 showers-0.003
Token,
Token ID11
Feature activation-7.34e-03

Pos logit contributions
 captain+0.005
hips+0.004
rave+0.004
ble+0.004
ole+0.004
Neg logit contributions
 minutes-0.003
 pic-0.003
storms-0.003
 showers-0.003
pill-0.003
Token they
Token ID484
Feature activation+7.17e-03

Pos logit contributions
 minutes+0.009
pill+0.008
 pic+0.008
storms+0.008
 showers+0.007
Neg logit contributions
 captain-0.014
ole-0.013
hips-0.013
rave-0.013
ble-0.013
Token filled
Token ID5901
Feature activation+2.32e-02

Pos logit contributions
 captain+0.015
hips+0.014
ole+0.014
rave+0.014
ble+0.014
Neg logit contributions
 minutes-0.007
 pic-0.007
storms-0.006
pill-0.006
 spilled-0.006
Token the
Token ID262
Feature activation+2.51e-02

Pos logit contributions
 captain+0.034
ole+0.032
hips+0.031
rave+0.031
ble+0.030
Neg logit contributions
 minutes-0.039
pill-0.037
storms-0.037
 pic-0.036
 showers-0.034
Token boxes
Token ID10559
Feature activation+5.93e-02

Pos logit contributions
 captain+0.037
hips+0.036
rave+0.036
ole+0.035
ble+0.034
Neg logit contributions
 minutes-0.040
 pic-0.038
pill-0.036
storms-0.036
 showers-0.035
Token on
Token ID319
Feature activation+4.51e-04

Pos logit contributions
roc+0.115
 captain+0.113
rave+0.109
amus+0.106
hips+0.105
Neg logit contributions
 minutes-0.068
 spilled-0.055
 pic-0.055
storms-0.052
 drifted-0.049
Token the
Token ID262
Feature activation+6.92e-03

Pos logit contributions
 captain+0.001
hips+0.001
ole+0.001
rave+0.001
ble+0.001
Neg logit contributions
 minutes-0.001
 pic-0.001
pill-0.001
storms-0.001
 showers-0.001
Token truck
Token ID7779
Feature activation+2.50e-02

Pos logit contributions
 captain+0.011
hips+0.011
ole+0.011
rave+0.011
ble+0.011
Neg logit contributions
 minutes-0.010
 pic-0.009
pill-0.009
storms-0.009
 showers-0.008
Token.
Token ID13
Feature activation+5.73e-03

Pos logit contributions
 captain+0.042
ole+0.040
hips+0.040
rave+0.040
ble+0.038
Neg logit contributions
 minutes-0.035
 pic-0.033
storms-0.033
pill-0.033
 showers-0.030
Token Jake
Token ID14757
Feature activation-1.26e-02

Pos logit contributions
 captain+0.008
hips+0.008
rave+0.008
ole+0.008
 Elliot+0.007
Neg logit contributions
 minutes-0.009
pill-0.009
 pic-0.009
storms-0.009
 spilled-0.008
Token outside
Token ID2354
Feature activation+8.57e-04

Pos logit contributions
 minutes+0.007
pill+0.007
storms+0.007
 pic+0.007
 showers+0.006
Neg logit contributions
 captain-0.006
ole-0.006
hips-0.006
rave-0.006
ble-0.006
Token.
Token ID13
Feature activation+1.79e-03

Pos logit contributions
 captain+0.001
ole+0.001
hips+0.001
rave+0.001
ble+0.001
Neg logit contributions
 minutes-0.001
pill-0.001
 pic-0.001
storms-0.001
 showers-0.001
Token They
Token ID1119
Feature activation+1.81e-02

Pos logit contributions
 captain+0.003
ole+0.002
hips+0.002
rave+0.002
 theirs+0.002
Neg logit contributions
pill-0.003
 minutes-0.003
storms-0.003
zed-0.002
 spilled-0.002
Token had
Token ID550
Feature activation+3.25e-03

Pos logit contributions
 captain+0.033
hips+0.030
ole+0.030
rave+0.029
ble+0.028
Neg logit contributions
 minutes-0.024
pill-0.023
storms-0.023
 pic-0.023
 showers-0.021
Token many
Token ID867
Feature activation-2.55e-02

Pos logit contributions
 captain+0.004
hips+0.003
rave+0.003
ole+0.003
 himself+0.003
Neg logit contributions
storms-0.006
pill-0.006
 minutes-0.006
 distur-0.006
zed-0.006
Token toys
Token ID14958
Feature activation+2.33e-02

Pos logit contributions
 minutes+0.046
storms+0.045
pill+0.044
 pic+0.043
 showers+0.040
Neg logit contributions
 captain-0.033
ole-0.031
hips-0.030
rave-0.030
ble-0.028
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
 captain+0.029
hips+0.029
ole+0.028
rave+0.025
bles+0.025
Neg logit contributions
 minutes-0.042
pill-0.042
storms-0.041
 pic-0.041
zed-0.039
Token but
Token ID475
Feature activation+1.77e-02

Pos logit contributions
 minutes+0.017
pill+0.016
storms+0.016
 pic+0.016
 showers+0.015
Neg logit contributions
 captain-0.018
hips-0.017
ole-0.017
rave-0.017
ble-0.016
Token their
Token ID511
Feature activation-9.34e-03

Pos logit contributions
 captain+0.031
hips+0.029
ole+0.029
rave+0.029
ble+0.028
Neg logit contributions
 minutes-0.025
 pic-0.023
pill-0.023
storms-0.022
 showers-0.021
Token favorite
Token ID4004
Feature activation-2.85e-02

Pos logit contributions
 minutes+0.017
pill+0.016
storms+0.016
 pic+0.015
zed+0.014
Neg logit contributions
 captain-0.013
ole-0.012
hips-0.011
rave-0.011
ble-0.010
Token was
Token ID373
Feature activation-5.27e-03

Pos logit contributions
 minutes+0.042
pill+0.041
storms+0.040
 pic+0.038
 showers+0.035
Neg logit contributions
 captain-0.048
ole-0.046
hips-0.043
rave-0.042
ble-0.041
Token
Token ID198
Feature activation+5.65e-03

Pos logit contributions
 captain+0.012
ole+0.011
hips+0.011
rave+0.011
ble+0.011
Neg logit contributions
 minutes-0.006
storms-0.005
 pic-0.005
pill-0.005
 showers-0.005
TokenThe
Token ID464
Feature activation+1.55e-03

Pos logit contributions
 captain+0.009
hips+0.009
ole+0.009
rave+0.009
ble+0.008
Neg logit contributions
pill-0.008
 minutes-0.008
 pic-0.007
storms-0.007
 showers-0.007
Token cell
Token ID2685
Feature activation-9.92e-03

Pos logit contributions
 captain+0.002
hips+0.002
ole+0.002
rave+0.002
ble+0.002
Neg logit contributions
 minutes-0.002
pill-0.002
 pic-0.002
storms-0.002
 showers-0.002
Token was
Token ID373
Feature activation-2.57e-03

Pos logit contributions
 minutes+0.015
pill+0.014
 pic+0.014
storms+0.013
 showers+0.013
Neg logit contributions
 captain-0.016
ole-0.015
hips-0.015
rave-0.015
ble-0.015
Token very
Token ID845
Feature activation-1.08e-02

Pos logit contributions
pill+0.004
 minutes+0.004
storms+0.004
 pic+0.004
 showers+0.004
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.003
rave-0.003
ble-0.003
Token grateful
Token ID14066
Feature activation+2.61e-02

Pos logit contributions
 minutes+0.017
 pic+0.016
pill+0.015
storms+0.015
 showers+0.015
Neg logit contributions
 captain-0.017
hips-0.016
ole-0.016
rave-0.016
ble-0.015
Token that
Token ID326
Feature activation+1.63e-02

Pos logit contributions
 captain+0.039
ole+0.037
hips+0.037
rave+0.036
ble+0.034
Neg logit contributions
 minutes-0.042
pill-0.040
 pic-0.040
storms-0.040
 showers-0.037
Token Reg
Token ID3310
Feature activation-5.06e-03

Pos logit contributions
 captain+0.025
ole+0.025
hips+0.024
rave+0.024
ble+0.022
Neg logit contributions
 minutes-0.024
pill-0.023
storms-0.022
 pic-0.022
 showers-0.021
Tokenret
Token ID1186
Feature activation-5.11e-03

Pos logit contributions
 minutes+0.009
pill+0.009
 pic+0.009
storms+0.009
 showers+0.008
Neg logit contributions
 captain-0.006
hips-0.006
ole-0.006
rave-0.006
ble-0.005
Token had
Token ID550
Feature activation+1.26e-02

Pos logit contributions
 minutes+0.008
pill+0.008
storms+0.007
 pic+0.007
 showers+0.007
Neg logit contributions
 captain-0.008
hips-0.007
ole-0.007
rave-0.007
ble-0.007
Token come
Token ID1282
Feature activation+2.27e-02

Pos logit contributions
 captain+0.021
ole+0.019
rave+0.019
hips+0.019
ble+0.018
Neg logit contributions
pill-0.019
storms-0.018
 minutes-0.018
 pic-0.017
 showers-0.016
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
 captain+0.024
ole+0.023
hips+0.023
rave+0.023
ble+0.022
Neg logit contributions
 minutes-0.019
 pic-0.018
pill-0.018
storms-0.018
 showers-0.016
Token<|endoftext|>
Token ID50256
Feature activation-8.79e-03

Pos logit contributions
ole+0.028
 captain+0.027
rave+0.027
hips+0.027
ble+0.026
Neg logit contributions
 minutes-0.021
storms-0.018
 pic-0.017
pill-0.017
 spilled-0.017
TokenOnce
Token ID7454
Feature activation+2.56e-02

Pos logit contributions
 minutes+0.012
storms+0.010
 pic+0.010
pill+0.010
 showers+0.010
Neg logit contributions
ole-0.015
rave-0.015
 captain-0.014
hips-0.014
ble-0.014
Token upon
Token ID2402
Feature activation-6.93e-03

Pos logit contributions
 captain+0.017
hips+0.014
ole+0.014
rave+0.014
ble+0.012
Neg logit contributions
 minutes-0.063
pill-0.060
 pic-0.060
storms-0.060
 showers-0.058
Token a
Token ID257
Feature activation-2.71e-02

Pos logit contributions
 minutes+0.011
pill+0.010
 pic+0.010
storms+0.010
 showers+0.010
Neg logit contributions
 captain-0.011
ole-0.010
hips-0.010
rave-0.010
ble-0.009
Token time
Token ID640
Feature activation+2.96e-02

Pos logit contributions
pill+0.036
storms+0.034
 showers+0.030
 overfl+0.029
pler+0.029
Neg logit contributions
ole-0.048
 promise-0.045
oy-0.043
rey-0.041
eka-0.040
Token,
Token ID11
Feature activation+4.73e-03

Pos logit contributions
 captain+0.040
ole+0.038
hips+0.038
rave+0.037
ble+0.035
Neg logit contributions
 minutes-0.052
pill-0.049
 pic-0.049
storms-0.048
 showers-0.046
Token there
Token ID612
Feature activation-1.77e-03

Pos logit contributions
 captain+0.008
hips+0.007
ole+0.007
rave+0.007
ble+0.007
Neg logit contributions
 minutes-0.007
 pic-0.007
pill-0.007
storms-0.007
 showers-0.006
Token was
Token ID373
Feature activation-1.70e-03

Pos logit contributions
 minutes+0.003
pill+0.003
storms+0.003
 pic+0.002
 showers+0.002
Neg logit contributions
 captain-0.003
ble-0.003
ole-0.003
rave-0.002
hips-0.002
Token a
Token ID257
Feature activation+1.11e-02

Pos logit contributions
 minutes+0.003
storms+0.003
pill+0.003
 pic+0.003
 knocks+0.003
Neg logit contributions
 captain-0.002
ole-0.002
rave-0.002
hips-0.002
ble-0.002
Token little
Token ID1310
Feature activation+7.26e-03

Pos logit contributions
 captain+0.020
hips+0.020
ole+0.019
rave+0.019
ble+0.018
Neg logit contributions
 minutes-0.014
 pic-0.013
pill-0.013
storms-0.013
 showers-0.012
Token day
Token ID1110
Feature activation+2.62e-02

Pos logit contributions
pill+0.009
 minutes+0.008
 pic+0.008
storms+0.007
zed+0.007
Neg logit contributions
 captain-0.010
ole-0.009
boat-0.008
ble-0.008
hips-0.008
Token.
Token ID13
Feature activation+2.55e-03

Pos logit contributions
 captain+0.035
ole+0.033
hips+0.032
rave+0.031
ble+0.030
Neg logit contributions
pill-0.046
 minutes-0.044
 pic-0.043
storms-0.043
 showers-0.041
Token Billy
Token ID15890
Feature activation+1.85e-02

Pos logit contributions
 captain+0.004
ole+0.004
hips+0.004
rave+0.004
 himself+0.003
Neg logit contributions
 minutes-0.004
pill-0.004
 spilled-0.004
 pic-0.004
storms-0.004
Token had
Token ID550
Feature activation+1.54e-02

Pos logit contributions
 captain+0.028
boat+0.023
rave+0.023
ole+0.023
 chest+0.023
Neg logit contributions
 minutes-0.029
pill-0.028
 pic-0.026
storms-0.026
 showers-0.026
Token been
Token ID587
Feature activation+7.12e-03

Pos logit contributions
 captain+0.020
ole+0.016
hips+0.016
rave+0.015
 himself+0.015
Neg logit contributions
pill-0.030
storms-0.029
 minutes-0.028
 pic-0.027
 showers-0.025
Token waiting
Token ID4953
Feature activation+1.28e-02

Pos logit contributions
 captain+0.011
ole+0.010
rave+0.009
ble+0.009
hips+0.009
Neg logit contributions
pill-0.012
storms-0.012
 minutes-0.011
 pic-0.011
 showers-0.010
Token all
Token ID477
Feature activation+1.13e-02

Pos logit contributions
 captain+0.014
ole+0.014
hips+0.014
rave+0.013
ble+0.012
Neg logit contributions
 minutes-0.026
 pic-0.024
storms-0.023
pill-0.023
 showers-0.023
Token week
Token ID1285
Feature activation+9.26e-03

Pos logit contributions
 captain+0.019
ole+0.018
hips+0.018
rave+0.018
ble+0.017
Neg logit contributions
pill-0.016
 minutes-0.016
 pic-0.015
storms-0.015
 showers-0.014
Token for
Token ID329
Feature activation+8.23e-03

Pos logit contributions
 captain+0.015
ole+0.014
hips+0.014
rave+0.013
ble+0.013
Neg logit contributions
 minutes-0.014
pill-0.014
storms-0.013
 pic-0.013
 showers-0.012
Token his
Token ID465
Feature activation-1.84e-03

Pos logit contributions
 captain+0.011
ole+0.010
hips+0.009
 himself+0.009
rave+0.009
Neg logit contributions
pill-0.015
storms-0.015
 minutes-0.014
 spilled-0.013
 pic-0.013
Token special
Token ID2041
Feature activation-7.38e-03

Pos logit contributions
pill+0.003
 minutes+0.003
storms+0.003
 pic+0.003
 showers+0.003
Neg logit contributions
 captain-0.003
ole-0.002
hips-0.002
rave-0.002
ble-0.002
Token to
Token ID284
Feature activation-6.71e-03

Pos logit contributions
 captain+0.013
ole+0.013
hips+0.013
rave+0.012
ble+0.012
Neg logit contributions
 minutes-0.015
pill-0.015
storms-0.014
 pic-0.014
 showers-0.013
Token raise
Token ID5298
Feature activation+6.18e-03

Pos logit contributions
 minutes+0.010
 pic+0.010
 showers+0.009
zed+0.009
storms+0.009
Neg logit contributions
ole-0.009
rave-0.009
 captain-0.009
hips-0.009
bles-0.009
Token their
Token ID511
Feature activation-1.35e-03

Pos logit contributions
 captain+0.009
ole+0.008
hips+0.008
rave+0.008
ble+0.007
Neg logit contributions
 minutes-0.011
pill-0.010
storms-0.010
 pic-0.010
 showers-0.009
Token spirits
Token ID13747
Feature activation+1.61e-02

Pos logit contributions
pill+0.002
 minutes+0.002
storms+0.002
 pic+0.002
zed+0.002
Neg logit contributions
 captain-0.002
ole-0.002
hips-0.002
rave-0.002
 promise-0.002
Token and
Token ID290
Feature activation-6.62e-03

Pos logit contributions
 captain+0.028
rave+0.027
hips+0.026
ole+0.026
ble+0.025
Neg logit contributions
 minutes-0.022
storms-0.020
 pic-0.020
pill-0.020
 showers-0.019
Token lend
Token ID22096
Feature activation+1.29e-02

Pos logit contributions
 minutes+0.012
 pic+0.011
pill+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.009
ole-0.008
hips-0.008
rave-0.008
ble-0.008
Token a
Token ID257
Feature activation-7.33e-03

Pos logit contributions
 captain+0.020
ole+0.019
hips+0.019
rave+0.019
ble+0.018
Neg logit contributions
 minutes-0.020
pill-0.019
storms-0.019
 pic-0.019
 showers-0.017
Token helping
Token ID5742
Feature activation-1.14e-02

Pos logit contributions
 minutes+0.012
 pic+0.012
pill+0.012
storms+0.012
 showers+0.011
Neg logit contributions
 captain-0.010
ole-0.010
hips-0.010
rave-0.010
ble-0.009
Token hand
Token ID1021
Feature activation-2.95e-02

Pos logit contributions
 minutes+0.018
pill+0.018
storms+0.017
 pic+0.017
 showers+0.016
Neg logit contributions
 captain-0.017
ole-0.017
hips-0.017
rave-0.016
ble-0.015
Token.
Token ID13
Feature activation+3.96e-03

Pos logit contributions
 minutes+0.045
pill+0.043
 pic+0.042
storms+0.042
 showers+0.039
Neg logit contributions
 captain-0.046
ole-0.044
hips-0.044
rave-0.043
ble-0.041
Token<|endoftext|>
Token ID50256
Feature activation-1.25e-02

Pos logit contributions
ole+0.006
hips+0.006
rave+0.006
 captain+0.006
 Crane+0.005
Neg logit contributions
 minutes-0.006
 spilled-0.005
storms-0.005
 spills-0.005
 knocks-0.005
Token saw
Token ID2497
Feature activation-1.37e-02

Pos logit contributions
 captain+0.002
rave+0.002
ole+0.001
cher+0.001
ter+0.001
Neg logit contributions
pill-0.002
 pic-0.002
storms-0.002
 minutes-0.002
 showers-0.001
Token that
Token ID326
Feature activation+7.03e-03

Pos logit contributions
 minutes+0.028
storms+0.027
 pic+0.027
zed+0.026
pill+0.025
Neg logit contributions
ter-0.014
 captain-0.013
ble-0.013
 himself-0.012
hips-0.012
Token she
Token ID673
Feature activation-2.12e-02

Pos logit contributions
 captain+0.012
ole+0.011
hips+0.011
rave+0.011
ble+0.011
Neg logit contributions
 minutes-0.010
pill-0.010
storms-0.009
 pic-0.009
zed-0.008
Token was
Token ID373
Feature activation-1.44e-02

Pos logit contributions
 minutes+0.027
 pic+0.026
pill+0.025
storms+0.025
 showers+0.023
Neg logit contributions
 captain-0.039
ole-0.037
rave-0.036
ble-0.036
hips-0.035
Token hurt
Token ID5938
Feature activation+7.62e-03

Pos logit contributions
 minutes+0.023
pill+0.023
 pic+0.022
storms+0.022
 showers+0.020
Neg logit contributions
 captain-0.022
ble-0.021
ole-0.021
rave-0.020
hips-0.020
Token.
Token ID13
Feature activation-1.32e-02

Pos logit contributions
 captain+0.012
ole+0.012
hips+0.012
rave+0.012
ble+0.011
Neg logit contributions
 minutes-0.011
pill-0.011
 pic-0.011
storms-0.010
 showers-0.010
Token "
Token ID366
Feature activation-1.38e-02

Pos logit contributions
 minutes+0.024
 pic+0.022
zed+0.022
pill+0.021
 spills+0.021
Neg logit contributions
rave-0.014
ole-0.014
 Elliot-0.014
 sir-0.014
 captain-0.013
TokenOh
Token ID5812
Feature activation-3.09e-02

Pos logit contributions
storms+0.019
 minutes+0.019
 pic+0.019
pill+0.018
 showers+0.016
Neg logit contributions
 captain-0.023
rave-0.022
ole-0.022
ble-0.021
hips-0.021
Token no
Token ID645
Feature activation-4.45e-03

Pos logit contributions
pill+0.050
 minutes+0.049
 pic+0.049
storms+0.049
 showers+0.044
Neg logit contributions
 captain-0.045
ole-0.042
rave-0.041
hips-0.041
ble-0.039
Token,
Token ID11
Feature activation-1.84e-03

Pos logit contributions
pill+0.009
 pic+0.008
storms+0.008
 minutes+0.008
 showers+0.008
Neg logit contributions
 captain-0.005
ole-0.005
rave-0.004
ble-0.004
hips-0.004
Token Lily
Token ID20037
Feature activation-1.50e-02

Pos logit contributions
 minutes+0.003
 pic+0.002
pill+0.002
storms+0.002
 showers+0.002
Neg logit contributions
 captain-0.003
ole-0.003
hips-0.003
rave-0.003
ble-0.003
Token you
Token ID345
Feature activation+1.11e-02

Pos logit contributions
 captain+0.014
ole+0.013
hips+0.013
rave+0.013
ble+0.013
Neg logit contributions
 minutes-0.017
pill-0.016
storms-0.016
 pic-0.016
 spilled-0.015
Token Sarah
Token ID10490
Feature activation-8.36e-03

Pos logit contributions
 captain+0.016
hips+0.016
ole+0.015
rave+0.015
ble+0.014
Neg logit contributions
 minutes-0.018
 pic-0.017
storms-0.017
pill-0.016
 showers-0.016
Token,
Token ID11
Feature activation-3.01e-03

Pos logit contributions
 minutes+0.013
pill+0.012
 pic+0.012
storms+0.012
 showers+0.011
Neg logit contributions
 captain-0.013
ole-0.013
hips-0.013
rave-0.012
ble-0.012
Token don
Token ID836
Feature activation+2.36e-02

Pos logit contributions
 minutes+0.005
pill+0.004
storms+0.004
 pic+0.004
 showers+0.004
Neg logit contributions
 captain-0.005
hips-0.004
ole-0.004
rave-0.004
ble-0.004
Token't
Token ID470
Feature activation+4.16e-03

Pos logit contributions
 captain+0.030
hips+0.029
ole+0.029
rave+0.029
ble+0.027
Neg logit contributions
 minutes-0.043
 pic-0.041
pill-0.040
storms-0.040
 showers-0.037
Token worry
Token ID5490
Feature activation-6.39e-03

Pos logit contributions
 captain+0.004
hips+0.004
ole+0.004
rave+0.004
ble+0.004
Neg logit contributions
 minutes-0.008
 pic-0.008
storms-0.008
pill-0.008
 showers-0.008
Token.
Token ID13
Feature activation-1.70e-02

Pos logit contributions
 minutes+0.010
pill+0.010
 pic+0.010
storms+0.010
 showers+0.009
Neg logit contributions
 captain-0.009
ole-0.009
hips-0.009
rave-0.009
ble-0.008
Token Witches
Token ID44910
Feature activation-1.55e-02

Pos logit contributions
 minutes+0.024
 pic+0.023
pill+0.022
storms+0.022
 spilled+0.021
Neg logit contributions
 captain-0.029
hips-0.027
rave-0.027
ole-0.027
ble-0.025
Token don
Token ID836
Feature activation+3.07e-02

Pos logit contributions
 minutes+0.030
pill+0.029
 pic+0.029
storms+0.028
 showers+0.027
Neg logit contributions
 captain-0.018
hips-0.018
rave-0.017
ole-0.017
ble-0.016
Token't
Token ID470
Feature activation+1.34e-02

Pos logit contributions
 captain+0.045
ole+0.043
hips+0.043
rave+0.042
ble+0.040
Neg logit contributions
 minutes-0.050
pill-0.047
 pic-0.047
storms-0.047
 showers-0.044
Token belong
Token ID5594
Feature activation+1.15e-02

Pos logit contributions
rave+0.018
 captain+0.018
ole+0.018
hips+0.018
ble+0.017
Neg logit contributions
 minutes-0.022
storms-0.021
 showers-0.020
 pic-0.020
 spilled-0.019
Token while
Token ID981
Feature activation-5.43e-03

Pos logit contributions
 minutes+0.008
 pic+0.007
 showers+0.007
storms+0.007
 spilled+0.007
Neg logit contributions
hips-0.011
ole-0.011
rave-0.011
 captain-0.010
ble-0.010
Token he
Token ID339
Feature activation-1.41e-02

Pos logit contributions
 minutes+0.009
pill+0.009
 pic+0.009
storms+0.008
 showers+0.008
Neg logit contributions
 captain-0.008
ole-0.007
hips-0.007
rave-0.007
ble-0.007
Token was
Token ID373
Feature activation-4.42e-03

Pos logit contributions
 minutes+0.022
pill+0.021
storms+0.021
 pic+0.019
 showers+0.019
Neg logit contributions
 captain-0.019
ble-0.018
rave-0.017
ole-0.017
rey-0.016
Token playing
Token ID2712
Feature activation+3.31e-04

Pos logit contributions
pill+0.008
storms+0.007
 pic+0.007
 minutes+0.007
growth+0.006
Neg logit contributions
 captain-0.006
ble-0.006
rave-0.006
bles-0.005
 steering-0.005
Token his
Token ID465
Feature activation+8.15e-03

Pos logit contributions
 captain+0.000
ole+0.000
hips+0.000
rave+0.000
ble+0.000
Neg logit contributions
pill-0.001
 minutes-0.001
storms-0.001
 pic-0.001
 spilled-0.001
Token piano
Token ID19132
Feature activation+7.95e-03

Pos logit contributions
 captain+0.011
ble+0.009
ole+0.009
rave+0.009
hips+0.009
Neg logit contributions
pill-0.015
 minutes-0.015
storms-0.015
 pic-0.014
 spilled-0.013
Token,
Token ID11
Feature activation-5.82e-04

Pos logit contributions
 captain+0.009
hips+0.008
ole+0.008
ble+0.008
 chest+0.008
Neg logit contributions
pill-0.016
 minutes-0.015
 pic-0.015
storms-0.014
 showers-0.014
Token he
Token ID339
Feature activation-3.22e-04

Pos logit contributions
 minutes+0.001
 pic+0.001
storms+0.001
pill+0.001
 showers+0.001
Neg logit contributions
ole-0.001
 captain-0.001
hips-0.001
rave-0.001
ble-0.001
Token noticed
Token ID6810
Feature activation-1.42e-02

Pos logit contributions
pill+0.001
 pic+0.000
 minutes+0.000
storms+0.000
 showers+0.000
Neg logit contributions
 captain-0.001
ble-0.000
bles-0.000
 upon-0.000
 guard-0.000
Token something
Token ID1223
Feature activation+1.85e-02

Pos logit contributions
pill+0.027
 minutes+0.027
 pic+0.026
storms+0.026
 knocks+0.023
Neg logit contributions
 captain-0.018
ble-0.016
 himself-0.015
ole-0.014
rave-0.014
Token strange
Token ID6283
Feature activation+1.50e-03

Pos logit contributions
 captain+0.026
ole+0.025
ble+0.025
hips+0.024
rave+0.024
Neg logit contributions
 minutes-0.030
pill-0.030
 pic-0.029
storms-0.029
 showers-0.026
Token on
Token ID319
Feature activation+7.23e-03

Pos logit contributions
hips+0.070
ole+0.068
 captain+0.068
roc+0.065
 mercy+0.063
Neg logit contributions
 minutes-0.047
 pic-0.045
 showers-0.043
storms-0.039
 mornings-0.038
Token,
Token ID11
Feature activation+1.73e-02

Pos logit contributions
 captain+0.008
ole+0.008
hips+0.007
ble+0.007
rave+0.007
Neg logit contributions
pill-0.015
 minutes-0.014
 pic-0.014
storms-0.014
 showers-0.013
Token let
Token ID1309
Feature activation-2.14e-02

Pos logit contributions
 captain+0.028
ole+0.026
hips+0.026
rave+0.026
ble+0.025
Neg logit contributions
 minutes-0.026
pill-0.025
storms-0.024
 pic-0.024
 showers-0.023
Token's
Token ID338
Feature activation+1.63e-02

Pos logit contributions
 minutes+0.034
storms+0.032
pill+0.031
 pic+0.027
 drifted+0.027
Neg logit contributions
ole-0.031
 captain-0.030
rave-0.029
 promise-0.028
roc-0.028
Token bake
Token ID28450
Feature activation-1.13e-02

Pos logit contributions
 captain+0.024
ole+0.023
hips+0.023
rave+0.023
ble+0.021
Neg logit contributions
 minutes-0.026
 pic-0.025
storms-0.024
pill-0.024
 showers-0.023
Token a
Token ID257
Feature activation-5.93e-03

Pos logit contributions
 minutes+0.018
pill+0.018
storms+0.018
 pic+0.017
 showers+0.016
Neg logit contributions
 captain-0.017
ole-0.016
rave-0.016
hips-0.016
ble-0.015
Token cake
Token ID12187
Feature activation+6.61e-03

Pos logit contributions
storms+0.009
pill+0.009
 minutes+0.009
 pic+0.009
 showers+0.008
Neg logit contributions
 captain-0.009
ole-0.009
rave-0.008
hips-0.008
ble-0.008
Token."
Token ID526
Feature activation+8.94e-03

Pos logit contributions
 captain+0.009
ole+0.008
hips+0.008
rave+0.008
ble+0.007
Neg logit contributions
 minutes-0.012
pill-0.012
storms-0.011
 pic-0.011
 showers-0.011
Token
Token ID198
Feature activation+8.73e-03

Pos logit contributions
ole+0.012
hips+0.012
 captain+0.011
rave+0.011
 himself+0.011
Neg logit contributions
 minutes-0.015
storms-0.013
pill-0.012
zed-0.012
 pic-0.012
Token
Token ID198
Feature activation+8.76e-03

Pos logit contributions
 captain+0.014
ole+0.014
hips+0.014
rave+0.014
ble+0.014
Neg logit contributions
 minutes-0.012
storms-0.012
pill-0.011
 pic-0.010
 showers-0.010
TokenL
Token ID43
Feature activation+9.07e-03

Pos logit contributions
 captain+0.018
ole+0.017
hips+0.017
rave+0.017
ble+0.016
Neg logit contributions
 minutes-0.010
storms-0.009
pill-0.009
 pic-0.009
 showers-0.008
Token and
Token ID290
Feature activation-1.44e-03

Pos logit contributions
 captain+0.026
hips+0.025
ole+0.025
rave+0.025
ble+0.023
Neg logit contributions
 minutes-0.023
storms-0.021
pill-0.020
 pic-0.020
 showers-0.019
Token tried
Token ID3088
Feature activation-1.61e-02

Pos logit contributions
 minutes+0.002
pill+0.002
storms+0.002
 pic+0.002
 showers+0.002
Neg logit contributions
 captain-0.003
ole-0.002
rave-0.002
hips-0.002
ble-0.002
Token to
Token ID284
Feature activation+5.76e-03

Pos logit contributions
 minutes+0.022
 pic+0.020
pill+0.020
storms+0.020
 showers+0.018
Neg logit contributions
 captain-0.028
ole-0.027
hips-0.027
rave-0.027
ble-0.026
Token splash
Token ID22870
Feature activation-3.19e-02

Pos logit contributions
ole+0.010
rave+0.010
hips+0.010
roc+0.009
bek+0.009
Neg logit contributions
 minutes-0.007
 pic-0.007
 spilled-0.006
 showers-0.006
 cou-0.006
Token the
Token ID262
Feature activation+6.90e-03

Pos logit contributions
 minutes+0.056
pill+0.054
 pic+0.053
storms+0.053
 showers+0.049
Neg logit contributions
 captain-0.043
ole-0.041
hips-0.040
rave-0.040
ble-0.038
Token fish
Token ID5916
Feature activation-2.88e-03

Pos logit contributions
 captain+0.010
hips+0.010
rave+0.010
ole+0.010
ble+0.009
Neg logit contributions
 minutes-0.011
 pic-0.010
pill-0.010
storms-0.010
 showers-0.010
Token away
Token ID1497
Feature activation+1.18e-02

Pos logit contributions
 minutes+0.004
storms+0.004
 pic+0.004
pill+0.004
 showers+0.004
Neg logit contributions
 captain-0.005
rave-0.004
hips-0.004
ole-0.004
ble-0.004
Token.
Token ID13
Feature activation-6.62e-03

Pos logit contributions
 captain+0.022
rave+0.021
hips+0.021
ole+0.021
ble+0.020
Neg logit contributions
 minutes-0.015
storms-0.013
 pic-0.013
pill-0.012
 showers-0.012
Token But
Token ID887
Feature activation+2.22e-02

Pos logit contributions
 minutes+0.011
storms+0.010
 pic+0.009
 spilled+0.009
pill+0.009
Neg logit contributions
ole-0.010
 captain-0.010
rave-0.010
 himself-0.009
ble-0.009
Token the
Token ID262
Feature activation-1.90e-03

Pos logit contributions
 captain+0.037
hips+0.036
rave+0.035
ole+0.035
ble+0.033
Neg logit contributions
 minutes-0.032
 pic-0.029
pill-0.029
storms-0.029
 showers-0.028
Token fish
Token ID5916
Feature activation-1.56e-02

Pos logit contributions
 minutes+0.003
 pic+0.003
pill+0.003
storms+0.003
 showers+0.003
Neg logit contributions
 captain-0.003
hips-0.002
rave-0.002
ole-0.002
ble-0.002
Token son
Token ID3367
Feature activation-7.11e-03

Pos logit contributions
hips+0.003
ole+0.003
rave+0.003
 captain+0.003
ble+0.003
Neg logit contributions
 minutes-0.002
 pic-0.002
 showers-0.002
pill-0.002
storms-0.002
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
 minutes+0.011
 pic+0.010
pill+0.010
storms+0.010
 showers+0.009
Neg logit contributions
 captain-0.011
hips-0.011
ole-0.010
rave-0.010
ble-0.010
Token No
Token ID1400
Feature activation-6.34e-03

Pos logit contributions
 minutes+0.014
pill+0.013
 pic+0.013
storms+0.013
 showers+0.012
Neg logit contributions
 captain-0.022
ole-0.021
hips-0.021
rave-0.020
ble-0.020
Token matter
Token ID2300
Feature activation-1.87e-02

Pos logit contributions
storms+0.011
pill+0.011
 pic+0.010
 minutes+0.010
 showers+0.009
Neg logit contributions
 captain-0.009
ole-0.008
rave-0.008
hips-0.008
ble-0.008
Token how
Token ID703
Feature activation+1.98e-02

Pos logit contributions
 minutes+0.026
 pic+0.023
storms+0.022
pill+0.022
 showers+0.022
Neg logit contributions
 captain-0.033
ole-0.031
hips-0.031
rave-0.031
ble-0.029
Token hot
Token ID3024
Feature activation-3.93e-02

Pos logit contributions
ole+0.029
 captain+0.029
rave+0.028
hips+0.027
ble+0.027
Neg logit contributions
 minutes-0.031
storms-0.030
pill-0.030
 pic-0.030
 showers-0.026
Token it
Token ID340
Feature activation-2.42e-02

Pos logit contributions
 minutes+0.065
pill+0.064
storms+0.062
 pic+0.061
 spilled+0.056
Neg logit contributions
 captain-0.056
ole-0.054
hips-0.053
ble-0.052
rave-0.051
Token is
Token ID318
Feature activation+2.77e-03

Pos logit contributions
 minutes+0.039
 pic+0.035
pill+0.034
storms+0.034
 sudden+0.032
Neg logit contributions
rave-0.036
 captain-0.036
hips-0.035
ole-0.034
ble-0.034
Token outside
Token ID2354
Feature activation-1.88e-02

Pos logit contributions
 captain+0.004
ole+0.004
hips+0.004
rave+0.004
ble+0.004
Neg logit contributions
 minutes-0.005
pill-0.005
 pic-0.005
storms-0.005
 showers-0.004
Token,
Token ID11
Feature activation-9.89e-03

Pos logit contributions
 minutes+0.033
pill+0.033
 pic+0.031
storms+0.031
 showers+0.029
Neg logit contributions
 captain-0.025
ole-0.024
hips-0.023
ble-0.022
rave-0.022
Token if
Token ID611
Feature activation+4.67e-04

Pos logit contributions
 minutes+0.014
 pic+0.013
pill+0.013
storms+0.013
 showers+0.012
Neg logit contributions
 captain-0.016
ole-0.016
hips-0.016
rave-0.015
ble-0.015
Token and
Token ID290
Feature activation+7.38e-03

Pos logit contributions
 captain+0.023
ole+0.022
hips+0.022
rave+0.022
ble+0.021
Neg logit contributions
 minutes-0.017
storms-0.016
 pic-0.016
pill-0.016
 showers-0.015
Token it
Token ID340
Feature activation-1.05e-02

Pos logit contributions
 captain+0.013
hips+0.012
ole+0.012
rave+0.012
ble+0.011
Neg logit contributions
 minutes-0.010
pill-0.010
 pic-0.009
storms-0.009
 showers-0.009
Token made
Token ID925
Feature activation-3.76e-03

Pos logit contributions
pill+0.016
 minutes+0.016
 pic+0.015
 showers+0.014
storms+0.014
Neg logit contributions
 captain-0.017
hips-0.015
rave-0.015
 promise-0.014
ole-0.014
Token Rob
Token ID3851
Feature activation-4.27e-03

Pos logit contributions
 minutes+0.008
pill+0.007
storms+0.007
 pic+0.007
 showers+0.007
Neg logit contributions
 captain-0.004
ole-0.004
hips-0.004
rave-0.004
ble-0.003
Tokenby
Token ID1525
Feature activation-3.18e-02

Pos logit contributions
 minutes+0.006
pill+0.005
storms+0.005
 pic+0.005
 showers+0.005
Neg logit contributions
 captain-0.007
hips-0.007
rave-0.007
ole-0.007
ble-0.007
Token feel
Token ID1254
Feature activation-3.72e-02

Pos logit contributions
 minutes+0.055
pill+0.052
 pic+0.052
storms+0.052
 showers+0.049
Neg logit contributions
 captain-0.043
ole-0.041
hips-0.041
rave-0.040
ble-0.038
Token sad
Token ID6507
Feature activation-1.90e-03

Pos logit contributions
pill+0.069
storms+0.068
 minutes+0.067
 pic+0.067
ud+0.060
Neg logit contributions
 captain-0.047
ole-0.041
 himself-0.041
hips-0.040
ble-0.040
Token.
Token ID13
Feature activation-7.10e-03

Pos logit contributions
pill+0.003
 pic+0.003
 minutes+0.003
zed+0.003
storms+0.003
Neg logit contributions
 captain-0.003
hips-0.002
ole-0.002
ble-0.002
 himself-0.002
Token
Token ID198
Feature activation-9.41e-03

Pos logit contributions
 minutes+0.011
 pic+0.010
pill+0.010
 spilled+0.010
storms+0.010
Neg logit contributions
 captain-0.011
hips-0.011
ole-0.011
rave-0.011
 Elliot-0.010
Token
Token ID198
Feature activation-4.61e-03

Pos logit contributions
 minutes+0.012
storms+0.011
pill+0.011
 pic+0.010
 showers+0.010
Neg logit contributions
 captain-0.017
ole-0.017
hips-0.017
rave-0.017
ble-0.016
TokenBut
Token ID1537
Feature activation+1.57e-02

Pos logit contributions
 minutes+0.007
 pic+0.006
pill+0.006
storms+0.006
 showers+0.006
Neg logit contributions
 captain-0.007
hips-0.007
ole-0.007
rave-0.007
ble-0.007
Token the
Token ID262
Feature activation+3.98e-03

Pos logit contributions
 minutes+0.008
pill+0.008
storms+0.008
 pic+0.008
 showers+0.007
Neg logit contributions
 captain-0.006
ole-0.006
hips-0.006
rave-0.006
ble-0.006
Token window
Token ID4324
Feature activation-5.55e-03

Pos logit contributions
 captain+0.005
hips+0.005
ole+0.005
rave+0.005
ble+0.005
Neg logit contributions
pill-0.007
 minutes-0.007
 pic-0.007
storms-0.007
 showers-0.006
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
 minutes+0.008
pill+0.007
 pic+0.007
storms+0.007
 showers+0.007
Neg logit contributions
 captain-0.010
ole-0.009
hips-0.009
rave-0.009
ble-0.009
Token felt
Token ID2936
Feature activation-4.17e-02

Pos logit contributions
 captain+0.021
rave+0.019
hips+0.019
ole+0.019
ble+0.019
Neg logit contributions
 minutes-0.014
pill-0.014
storms-0.014
 pic-0.014
 showers-0.012
Token how
Token ID703
Feature activation+1.09e-02

Pos logit contributions
 minutes+0.072
pill+0.072
storms+0.071
 pic+0.070
 spilled+0.061
Neg logit contributions
 captain-0.057
ble-0.051
hips-0.051
ole-0.051
rave-0.050
Token cold
Token ID4692
Feature activation-3.82e-02

Pos logit contributions
 captain+0.017
ole+0.017
hips+0.016
rave+0.016
ble+0.016
Neg logit contributions
 minutes-0.017
pill-0.016
 pic-0.016
storms-0.016
 showers-0.014
Token it
Token ID340
Feature activation-1.76e-02

Pos logit contributions
 minutes+0.068
pill+0.067
 pic+0.065
storms+0.062
 showers+0.058
Neg logit contributions
 captain-0.049
hips-0.046
ole-0.046
ble-0.045
rave-0.043
Token was
Token ID373
Feature activation-4.18e-03

Pos logit contributions
 minutes+0.029
pill+0.029
 pic+0.027
 showers+0.025
 mornings+0.024
Neg logit contributions
 captain-0.025
ble-0.024
boat-0.022
hips-0.022
ter-0.022
Token.
Token ID13
Feature activation-7.86e-04

Pos logit contributions
pill+0.007
 minutes+0.007
 pic+0.007
storms+0.006
 showers+0.006
Neg logit contributions
 captain-0.006
ole-0.006
ble-0.006
hips-0.006
rave-0.005
Token He
Token ID679
Feature activation+1.54e-02

Pos logit contributions
 minutes+0.002
pill+0.002
storms+0.002
 pic+0.002
 spilled+0.001
Neg logit contributions
 captain-0.001
rave-0.001
 himself-0.001
ole-0.001
 ashore-0.001
Token gigg
Token ID30442
Feature activation-3.15e-03

Pos logit contributions
 captain+0.025
rave+0.022
ble+0.021
ole+0.020
eka+0.020
Neg logit contributions
storms-0.024
pill-0.023
 minutes-0.021
 pic-0.021
 showers-0.021
Token a
Token ID257
Feature activation+1.18e-02

Pos logit contributions
pill+0.019
 minutes+0.019
storms+0.019
 pic+0.018
 showers+0.017
Neg logit contributions
 captain-0.019
ole-0.018
hips-0.018
rave-0.017
ble-0.016
Token long
Token ID890
Feature activation-2.75e-03

Pos logit contributions
 captain+0.019
ole+0.017
hips+0.017
rave+0.017
ble+0.016
Neg logit contributions
 minutes-0.018
pill-0.018
storms-0.017
 pic-0.017
 showers-0.016
Token drive
Token ID3708
Feature activation+7.60e-03

Pos logit contributions
 minutes+0.003
pill+0.003
storms+0.003
 pic+0.003
 showers+0.003
Neg logit contributions
 captain-0.005
ole-0.005
hips-0.005
rave-0.005
ble-0.005
Token.
Token ID13
Feature activation-5.15e-03

Pos logit contributions
 captain+0.012
ole+0.011
hips+0.011
rave+0.011
ble+0.010
Neg logit contributions
 minutes-0.012
pill-0.012
 pic-0.011
storms-0.011
 showers-0.011
Token M
Token ID337
Feature activation-1.31e-02

Pos logit contributions
storms+0.008
 minutes+0.008
pill+0.008
 spilled+0.008
 pic+0.008
Neg logit contributions
rave-0.006
 captain-0.006
hips-0.006
ole-0.006
 name-0.006
Tokenabel
Token ID9608
Feature activation-4.01e-02

Pos logit contributions
 minutes+0.013
 pic+0.012
pill+0.012
storms+0.012
 showers+0.011
Neg logit contributions
 captain-0.027
rave-0.026
ole-0.026
ble-0.026
hips-0.025
Token was
Token ID373
Feature activation-3.18e-04

Pos logit contributions
pill+0.064
storms+0.060
 pic+0.059
 showers+0.059
 minutes+0.055
Neg logit contributions
 captain-0.061
ole-0.053
ble-0.051
oy-0.051
 promise-0.049
Token tired
Token ID10032
Feature activation+1.41e-03

Pos logit contributions
pill+0.001
storms+0.001
 minutes+0.001
 pic+0.000
 showers+0.000
Neg logit contributions
 captain-0.000
rave-0.000
ole-0.000
hips-0.000
ble-0.000
Token but
Token ID475
Feature activation+1.78e-02

Pos logit contributions
 captain+0.002
ole+0.002
hips+0.002
ble+0.002
rave+0.002
Neg logit contributions
pill-0.003
 minutes-0.002
 pic-0.002
storms-0.002
zed-0.002
Token she
Token ID673
Feature activation-8.15e-03

Pos logit contributions
 captain+0.030
ole+0.028
rave+0.028
hips+0.028
ble+0.028
Neg logit contributions
 minutes-0.025
pill-0.025
storms-0.024
 pic-0.024
 showers-0.021
Token tried
Token ID3088
Feature activation+1.69e-03

Pos logit contributions
pill+0.011
 minutes+0.011
storms+0.011
 pic+0.011
 showers+0.010
Neg logit contributions
 captain-0.014
rave-0.013
ole-0.013
ble-0.012
hips-0.012
Token in
Token ID287
Feature activation-1.08e-02

Pos logit contributions
pill+0.029
 minutes+0.029
 pic+0.028
storms+0.028
 showers+0.026
Neg logit contributions
 captain-0.021
ole-0.020
hips-0.020
ble-0.019
rave-0.018
Token the
Token ID262
Feature activation+2.50e-03

Pos logit contributions
pill+0.024
storms+0.022
 minutes+0.020
pler+0.019
iche+0.019
Neg logit contributions
 himself-0.010
 captain-0.010
 ourselves-0.010
hips-0.009
 chest-0.009
Token arm
Token ID3211
Feature activation-2.94e-02

Pos logit contributions
 captain+0.004
 chest+0.003
 hero+0.003
 guard+0.003
ole+0.003
Neg logit contributions
pill-0.004
storms-0.004
 minutes-0.004
 pic-0.004
zed-0.003
Tokenchair
Token ID16337
Feature activation-1.36e-02

Pos logit contributions
 pic+0.038
pill+0.038
 minutes+0.035
 sudden+0.032
 mixes+0.032
Neg logit contributions
 chest-0.046
 captain-0.045
jack-0.044
boat-0.044
hips-0.043
Token,
Token ID11
Feature activation+5.76e-03

Pos logit contributions
pill+0.023
 minutes+0.022
 pic+0.022
storms+0.021
 showers+0.021
Neg logit contributions
 captain-0.019
hips-0.018
ole-0.018
rave-0.017
ble-0.017
Token feeling
Token ID4203
Feature activation-5.09e-02

Pos logit contributions
 captain+0.008
rave+0.007
hips+0.007
ble+0.007
 chest+0.007
Neg logit contributions
pill-0.010
 minutes-0.009
storms-0.009
 pic-0.009
 showers-0.008
Token so
Token ID523
Feature activation-2.71e-02

Pos logit contributions
pill+0.099
storms+0.096
 pic+0.093
 minutes+0.090
 knocks+0.086
Neg logit contributions
 captain-0.055
 himself-0.054
ble-0.049
 luck-0.048
ter-0.044
Token cozy
Token ID37438
Feature activation-8.35e-03

Pos logit contributions
pill+0.049
storms+0.046
 minutes+0.044
 pic+0.043
pler+0.039
Neg logit contributions
ble-0.036
 captain-0.034
 himself-0.033
 luck-0.033
hips-0.032
Token and
Token ID290
Feature activation-1.90e-02

Pos logit contributions
 minutes+0.012
pill+0.011
 pic+0.011
storms+0.011
 showers+0.010
Neg logit contributions
 captain-0.014
ole-0.013
hips-0.013
rave-0.013
ble-0.013
Token happy
Token ID3772
Feature activation-4.94e-04

Pos logit contributions
pill+0.034
 minutes+0.032
storms+0.032
 pic+0.030
ud+0.028
Neg logit contributions
 captain-0.026
ble-0.023
hips-0.023
rave-0.022
ole-0.022
Token.
Token ID13
Feature activation-9.95e-04

Pos logit contributions
pill+0.001
 minutes+0.001
 pic+0.001
storms+0.001
pler+0.001
Neg logit contributions
 captain-0.001
ble-0.001
hips-0.001
 luck-0.001
ole-0.001