TOP ACTIVATIONS
MAX = 3.348

warm and cozy in their swe aters . They fall asleep
!" To her su prise , the thunder went
candy and ride in his toy je ep . One day
can we go in the toy store ?" Her mom my
Looking back , he was su pr ised to see a
ear . Ben cried and bl ed . Lily screamed and
takes his ball and his k ite and his bike .
head . Ben cried and bl ed . Sam screamed and
dog looks at him and bl inks . Ben thinks the
them . They cried and bl ed and hurt .
back to their ball and k ite . They are happy
little helicopter and the little t eddy bear mom my ,
hurt her knee and it bl ed . L
for him - a little su gary treat . <|endoftext|> Once
got off the couch and tr ud ged out of the
we can go to the toy and book stalls ."
we can go to the toy store and the candy store
might be ruined . Daisy tr ud ged along , carrying
mom took him to a k ara oke party . There
?" Tom asked the mother k ang aroo .

MIN ACTIVATIONS
MIN = -3.389

's hands and falls on the floor . It makes a
hands . It fell on the floor and made a loud
hand . It falls on the floor and breaks into many
a rock and fell on the ground . She scrap ed
an ordinary marble lying on the ground . She picked it
noticed a penny lying on the ground near the edge of
She opened the long drawer and there was her
hand . It fell on the floor and broke into pieces
see a big paper on the table . It has a
and the water falls on the ground . L ila and
blue , yellow , green , and more .
, and it fell on the floor . It broke into
friends found some sticks on the ground .
- tap - tap on the leaf . It was a
saw a marble laying on the ground and asked his Dad
saw the shell lying on the sand . He picked it
. The sponge fell on the floor and set the kitchen
falls down and lands on the ground . It is wet
. The coin falls on the floor . It rolls under
the stones fell back on the ground , or on the

INTERVAL 1.664 - 3.348
CONTAINS 0.189%

spend the night in the k enn el .
" Hey Billy , your t eddy bear matches my ball
we can brush him and make him look handsome ."
She had brought a very y ummy treat for the star
. Lily gave him a big hug and they sn ugg

INTERVAL -0.020 - 1.664
CONTAINS 50.684%

eyes and slid down the slide . He felt
, she had a surprise for her mom ! She wanted
, Lucky went for a walk and got lost . He
too late . Anna had no more stories to tell .
be friends with the little boy . The little boy felt

INTERVAL -1.705 - -0.020
CONTAINS 48.888%

rushed to set up their camp before the sun set .
glove and put it in her pocket . She had two
" Mom , storm !" They ran back to
and liked to eat a lot . Every day
. She wears a hat . " B oys

INTERVAL -3.389 - -1.705
CONTAINS 0.239%

play with dolls and cars and books . They always shared
They pour some oil on the floor and on their cars
" I found it on the ground . Do you want
Yes , Anna . That sounds fun ." Anna
bowl slipped and fell on the floor . The dough spl
Token warm
Token ID5814
Feature activation+2.92e-01

Pos logit contributions
 before+0.013
 grant+0.013
idi+0.012
ers+0.012
ace+0.011
Neg logit contributions
und-0.017
idd-0.016
rous-0.016
rou-0.015
iw-0.015
Token and
Token ID290
Feature activation+1.14e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.015
Neg logit contributions
 before-0.006
 grant-0.005
idi-0.005
ers-0.005
 finish-0.004
Token cozy
Token ID37438
Feature activation-2.12e-02

Pos logit contributions
und+0.006
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
Token in
Token ID287
Feature activation+1.06e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.000
ers+0.000
 finish+0.000
Neg logit contributions
und-0.001
idd-0.001
rou-0.001
rous-0.001
iw-0.001
Token their
Token ID511
Feature activation+1.84e-01

Pos logit contributions
und+0.006
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.002
ers-0.002
ace-0.002
Token swe
Token ID3490
Feature activation+3.35e+00

Pos logit contributions
und+0.009
idd+0.008
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.006
 grant-0.005
idi-0.005
ers-0.005
 finish-0.004
Tokenaters
Token ID8605
Feature activation+1.73e-01

Pos logit contributions
idd+0.130
und+0.128
rol+0.126
rou+0.117
haw+0.116
Neg logit contributions
ace-0.102
 before-0.094
 eye-0.093
 be-0.093
 finish-0.093
Token.
Token ID13
Feature activation-3.26e-01

Pos logit contributions
und+0.009
idd+0.009
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.004
ers-0.003
ace-0.003
Token They
Token ID1119
Feature activation-2.75e-01

Pos logit contributions
 before+0.011
 grant+0.010
ers+0.010
idi+0.009
ace+0.009
Neg logit contributions
und-0.015
idd-0.014
rous-0.013
iw-0.013
rou-0.012
Token fall
Token ID2121
Feature activation+5.51e-01

Pos logit contributions
 before+0.009
idi+0.008
 grant+0.008
ers+0.008
ace+0.007
Neg logit contributions
und-0.012
idd-0.011
rou-0.011
rous-0.011
iw-0.010
Token asleep
Token ID16039
Feature activation-4.05e-02

Pos logit contributions
und+0.023
idd+0.021
rous+0.020
iw+0.019
rou+0.019
Neg logit contributions
 before-0.022
 grant-0.019
idi-0.018
ers-0.018
ace-0.018
Token!"
Token ID2474
Feature activation-1.07e-01

Pos logit contributions
und+0.033
idd+0.031
rous+0.029
iw+0.028
rou+0.028
Neg logit contributions
 before-0.032
 grant-0.028
ers-0.026
idi-0.026
 finish-0.025
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.006
idd-0.005
rous-0.005
iw-0.005
rou-0.005
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
 before+0.007
 grant+0.006
idi+0.006
ers+0.005
ace+0.005
Neg logit contributions
und-0.012
idd-0.010
rous-0.010
rou-0.010
rol-0.010
TokenTo
Token ID2514
Feature activation-3.17e-01

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.004
ers+0.004
ace+0.004
Neg logit contributions
und-0.014
idd-0.013
rous-0.012
rou-0.012
iw-0.012
Token her
Token ID607
Feature activation+3.29e-02

Pos logit contributions
 before+0.009
 grant+0.008
idi+0.008
ers+0.008
ace+0.007
Neg logit contributions
und-0.016
idd-0.014
rous-0.013
rol-0.013
rou-0.013
Token su
Token ID424
Feature activation+3.33e+00

Pos logit contributions
und+0.001
idd+0.001
rous+0.001
rou+0.001
iw+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Tokenprise
Token ID7919
Feature activation+8.42e-01

Pos logit contributions
und+0.106
ays+0.104
idd+0.095
rou+0.095
 Sorry+0.093
Neg logit contributions
In-0.122
The-0.122
ers-0.117
 before-0.111
 finish-0.110
Token,
Token ID11
Feature activation-1.33e-01

Pos logit contributions
und+0.040
idd+0.038
iw+0.036
rous+0.036
rou+0.035
Neg logit contributions
 before-0.028
 grant-0.024
idi-0.023
ers-0.022
 finish-0.022
Token the
Token ID262
Feature activation-1.85e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.008
idd-0.008
rous-0.007
rou-0.007
iw-0.007
Token thunder
Token ID18355
Feature activation-6.31e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.008
idd-0.008
rou-0.007
rous-0.007
iw-0.007
Token went
Token ID1816
Feature activation+6.70e-01

Pos logit contributions
 before+0.020
 grant+0.020
idi+0.018
ace+0.018
ers+0.017
Neg logit contributions
und-0.030
idd-0.027
rou-0.024
rol-0.024
rous-0.024
Token candy
Token ID18550
Feature activation+8.66e-01

Pos logit contributions
und+0.032
idd+0.030
rou+0.028
rous+0.028
rol+0.028
Neg logit contributions
 before-0.022
 grant-0.019
idi-0.018
ers-0.018
 finish-0.017
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
und+0.050
idd+0.048
rous+0.046
rou+0.045
rol+0.045
Neg logit contributions
 before-0.021
ers-0.016
 grant-0.015
idi-0.014
 finish-0.014
Token ride
Token ID6594
Feature activation-3.93e-01

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.008
idd-0.007
iw-0.006
rous-0.006
rou-0.006
Token in
Token ID287
Feature activation+4.41e-01

Pos logit contributions
 grant+0.013
 before+0.012
idi+0.011
ace+0.011
 finish+0.010
Neg logit contributions
und-0.018
idd-0.016
rous-0.016
iw-0.015
rol-0.015
Token his
Token ID465
Feature activation+1.26e+00

Pos logit contributions
und+0.029
idd+0.028
rou+0.027
rol+0.027
rous+0.026
Neg logit contributions
 before-0.006
 grant-0.005
idi-0.004
ers-0.003
 finish-0.003
Token toy
Token ID13373
Feature activation+3.25e+00

Pos logit contributions
und+0.069
rol+0.067
idd+0.064
rou+0.062
ays+0.060
Neg logit contributions
 before-0.028
idi-0.027
 finish-0.026
 floor-0.025
 shelf-0.024
Token je
Token ID11223
Feature activation+1.61e+00

Pos logit contributions
rou+0.180
und+0.166
rol+0.162
itting+0.154
unch+0.153
Neg logit contributions
 shelf-0.077
 before-0.074
 other-0.073
 floor-0.072
ers-0.066
Tokenep
Token ID538
Feature activation-4.82e-02

Pos logit contributions
und+0.071
idd+0.064
 Sorry+0.063
 Enjoy+0.063
ays+0.063
Neg logit contributions
ers-0.051
 before-0.048
idi-0.044
The-0.043
 entire-0.042
Token.
Token ID13
Feature activation+3.18e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
 finish+0.001
Neg logit contributions
und-0.003
idd-0.002
rous-0.002
rol-0.002
rou-0.002
Token One
Token ID1881
Feature activation-5.26e-01

Pos logit contributions
und+0.016
idd+0.015
rous+0.014
rou+0.014
rol+0.013
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.008
ers-0.008
 finish-0.008
Token day
Token ID1110
Feature activation+3.22e-01

Pos logit contributions
 grant+0.017
 before+0.017
ers+0.015
idi+0.015
ace+0.015
Neg logit contributions
und-0.023
idd-0.022
rous-0.021
rou-0.020
iw-0.020
Token can
Token ID460
Feature activation-3.49e-01

Pos logit contributions
 before+0.009
idi+0.008
 grant+0.008
ers+0.008
ace+0.007
Neg logit contributions
und-0.011
idd-0.010
rou-0.010
rous-0.010
iw-0.009
Token we
Token ID356
Feature activation+2.56e-01

Pos logit contributions
 before+0.013
idi+0.012
 grant+0.012
ers+0.012
ace+0.011
Neg logit contributions
und-0.014
idd-0.013
rous-0.012
iw-0.012
 Sorry-0.012
Token go
Token ID467
Feature activation+3.42e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
iw+0.012
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.005
ers-0.005
 finish-0.005
Token in
Token ID287
Feature activation+7.42e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.014
Neg logit contributions
 before-0.011
 grant-0.009
idi-0.009
ers-0.008
 finish-0.008
Token the
Token ID262
Feature activation+1.58e+00

Pos logit contributions
und+0.044
idd+0.042
rol+0.040
rou+0.040
iw+0.040
Neg logit contributions
 before-0.016
 grant-0.012
idi-0.011
 finish-0.011
ers-0.010
Token toy
Token ID13373
Feature activation+3.15e+00

Pos logit contributions
und+0.074
unch+0.070
idd+0.069
rou+0.068
rol+0.065
Neg logit contributions
 finish-0.050
 before-0.049
 floor-0.046
 corner-0.046
 ground-0.045
Token store
Token ID3650
Feature activation+8.35e-01

Pos logit contributions
und+0.172
unch+0.168
beh+0.166
rou+0.166
haw+0.164
Neg logit contributions
 before-0.087
 finish-0.076
 end-0.067
 floor-0.067
 shelf-0.066
Token?"
Token ID1701
Feature activation+1.37e-01

Pos logit contributions
und+0.040
idd+0.037
rol+0.035
iw+0.034
rous+0.034
Neg logit contributions
 before-0.029
 grant-0.024
 finish-0.023
idi-0.022
ers-0.022
Token Her
Token ID2332
Feature activation+6.32e-02

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.004
ers-0.003
ace-0.003
Token mom
Token ID1995
Feature activation+5.22e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Tokenmy
Token ID1820
Feature activation+2.70e-01

Pos logit contributions
und+0.023
idd+0.020
rous+0.019
iw+0.019
rol+0.019
Neg logit contributions
 before-0.020
 grant-0.018
idi-0.017
ers-0.016
 had-0.016
Token Looking
Token ID15616
Feature activation+3.59e-01

Pos logit contributions
 before+0.013
 grant+0.012
idi+0.011
ers+0.011
ace+0.011
Neg logit contributions
und-0.018
idd-0.017
uck-0.015
rou-0.015
rous-0.015
Token back
Token ID736
Feature activation+4.27e-01

Pos logit contributions
und+0.018
idd+0.017
rous+0.015
rou+0.015
iw+0.015
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
 finish-0.009
Token,
Token ID11
Feature activation+5.52e-03

Pos logit contributions
und+0.022
idd+0.020
rou+0.019
rol+0.019
rous+0.019
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.010
ers-0.010
 finish-0.010
Token he
Token ID339
Feature activation-3.17e-01

Pos logit contributions
und+0.000
idd+0.000
rous+0.000
rou+0.000
iw+0.000
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
ace-0.000
Token was
Token ID373
Feature activation-5.07e-01

Pos logit contributions
 before+0.012
 grant+0.012
ace+0.011
ers+0.011
idi+0.011
Neg logit contributions
und-0.013
idd-0.012
rou-0.011
rous-0.011
iw-0.010
Token su
Token ID424
Feature activation+3.09e+00

Pos logit contributions
 grant+0.018
 before+0.018
idi+0.016
ers+0.016
ace+0.016
Neg logit contributions
und-0.021
idd-0.020
rou-0.019
rous-0.018
rol-0.017
Tokenpr
Token ID1050
Feature activation+1.15e+00

Pos logit contributions
und+0.100
ays+0.090
 Enjoy+0.088
 Sorry+0.086
 sorts+0.081
Neg logit contributions
The-0.120
 before-0.116
In-0.114
isy-0.113
ers-0.112
Tokenised
Token ID1417
Feature activation+9.40e-02

Pos logit contributions
und+0.039
idd+0.038
 Enjoy+0.035
iw+0.035
 Sorry+0.035
Neg logit contributions
 before-0.046
 grant-0.043
ace-0.042
idi-0.042
 entire-0.041
Token to
Token ID284
Feature activation-4.54e-01

Pos logit contributions
und+0.005
idd+0.005
rou+0.004
rous+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token see
Token ID766
Feature activation+8.86e-01

Pos logit contributions
 before+0.011
ers+0.011
idi+0.010
 grant+0.010
ace+0.010
Neg logit contributions
und-0.023
idd-0.021
rous-0.020
 Enjoy-0.020
iw-0.020
Token a
Token ID257
Feature activation+5.17e-01

Pos logit contributions
und+0.046
idd+0.044
rol+0.041
rous+0.041
iw+0.041
Neg logit contributions
 before-0.026
 grant-0.022
idi-0.019
ers-0.019
 had-0.018
Token ear
Token ID1027
Feature activation+2.03e-02

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
 finish+0.003
Neg logit contributions
und-0.006
idd-0.006
rou-0.005
rous-0.005
iw-0.005
Token.
Token ID13
Feature activation-6.70e-01

Pos logit contributions
und+0.001
idd+0.001
rou+0.001
rous+0.001
rol+0.001
Neg logit contributions
 before-0.001
 grant-0.000
idi-0.000
ers-0.000
 finish-0.000
Token Ben
Token ID3932
Feature activation-3.44e-01

Pos logit contributions
 before+0.021
 grant+0.020
ace+0.019
idi+0.019
ers+0.018
Neg logit contributions
und-0.031
idd-0.028
ays-0.027
iw-0.026
uck-0.026
Token cried
Token ID16896
Feature activation+6.20e-01

Pos logit contributions
 before+0.011
 grant+0.010
idi+0.010
ace+0.009
ers+0.009
Neg logit contributions
und-0.016
idd-0.015
rou-0.013
iw-0.013
rol-0.013
Token and
Token ID290
Feature activation+9.69e-01

Pos logit contributions
und+0.037
idd+0.035
rous+0.034
iw+0.033
rou+0.032
Neg logit contributions
 before-0.015
 grant-0.011
ers-0.010
ace-0.010
idi-0.010
Token bl
Token ID698
Feature activation+3.09e+00

Pos logit contributions
und+0.049
idd+0.047
rous+0.046
rou+0.044
rol+0.044
Neg logit contributions
 before-0.029
 grant-0.026
 had-0.024
idi-0.024
 finish-0.023
Tokened
Token ID276
Feature activation+1.24e+00

Pos logit contributions
aman+0.151
rous+0.149
 batch+0.148
 Enjoy+0.141
und+0.137
Neg logit contributions
 had-0.074
ace-0.069
ers-0.067
 forgot-0.067
piece-0.066
Token.
Token ID13
Feature activation-9.55e-01

Pos logit contributions
und+0.080
idd+0.080
rous+0.076
iw+0.076
unch+0.075
Neg logit contributions
 before-0.024
 had-0.013
ers-0.013
 grant-0.012
idi-0.012
Token Lily
Token ID20037
Feature activation-6.82e-01

Pos logit contributions
 grant+0.033
 before+0.033
ace+0.030
ers+0.029
isy+0.029
Neg logit contributions
und-0.042
idd-0.037
uck-0.034
ays-0.034
iw-0.034
Token screamed
Token ID25421
Feature activation+1.11e+00

Pos logit contributions
 before+0.020
 grant+0.019
idi+0.018
ace+0.017
 entire+0.017
Neg logit contributions
und-0.033
idd-0.030
rou-0.028
iw-0.027
uck-0.027
Token and
Token ID290
Feature activation+9.71e-01

Pos logit contributions
und+0.072
idd+0.070
rous+0.068
iw+0.067
rol+0.065
Neg logit contributions
 before-0.023
 grant-0.014
 finish-0.012
 had-0.012
ace-0.011
Token takes
Token ID2753
Feature activation+2.31e-01

Pos logit contributions
und+0.021
idd+0.020
rous+0.018
rol+0.018
rou+0.018
Neg logit contributions
 before-0.019
 grant-0.018
idi-0.017
ers-0.016
 finish-0.016
Token his
Token ID465
Feature activation-1.73e-01

Pos logit contributions
und+0.012
idd+0.011
rous+0.011
rou+0.011
iw+0.011
Neg logit contributions
 before-0.006
 grant-0.006
idi-0.005
ers-0.005
 finish-0.005
Token ball
Token ID2613
Feature activation+6.44e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.008
idd-0.007
rous-0.007
iw-0.006
rou-0.006
Token and
Token ID290
Feature activation+4.48e-01

Pos logit contributions
und+0.040
idd+0.037
rous+0.036
rou+0.035
rol+0.035
Neg logit contributions
 before-0.013
 grant-0.010
 finish-0.008
ers-0.008
idi-0.008
Token his
Token ID465
Feature activation+2.92e-01

Pos logit contributions
und+0.020
idd+0.019
rous+0.017
rou+0.017
rol+0.017
Neg logit contributions
 before-0.016
 grant-0.014
idi-0.014
ers-0.013
 finish-0.013
Token k
Token ID479
Feature activation+3.09e+00

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
rol+0.012
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.008
ers-0.008
 finish-0.008
Tokenite
Token ID578
Feature activation+3.32e-01

Pos logit contributions
aman+0.122
und+0.114
arre+0.108
rol+0.104
rous+0.103
Neg logit contributions
ace-0.092
 before-0.086
ers-0.085
 be-0.083
 eight-0.083
Token and
Token ID290
Feature activation+2.34e-01

Pos logit contributions
und+0.019
idd+0.018
rous+0.017
rou+0.016
iw+0.016
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token his
Token ID465
Feature activation+3.65e-02

Pos logit contributions
und+0.011
idd+0.010
rous+0.009
rou+0.009
iw+0.009
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.007
 finish-0.006
Token bike
Token ID7161
Feature activation+8.72e-01

Pos logit contributions
und+0.002
idd+0.002
rous+0.001
rou+0.001
iw+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
und+0.053
idd+0.051
rous+0.049
rol+0.047
rou+0.047
Neg logit contributions
 before-0.019
 grant-0.014
ers-0.013
 finish-0.013
 had-0.012
Token head
Token ID1182
Feature activation+3.98e-01

Pos logit contributions
idi+0.065
 before+0.057
In+0.053
 grant+0.053
etta+0.053
Neg logit contributions
und-0.098
idd-0.092
 batch-0.089
rou-0.087
ays-0.082
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
und+0.023
idd+0.021
rous+0.020
rou+0.020
iw+0.020
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.007
ers-0.007
 finish-0.006
Token Ben
Token ID3932
Feature activation-3.70e-01

Pos logit contributions
 before+0.011
 grant+0.010
idi+0.010
ers+0.009
ace+0.009
Neg logit contributions
und-0.018
idd-0.017
iw-0.015
ays-0.015
rous-0.015
Token cried
Token ID16896
Feature activation+5.49e-01

Pos logit contributions
 before+0.013
 grant+0.012
idi+0.012
ace+0.011
ers+0.011
Neg logit contributions
und-0.016
idd-0.015
rou-0.013
iw-0.013
ays-0.013
Token and
Token ID290
Feature activation+7.33e-01

Pos logit contributions
und+0.032
idd+0.031
rous+0.029
iw+0.029
rol+0.028
Neg logit contributions
 before-0.013
 grant-0.010
ace-0.009
idi-0.009
 finish-0.009
Token bl
Token ID698
Feature activation+3.06e+00

Pos logit contributions
und+0.034
idd+0.032
rous+0.030
rou+0.029
rol+0.029
Neg logit contributions
 before-0.025
 grant-0.023
idi-0.021
 had-0.021
 finish-0.020
Tokened
Token ID276
Feature activation+1.34e+00

Pos logit contributions
aman+0.148
 batch+0.144
rous+0.141
 course+0.137
 Enjoy+0.135
Neg logit contributions
 had-0.077
piece-0.074
 forgot-0.071
ace-0.071
 before-0.065
Token.
Token ID13
Feature activation-6.41e-01

Pos logit contributions
idd+0.087
und+0.086
rous+0.083
iw+0.082
unch+0.082
Neg logit contributions
 before-0.025
 had-0.012
 finish-0.012
 grant-0.012
ers-0.012
Token Sam
Token ID3409
Feature activation-4.14e-01

Pos logit contributions
 before+0.021
 grant+0.020
ers+0.018
ace+0.018
idi+0.018
Neg logit contributions
und-0.030
idd-0.027
iw-0.025
uck-0.024
rous-0.024
Token screamed
Token ID25421
Feature activation+1.22e+00

Pos logit contributions
 before+0.014
 grant+0.012
idi+0.012
ace+0.011
ers+0.011
Neg logit contributions
und-0.019
idd-0.018
rou-0.016
iw-0.016
rol-0.016
Token and
Token ID290
Feature activation+6.71e-01

Pos logit contributions
und+0.082
idd+0.080
rous+0.079
iw+0.078
rol+0.075
Neg logit contributions
 before-0.022
 grant-0.012
 finish-0.011
 had-0.010
ace-0.008
Token dog
Token ID3290
Feature activation+8.05e-01

Pos logit contributions
und+0.039
idd+0.035
rol+0.034
rous+0.033
iw+0.033
Neg logit contributions
 before-0.025
 grant-0.023
idi-0.022
 had-0.021
 finish-0.021
Token looks
Token ID3073
Feature activation+1.26e+00

Pos logit contributions
und+0.037
idd+0.034
rous+0.032
rou+0.031
rol+0.031
Neg logit contributions
 before-0.028
 grant-0.026
idi-0.025
ers-0.023
 had-0.023
Token at
Token ID379
Feature activation+2.50e-01

Pos logit contributions
und+0.056
idd+0.052
rol+0.046
rou+0.046
iw+0.046
Neg logit contributions
 before-0.048
idi-0.042
 grant-0.041
 had-0.040
 finish-0.038
Token him
Token ID683
Feature activation+3.09e-01

Pos logit contributions
und+0.013
idd+0.012
rous+0.012
rou+0.011
iw+0.011
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
ace-0.005
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.015
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.005
Token bl
Token ID698
Feature activation+3.06e+00

Pos logit contributions
und+0.051
idd+0.049
rol+0.045
rous+0.044
rou+0.043
Neg logit contributions
 before-0.036
 grant-0.033
idi-0.031
 had-0.029
 finish-0.029
Tokeninks
Token ID2973
Feature activation+7.91e-01

Pos logit contributions
und+0.130
 batch+0.127
aman+0.127
 course+0.118
idd+0.118
Neg logit contributions
piece-0.088
ia-0.084
ace-0.083
 before-0.083
mit-0.076
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
und+0.044
idd+0.042
rous+0.040
iw+0.040
rou+0.039
Neg logit contributions
 before-0.020
 grant-0.017
idi-0.015
ers-0.015
ace-0.014
Token Ben
Token ID3932
Feature activation-6.14e-02

Pos logit contributions
 before+0.013
 grant+0.012
ace+0.011
idi+0.011
ers+0.011
Neg logit contributions
und-0.020
idd-0.019
ays-0.017
iw-0.017
rous-0.017
Token thinks
Token ID6834
Feature activation-5.38e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.003
idd-0.003
rou-0.002
rous-0.002
iw-0.002
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
 grant+0.017
 before+0.016
idi+0.016
ace+0.015
 entire+0.015
Neg logit contributions
und-0.023
idd-0.022
rou-0.021
iw-0.021
rous-0.020
Token them
Token ID606
Feature activation+1.22e+00

Pos logit contributions
 grant+0.007
 before+0.007
idi+0.007
ers+0.006
ace+0.006
Neg logit contributions
und-0.010
idd-0.009
ays-0.009
rous-0.008
rol-0.008
Token.
Token ID13
Feature activation-3.01e-01

Pos logit contributions
und+0.073
idd+0.072
rous+0.069
iw+0.069
rou+0.067
Neg logit contributions
 before-0.028
 grant-0.019
 finish-0.019
ace-0.017
ers-0.017
Token They
Token ID1119
Feature activation-2.70e-01

Pos logit contributions
 before+0.009
 grant+0.008
idi+0.008
ers+0.007
ace+0.007
Neg logit contributions
und-0.015
idd-0.014
ays-0.013
iw-0.013
rous-0.013
Token cried
Token ID16896
Feature activation+4.04e-01

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.009
ers+0.008
ace+0.008
Neg logit contributions
und-0.012
idd-0.011
iw-0.010
rou-0.010
rol-0.010
Token and
Token ID290
Feature activation+6.36e-01

Pos logit contributions
und+0.024
idd+0.022
rous+0.021
iw+0.021
rou+0.021
Neg logit contributions
 before-0.009
 grant-0.007
idi-0.007
ers-0.006
ace-0.006
Token bl
Token ID698
Feature activation+3.02e+00

Pos logit contributions
und+0.030
idd+0.028
rous+0.027
rou+0.026
iw+0.026
Neg logit contributions
 before-0.021
 grant-0.020
idi-0.018
 had-0.018
 finish-0.017
Tokened
Token ID276
Feature activation+1.11e+00

Pos logit contributions
aman+0.143
rous+0.141
 batch+0.141
 course+0.134
 Enjoy+0.132
Neg logit contributions
 had-0.072
ace-0.071
piece-0.070
 forgot-0.069
ers-0.067
Token and
Token ID290
Feature activation+7.36e-01

Pos logit contributions
und+0.069
idd+0.068
rous+0.065
iw+0.064
unch+0.063
Neg logit contributions
 before-0.023
 grant-0.014
ers-0.014
 had-0.014
ace-0.013
Token hurt
Token ID5938
Feature activation+9.25e-02

Pos logit contributions
und+0.036
idd+0.034
rous+0.032
rou+0.031
rol+0.031
Neg logit contributions
 before-0.024
 grant-0.021
 had-0.020
idi-0.020
 finish-0.019
Token.
Token ID13
Feature activation-7.83e-01

Pos logit contributions
und+0.005
idd+0.005
rous+0.004
rou+0.004
rol+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
 finish-0.002
Token
Token ID198
Feature activation-6.00e-01

Pos logit contributions
 before+0.028
 grant+0.026
idi+0.025
ers+0.024
isy+0.023
Neg logit contributions
und-0.035
idd-0.031
ays-0.028
iw-0.028
 Sorry-0.028
Token back
Token ID736
Feature activation+3.19e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.015
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.010
 finish-0.010
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
rol+0.015
Neg logit contributions
 before-0.009
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token their
Token ID511
Feature activation+6.75e-01

Pos logit contributions
und+0.074
idd+0.071
rol+0.070
rou+0.067
iw+0.066
Neg logit contributions
 before-0.026
 grant-0.020
 finish-0.018
idi-0.018
 the-0.017
Token ball
Token ID2613
Feature activation+9.43e-01

Pos logit contributions
und+0.034
idd+0.031
rol+0.030
rou+0.029
iw+0.029
Neg logit contributions
 before-0.021
 grant-0.018
idi-0.017
 finish-0.017
 floor-0.016
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
und+0.057
idd+0.054
rous+0.052
rou+0.051
rol+0.050
Neg logit contributions
 before-0.021
 grant-0.015
ers-0.014
 finish-0.014
idi-0.013
Token k
Token ID479
Feature activation+2.99e+00

Pos logit contributions
 before+0.016
 grant+0.015
idi+0.014
ers+0.014
ace+0.014
Neg logit contributions
und-0.023
idd-0.021
rous-0.020
iw-0.020
rou-0.019
Tokenite
Token ID578
Feature activation+6.53e-01

Pos logit contributions
aman+0.107
und+0.106
 batch+0.100
OO+0.097
 Good+0.096
Neg logit contributions
The-0.097
ers-0.091
 before-0.087
ars-0.082
oster-0.077
Token.
Token ID13
Feature activation-4.56e-01

Pos logit contributions
und+0.037
idd+0.035
rous+0.033
rou+0.033
iw+0.033
Neg logit contributions
 before-0.016
 grant-0.013
ers-0.012
idi-0.011
 finish-0.011
Token They
Token ID1119
Feature activation-2.90e-01

Pos logit contributions
 before+0.016
 grant+0.015
ers+0.014
idi+0.014
ace+0.013
Neg logit contributions
und-0.021
idd-0.019
 Enjoy-0.017
iw-0.017
ays-0.017
Token are
Token ID389
Feature activation-3.31e-01

Pos logit contributions
 before+0.009
idi+0.008
 grant+0.008
ers+0.008
ace+0.007
Neg logit contributions
und-0.014
idd-0.013
rou-0.012
rous-0.012
iw-0.012
Token happy
Token ID3772
Feature activation+2.63e-01

Pos logit contributions
 before+0.012
 grant+0.012
idi+0.011
ers+0.010
ace+0.010
Neg logit contributions
und-0.014
idd-0.013
rou-0.012
rous-0.012
rol-0.012
Token little
Token ID1310
Feature activation+6.66e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.013
rou+0.012
iw+0.012
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token helicopter
Token ID15392
Feature activation+6.02e-01

Pos logit contributions
und+0.035
idd+0.032
rou+0.031
rol+0.030
rous+0.030
Neg logit contributions
 before-0.020
 grant-0.017
idi-0.015
 finish-0.015
ers-0.015
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
und+0.028
idd+0.026
rous+0.025
rou+0.024
iw+0.024
Neg logit contributions
 before-0.020
 grant-0.018
idi-0.017
ers-0.016
 finish-0.016
Token the
Token ID262
Feature activation-4.77e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
iw+0.012
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token little
Token ID1310
Feature activation+8.59e-01

Pos logit contributions
 before+0.013
 grant+0.011
idi+0.011
ers+0.010
ace+0.010
Neg logit contributions
und-0.024
idd-0.023
rou-0.021
rous-0.021
rol-0.021
Token t
Token ID256
Feature activation+2.92e+00

Pos logit contributions
und+0.047
idd+0.043
rou+0.041
rol+0.041
rous+0.041
Neg logit contributions
 before-0.023
 grant-0.020
idi-0.018
 finish-0.018
 had-0.018
Tokeneddy
Token ID21874
Feature activation+4.23e-01

Pos logit contributions
rous+0.130
und+0.126
 Enjoy+0.125
iw+0.124
 batch+0.123
Neg logit contributions
ace-0.077
ers-0.069
 entire-0.066
 grant-0.065
The-0.065
Token bear
Token ID6842
Feature activation+9.08e-01

Pos logit contributions
und+0.023
idd+0.022
rous+0.020
rou+0.020
iw+0.020
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
ace-0.008
Token mom
Token ID1995
Feature activation+7.95e-01

Pos logit contributions
und+0.043
idd+0.040
rous+0.038
iw+0.037
rou+0.037
Neg logit contributions
 before-0.030
 grant-0.027
idi-0.024
ers-0.024
 finish-0.024
Tokenmy
Token ID1820
Feature activation+1.08e+00

Pos logit contributions
und+0.037
idd+0.035
rous+0.033
iw+0.032
rou+0.032
Neg logit contributions
 before-0.027
 grant-0.024
idi-0.022
ers-0.022
 had-0.022
Token,
Token ID11
Feature activation+5.10e-01

Pos logit contributions
und+0.051
idd+0.047
rous+0.045
iw+0.044
rou+0.043
Neg logit contributions
 before-0.036
 grant-0.033
ers-0.029
 had-0.029
idi-0.029
Token hurt
Token ID5938
Feature activation+1.08e-01

Pos logit contributions
 before+0.011
 grant+0.011
idi+0.010
ers+0.010
ace+0.010
Neg logit contributions
und-0.013
idd-0.012
rou-0.011
iw-0.011
rous-0.011
Token her
Token ID607
Feature activation-3.43e-01

Pos logit contributions
und+0.006
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
 finish-0.002
Token knee
Token ID10329
Feature activation+5.72e-01

Pos logit contributions
 before+0.011
 grant+0.011
idi+0.011
ers+0.010
 finish+0.009
Neg logit contributions
und-0.015
idd-0.014
rou-0.013
rous-0.013
iw-0.013
Token and
Token ID290
Feature activation+4.16e-01

Pos logit contributions
und+0.034
idd+0.033
rous+0.031
iw+0.030
rol+0.030
Neg logit contributions
 before-0.012
 grant-0.010
idi-0.008
ers-0.008
 finish-0.008
Token it
Token ID340
Feature activation+4.81e-01

Pos logit contributions
und+0.020
idd+0.019
rous+0.018
rou+0.018
rol+0.018
Neg logit contributions
 before-0.013
 grant-0.012
idi-0.011
ers-0.010
 finish-0.010
Token bl
Token ID698
Feature activation+2.92e+00

Pos logit contributions
und+0.026
idd+0.025
rous+0.023
iw+0.023
rou+0.023
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.010
ers-0.010
 finish-0.010
Tokened
Token ID276
Feature activation+1.79e+00

Pos logit contributions
 batch+0.142
aman+0.139
rous+0.136
und+0.134
 sorts+0.130
Neg logit contributions
ace-0.071
 before-0.068
 had-0.068
piece-0.066
kin-0.065
Token.
Token ID13
Feature activation-7.26e-02

Pos logit contributions
idd+0.112
und+0.111
rous+0.105
iw+0.105
unch+0.104
Neg logit contributions
 before-0.040
 had-0.027
ers-0.023
 the-0.023
ace-0.022
Token
Token ID198
Feature activation-5.63e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.004
idd-0.003
rous-0.003
iw-0.003
rou-0.003
Token
Token ID198
Feature activation-5.89e-01

Pos logit contributions
 before+0.018
 grant+0.017
idi+0.016
ers+0.015
ace+0.015
Neg logit contributions
und-0.027
idd-0.024
rous-0.022
rou-0.022
iw-0.022
TokenL
Token ID43
Feature activation-2.53e-01

Pos logit contributions
 before+0.019
 grant+0.017
ace+0.016
idi+0.015
ers+0.015
Neg logit contributions
und-0.029
idd-0.026
rous-0.024
uck-0.024
rou-0.023
Token for
Token ID329
Feature activation+8.61e-02

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.005
idd-0.004
rous-0.004
rou-0.004
iw-0.004
Token him
Token ID683
Feature activation-3.49e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token -
Token ID532
Feature activation+5.63e-01

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.009
ers+0.008
ace+0.008
Neg logit contributions
und-0.017
idd-0.016
rou-0.015
rous-0.015
iw-0.015
Token a
Token ID257
Feature activation+1.13e-01

Pos logit contributions
und+0.029
idd+0.028
rous+0.026
rou+0.025
rol+0.025
Neg logit contributions
 before-0.016
 grant-0.014
idi-0.013
ers-0.012
 finish-0.012
Token little
Token ID1310
Feature activation+1.08e+00

Pos logit contributions
und+0.005
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.004
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
Token su
Token ID424
Feature activation+2.91e+00

Pos logit contributions
und+0.056
idd+0.051
rol+0.048
rous+0.048
ays+0.048
Neg logit contributions
 before-0.033
 grant-0.029
idi-0.026
 finish-0.026
 had-0.025
Tokengary
Token ID14849
Feature activation+3.11e-01

Pos logit contributions
und+0.113
ays+0.099
 Sorry+0.091
 afar+0.088
bat+0.087
Neg logit contributions
ers-0.102
 before-0.100
isy-0.099
 grant-0.095
The-0.093
Token treat
Token ID2190
Feature activation+2.75e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
rol+0.012
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
 finish-0.009
Token.
Token ID13
Feature activation+6.26e-02

Pos logit contributions
und+0.012
idd+0.011
rous+0.010
rou+0.010
iw+0.010
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.009
ers-0.008
 finish-0.008
Token<|endoftext|>
Token ID50256
Feature activation-4.07e-01

Pos logit contributions
und+0.003
idd+0.003
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.001
ace-0.001
TokenOnce
Token ID7454
Feature activation-3.33e-02

Pos logit contributions
 before+0.016
 grant+0.015
idi+0.014
ace+0.014
 finish+0.014
Neg logit contributions
und-0.017
idd-0.015
rol-0.013
iw-0.013
ays-0.013
Token got
Token ID1392
Feature activation+5.75e-01

Pos logit contributions
und+0.022
idd+0.021
rous+0.019
rou+0.019
iw+0.019
Neg logit contributions
 before-0.015
 grant-0.013
idi-0.013
ers-0.012
 finish-0.012
Token off
Token ID572
Feature activation-2.94e-01

Pos logit contributions
und+0.031
idd+0.028
rou+0.027
iw+0.026
rous+0.026
Neg logit contributions
 before-0.016
 grant-0.014
idi-0.013
 finish-0.012
ers-0.012
Token the
Token ID262
Feature activation-2.07e-01

Pos logit contributions
 before+0.007
 grant+0.007
idi+0.006
ace+0.006
ers+0.006
Neg logit contributions
und-0.016
idd-0.015
rous-0.014
rou-0.014
iw-0.014
Token couch
Token ID18507
Feature activation+1.28e+00

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.010
idd-0.009
rous-0.009
rou-0.009
 batch-0.009
Token and
Token ID290
Feature activation+8.26e-01

Pos logit contributions
und+0.078
idd+0.077
rous+0.074
iw+0.072
rou+0.072
Neg logit contributions
 before-0.026
 grant-0.018
ers-0.016
 finish-0.016
idi-0.016
Token tr
Token ID491
Feature activation+2.89e+00

Pos logit contributions
und+0.044
idd+0.041
rous+0.039
rou+0.039
iw+0.039
Neg logit contributions
 before-0.024
 grant-0.019
idi-0.019
 had-0.018
 finish-0.018
Tokenud
Token ID463
Feature activation+4.39e-01

Pos logit contributions
 Sorry+0.087
 Enjoy+0.081
haw+0.080
iw+0.075
cient+0.074
Neg logit contributions
idi-0.107
ace-0.104
 before-0.099
piece-0.097
ers-0.096
Tokenged
Token ID2004
Feature activation+9.78e-01

Pos logit contributions
und+0.016
idd+0.014
rous+0.013
iw+0.013
rou+0.013
Neg logit contributions
 before-0.020
 grant-0.018
idi-0.017
ers-0.017
ace-0.017
Token out
Token ID503
Feature activation-2.14e-01

Pos logit contributions
und+0.049
idd+0.047
iw+0.044
rou+0.044
ays+0.044
Neg logit contributions
 before-0.031
idi-0.025
ers-0.024
 grant-0.024
 had-0.023
Token of
Token ID286
Feature activation+8.72e-01

Pos logit contributions
 before+0.006
 grant+0.005
idi+0.005
ers+0.004
ace+0.004
Neg logit contributions
und-0.011
idd-0.010
rou-0.010
rous-0.010
rol-0.010
Token the
Token ID262
Feature activation+1.94e-01

Pos logit contributions
und+0.057
idd+0.055
rou+0.052
unch+0.052
iw+0.051
Neg logit contributions
 before-0.014
idi-0.010
 grant-0.009
 finish-0.008
ers-0.008
Token we
Token ID356
Feature activation+9.77e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.004
idd-0.004
rous-0.004
rou-0.004
iw-0.004
Token can
Token ID460
Feature activation+4.28e-01

Pos logit contributions
und+0.052
idd+0.048
rous+0.047
rou+0.045
rol+0.045
Neg logit contributions
 before-0.027
 grant-0.024
 finish-0.023
 had-0.021
ace-0.021
Token go
Token ID467
Feature activation+5.18e-01

Pos logit contributions
und+0.025
idd+0.023
rous+0.022
rou+0.022
iw+0.022
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.008
 finish-0.007
ers-0.007
Token to
Token ID284
Feature activation-8.81e-02

Pos logit contributions
und+0.027
idd+0.025
rous+0.024
rou+0.024
iw+0.024
Neg logit contributions
 before-0.015
 grant-0.012
idi-0.012
 finish-0.011
ers-0.011
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
 before+0.002
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.005
idd-0.005
rous-0.005
rou-0.005
iw-0.005
Token toy
Token ID13373
Feature activation+2.87e+00

Pos logit contributions
und+0.050
idd+0.045
rol+0.042
unch+0.042
ays+0.042
Neg logit contributions
 before-0.035
 finish-0.031
 grant-0.031
idi-0.030
 floor-0.030
Token and
Token ID290
Feature activation-6.98e-01

Pos logit contributions
und+0.159
unch+0.158
rou+0.154
rol+0.150
idd+0.146
Neg logit contributions
 before-0.085
 finish-0.070
 shelf-0.066
 floor-0.064
 end-0.064
Token book
Token ID1492
Feature activation+1.04e+00

Pos logit contributions
 before+0.018
 grant+0.017
idi+0.017
ers+0.017
ace+0.016
Neg logit contributions
und-0.034
idd-0.032
rous-0.030
 Enjoy-0.030
iw-0.030
Token stalls
Token ID40308
Feature activation+2.13e-01

Pos logit contributions
und+0.055
idd+0.052
rous+0.049
rou+0.048
iw+0.048
Neg logit contributions
 before-0.031
ers-0.025
 grant-0.024
 finish-0.024
idi-0.023
Token."
Token ID526
Feature activation-7.11e-01

Pos logit contributions
und+0.012
idd+0.011
rous+0.010
rou+0.010
iw+0.010
Neg logit contributions
 before-0.005
 grant-0.005
idi-0.005
ers-0.004
 finish-0.004
Token
Token ID198
Feature activation-5.04e-01

Pos logit contributions
 before+0.024
 grant+0.024
ers+0.022
ace+0.022
idi+0.022
Neg logit contributions
und-0.030
idd-0.027
iw-0.027
ays-0.026
 batch-0.026
Token we
Token ID356
Feature activation+7.41e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.004
idd-0.003
rou-0.003
rous-0.003
iw-0.003
Token can
Token ID460
Feature activation+1.73e-01

Pos logit contributions
und+0.038
idd+0.035
rous+0.033
iw+0.033
rou+0.033
Neg logit contributions
 before-0.022
 grant-0.020
 finish-0.018
 had-0.018
idi-0.018
Token go
Token ID467
Feature activation+1.42e-01

Pos logit contributions
und+0.010
idd+0.009
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.003
ers-0.003
ace-0.003
Token to
Token ID284
Feature activation-1.74e-01

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
ace-0.004
Token the
Token ID262
Feature activation+9.68e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.010
idd-0.009
rous-0.009
rou-0.009
iw-0.009
Token toy
Token ID13373
Feature activation+2.86e+00

Pos logit contributions
und+0.046
idd+0.042
rol+0.039
ays+0.039
unch+0.038
Neg logit contributions
 before-0.034
 grant-0.030
 finish-0.029
idi-0.029
 floor-0.028
Token store
Token ID3650
Feature activation+8.02e-01

Pos logit contributions
und+0.150
rou+0.148
unch+0.147
rous+0.142
idd+0.140
Neg logit contributions
 before-0.088
 finish-0.069
 shelf-0.067
ers-0.065
 floor-0.064
Token and
Token ID290
Feature activation-4.37e-01

Pos logit contributions
und+0.045
idd+0.042
rous+0.039
rol+0.039
rou+0.039
Neg logit contributions
 before-0.022
 grant-0.016
ers-0.016
 finish-0.015
idi-0.015
Token the
Token ID262
Feature activation+5.09e-02

Pos logit contributions
 before+0.012
idi+0.011
ers+0.010
 grant+0.010
ace+0.010
Neg logit contributions
und-0.022
idd-0.020
rous-0.019
iw-0.019
rou-0.019
Token candy
Token ID18550
Feature activation+1.78e+00

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.001
ace-0.001
Token store
Token ID3650
Feature activation+2.53e-01

Pos logit contributions
und+0.092
idd+0.086
rous+0.083
rou+0.082
unch+0.080
Neg logit contributions
 before-0.058
ers-0.047
 finish-0.045
 had-0.044
 floor-0.044
Token might
Token ID1244
Feature activation-5.84e-01

Pos logit contributions
 before+0.024
 grant+0.024
idi+0.023
ace+0.020
 finish+0.020
Neg logit contributions
und-0.045
idd-0.041
rol-0.039
rou-0.039
uck-0.037
Token be
Token ID307
Feature activation-3.66e-01

Pos logit contributions
 before+0.015
idi+0.014
 grant+0.013
ers+0.013
ace+0.012
Neg logit contributions
und-0.030
idd-0.027
rol-0.026
rou-0.026
rous-0.025
Token ruined
Token ID20484
Feature activation-3.21e-02

Pos logit contributions
 grant+0.012
 before+0.012
idi+0.011
ers+0.010
ace+0.010
Neg logit contributions
und-0.016
idd-0.015
rou-0.014
rous-0.014
rol-0.014
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
 finish+0.001
Neg logit contributions
und-0.002
idd-0.002
rou-0.001
rous-0.001
rol-0.001
Token Daisy
Token ID40355
Feature activation-7.87e-01

Pos logit contributions
und+0.015
idd+0.014
rou+0.013
rous+0.013
iw+0.013
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.009
ers-0.008
 finish-0.008
Token tr
Token ID491
Feature activation+2.86e+00

Pos logit contributions
 before+0.023
 grant+0.022
idi+0.019
ace+0.019
ers+0.019
Neg logit contributions
und-0.038
idd-0.035
rou-0.033
uck-0.032
rol-0.032
Tokenud
Token ID463
Feature activation+6.60e-01

Pos logit contributions
 Sorry+0.085
 Enjoy+0.084
 Good+0.080
haw+0.073
cient+0.069
Neg logit contributions
ace-0.110
idi-0.104
ers-0.098
kin-0.097
ia-0.096
Tokenged
Token ID2004
Feature activation+7.06e-01

Pos logit contributions
und+0.020
idd+0.018
rous+0.017
iw+0.016
rou+0.016
Neg logit contributions
 before-0.033
 grant-0.030
idi-0.029
ers-0.028
 had-0.028
Token along
Token ID1863
Feature activation-7.97e-01

Pos logit contributions
und+0.037
idd+0.036
rou+0.033
ays+0.033
rol+0.033
Neg logit contributions
 before-0.021
 grant-0.017
idi-0.017
 finish-0.015
ers-0.015
Token,
Token ID11
Feature activation+8.05e-02

Pos logit contributions
 grant+0.018
 before+0.017
idi+0.016
ace+0.016
ers+0.015
Neg logit contributions
und-0.043
idd-0.037
rous-0.036
 batch-0.035
rou-0.035
Token carrying
Token ID6872
Feature activation+9.43e-02

Pos logit contributions
und+0.004
idd+0.004
rous+0.004
rou+0.004
iw+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token mom
Token ID1995
Feature activation+2.50e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
rous-0.007
iw-0.006
Token took
Token ID1718
Feature activation+1.38e+00

Pos logit contributions
und+0.011
idd+0.010
rous+0.010
rou+0.010
iw+0.009
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.008
ers-0.007
 finish-0.007
Token him
Token ID683
Feature activation+1.34e-01

Pos logit contributions
und+0.053
rou+0.051
idd+0.051
iw+0.047
unch+0.046
Neg logit contributions
 before-0.057
idi-0.051
ers-0.050
 finish-0.049
 grant-0.048
Token to
Token ID284
Feature activation-1.92e-01

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.004
 grant-0.003
idi-0.003
ers-0.003
 finish-0.003
Token a
Token ID257
Feature activation+1.45e+00

Pos logit contributions
 before+0.004
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.011
idd-0.010
rous-0.010
rou-0.010
iw-0.010
Token k
Token ID479
Feature activation+2.86e+00

Pos logit contributions
und+0.080
idd+0.074
rol+0.072
ays+0.071
unch+0.067
Neg logit contributions
 before-0.041
idi-0.035
 finish-0.035
 grant-0.035
 shelf-0.031
Tokenara
Token ID3301
Feature activation+6.05e-01

Pos logit contributions
und+0.102
haw+0.086
aman+0.086
ahoo+0.084
rol+0.084
Neg logit contributions
 before-0.105
The-0.104
 corner-0.099
 finish-0.092
 shelf-0.090
Tokenoke
Token ID2088
Feature activation+1.18e+00

Pos logit contributions
und+0.032
idd+0.030
rous+0.028
rol+0.028
iw+0.028
Neg logit contributions
 before-0.017
 grant-0.015
idi-0.013
 finish-0.013
ers-0.013
Token party
Token ID2151
Feature activation+1.45e-01

Pos logit contributions
und+0.053
rou+0.046
rous+0.046
rol+0.046
iw+0.045
Neg logit contributions
 before-0.042
ers-0.038
 grant-0.037
ace-0.036
idi-0.036
Token.
Token ID13
Feature activation+1.74e-01

Pos logit contributions
und+0.008
idd+0.007
rous+0.007
rou+0.007
iw+0.006
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.003
ers-0.003
ace-0.003
Token There
Token ID1318
Feature activation+1.33e+00

Pos logit contributions
und+0.007
idd+0.007
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.006
 grant-0.006
idi-0.006
ers-0.005
 finish-0.005
Token?"
Token ID1701
Feature activation-7.08e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.004
idd-0.004
rous-0.003
iw-0.003
rou-0.003
Token Tom
Token ID4186
Feature activation+3.44e-03

Pos logit contributions
 grant+0.023
 before+0.023
ace+0.021
ers+0.021
idi+0.020
Neg logit contributions
und-0.031
idd-0.028
rous-0.027
 batch-0.026
iw-0.026
Token asked
Token ID1965
Feature activation-1.17e+00

Pos logit contributions
und+0.000
idd+0.000
rous+0.000
rou+0.000
iw+0.000
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
 finish-0.000
Token the
Token ID262
Feature activation+8.92e-01

Pos logit contributions
 grant+0.038
 before+0.033
 ground+0.032
idi+0.032
 floor+0.031
Neg logit contributions
und-0.049
idd-0.046
uck-0.044
 batch-0.042
ays-0.042
Token mother
Token ID2802
Feature activation-1.28e+00

Pos logit contributions
und+0.048
idd+0.042
rol+0.041
rou+0.041
rous+0.040
Neg logit contributions
 before-0.026
 grant-0.023
idi-0.023
ace-0.021
 third-0.021
Token k
Token ID479
Feature activation+2.85e+00

Pos logit contributions
 grant+0.041
 before+0.037
idi+0.036
ers+0.034
 entire+0.033
Neg logit contributions
und-0.053
idd-0.053
iw-0.049
rou-0.049
uck-0.048
Tokenang
Token ID648
Feature activation+3.95e-01

Pos logit contributions
und+0.095
arre+0.088
 Enjoy+0.086
 batch+0.084
aman+0.084
Neg logit contributions
The-0.102
ace-0.099
 before-0.098
 grant-0.093
ne-0.090
Tokenaroo
Token ID38049
Feature activation+1.83e-01

Pos logit contributions
und+0.019
idd+0.017
rous+0.017
rou+0.016
iw+0.016
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.011
ers-0.010
ace-0.010
Token.
Token ID13
Feature activation-4.37e-01

Pos logit contributions
und+0.010
idd+0.009
rous+0.009
rou+0.009
iw+0.009
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.003
 finish-0.003
Token
Token ID198
Feature activation-4.98e-01

Pos logit contributions
 before+0.013
 grant+0.013
ers+0.012
ace+0.011
idi+0.011
Neg logit contributions
und-0.021
idd-0.019
iw-0.018
rous-0.018
uck-0.018
Token
Token ID198
Feature activation-4.85e-01

Pos logit contributions
 before+0.016
 grant+0.015
ace+0.013
idi+0.013
ers+0.013
Neg logit contributions
und-0.024
idd-0.022
rous-0.020
uck-0.020
iw-0.020
Token's
Token ID338
Feature activation-8.25e-01

Pos logit contributions
 before+0.003
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.006
idd-0.005
rou-0.005
rous-0.005
iw-0.005
Token hands
Token ID2832
Feature activation+8.35e-01

Pos logit contributions
 before+0.028
idi+0.027
 grant+0.026
ers+0.024
etta+0.023
Neg logit contributions
und-0.035
idd-0.034
ays-0.032
rou-0.030
rous-0.030
Token and
Token ID290
Feature activation+2.71e-01

Pos logit contributions
und+0.051
idd+0.050
rous+0.048
iw+0.047
rou+0.047
Neg logit contributions
 before-0.016
 grant-0.011
 finish-0.010
ers-0.010
 had-0.009
Token falls
Token ID8953
Feature activation+6.65e-01

Pos logit contributions
und+0.013
idd+0.012
rous+0.011
rou+0.011
rol+0.011
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.008
ers-0.007
 finish-0.007
Token on
Token ID319
Feature activation-2.78e-01

Pos logit contributions
und+0.037
idd+0.035
rous+0.034
iw+0.033
rou+0.033
Neg logit contributions
 before-0.017
 grant-0.013
 finish-0.012
ers-0.012
idi-0.011
Token the
Token ID262
Feature activation-3.39e+00

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.004
ace+0.004
ers+0.004
Neg logit contributions
und-0.017
idd-0.015
rous-0.015
iw-0.015
rou-0.014
Token floor
Token ID4314
Feature activation+1.28e+00

Pos logit contributions
idi+0.109
In+0.102
etta+0.101
ace+0.098
 grant+0.092
Neg logit contributions
und-0.109
idd-0.106
ays-0.099
rou-0.097
 batch-0.095
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
und+0.079
idd+0.075
rous+0.075
iw+0.071
rol+0.071
Neg logit contributions
 before-0.026
 grant-0.016
ers-0.016
 finish-0.015
 floor-0.015
Token It
Token ID632
Feature activation+3.43e-01

Pos logit contributions
und+0.010
idd+0.009
rous+0.009
rou+0.009
iw+0.008
Neg logit contributions
 before-0.005
 grant-0.005
idi-0.004
ers-0.004
 finish-0.004
Token makes
Token ID1838
Feature activation+9.00e-01

Pos logit contributions
und+0.015
idd+0.014
rous+0.013
rou+0.013
iw+0.013
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.011
ers-0.010
 finish-0.010
Token a
Token ID257
Feature activation+5.94e-01

Pos logit contributions
und+0.054
idd+0.051
iw+0.049
rous+0.048
rou+0.047
Neg logit contributions
 before-0.019
 grant-0.015
idi-0.014
 finish-0.014
ers-0.014
Token hands
Token ID2832
Feature activation+4.80e-01

Pos logit contributions
 before+0.039
 grant+0.038
idi+0.036
etta+0.033
ers+0.033
Neg logit contributions
und-0.041
idd-0.039
iw-0.037
rous-0.037
 batch-0.036
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
und+0.027
idd+0.026
rous+0.025
rou+0.024
iw+0.024
Neg logit contributions
 before-0.011
 grant-0.009
idi-0.008
ers-0.008
 finish-0.008
Token It
Token ID632
Feature activation-3.64e-01

Pos logit contributions
 before+0.013
 grant+0.012
idi+0.011
ers+0.011
ace+0.011
Neg logit contributions
und-0.019
idd-0.017
ays-0.016
rous-0.016
iw-0.016
Token fell
Token ID3214
Feature activation+4.09e-01

Pos logit contributions
 before+0.012
 grant+0.011
idi+0.010
ace+0.010
ers+0.010
Neg logit contributions
und-0.017
idd-0.015
rol-0.014
iw-0.014
rou-0.014
Token on
Token ID319
Feature activation-5.99e-01

Pos logit contributions
und+0.021
idd+0.020
rous+0.019
rou+0.019
iw+0.019
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
ace-0.009
Token the
Token ID262
Feature activation-3.24e+00

Pos logit contributions
 grant+0.012
 before+0.012
idi+0.011
ace+0.010
etta+0.009
Neg logit contributions
und-0.034
idd-0.031
rous-0.030
iw-0.029
 batch-0.029
Token floor
Token ID4314
Feature activation+5.20e-01

Pos logit contributions
idi+0.103
etta+0.097
 grant+0.093
In+0.088
 granted+0.087
Neg logit contributions
und-0.115
 batch-0.109
iw-0.107
idd-0.106
rou-0.094
Token and
Token ID290
Feature activation+2.18e-01

Pos logit contributions
und+0.030
idd+0.028
rous+0.027
rou+0.027
iw+0.027
Neg logit contributions
 before-0.012
 grant-0.010
idi-0.009
ers-0.008
 finish-0.008
Token made
Token ID925
Feature activation+6.89e-01

Pos logit contributions
und+0.011
idd+0.010
rous+0.009
rou+0.009
iw+0.009
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
 finish-0.005
Token a
Token ID257
Feature activation+5.60e-01

Pos logit contributions
und+0.040
idd+0.038
iw+0.036
rous+0.036
rou+0.035
Neg logit contributions
 before-0.016
 grant-0.013
idi-0.012
ers-0.011
 finish-0.011
Token loud
Token ID7812
Feature activation+1.31e+00

Pos logit contributions
und+0.029
idd+0.027
rous+0.025
rol+0.025
ays+0.025
Neg logit contributions
 before-0.016
 grant-0.015
idi-0.013
 finish-0.013
 floor-0.012
Token hand
Token ID1021
Feature activation+4.06e-01

Pos logit contributions
idi+0.038
 before+0.037
 grant+0.036
ers+0.034
etta+0.031
Neg logit contributions
und-0.049
idd-0.045
ays-0.043
iw-0.042
rou-0.041
Token.
Token ID13
Feature activation-6.91e-02

Pos logit contributions
und+0.023
idd+0.022
rous+0.021
rou+0.020
iw+0.020
Neg logit contributions
 before-0.010
 grant-0.008
idi-0.007
ers-0.007
 finish-0.007
Token It
Token ID632
Feature activation+3.16e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.003
idd-0.003
rous-0.003
iw-0.003
rou-0.003
Token falls
Token ID8953
Feature activation+5.49e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
iw+0.012
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.010
ers-0.009
 finish-0.009
Token on
Token ID319
Feature activation-6.26e-01

Pos logit contributions
und+0.029
idd+0.027
rous+0.026
iw+0.025
rou+0.025
Neg logit contributions
 before-0.016
 grant-0.013
idi-0.012
ers-0.012
 finish-0.012
Token the
Token ID262
Feature activation-3.21e+00

Pos logit contributions
 grant+0.013
 before+0.012
idi+0.011
ace+0.010
ers+0.010
Neg logit contributions
und-0.036
idd-0.032
 batch-0.030
iw-0.030
rous-0.030
Token floor
Token ID4314
Feature activation+7.92e-01

Pos logit contributions
idi+0.106
etta+0.093
 behold+0.087
mit+0.087
 grant+0.087
Neg logit contributions
und-0.115
 batch-0.102
idd-0.098
rou-0.096
ays-0.096
Token and
Token ID290
Feature activation+8.18e-01

Pos logit contributions
und+0.047
idd+0.044
rous+0.043
iw+0.042
rol+0.041
Neg logit contributions
 before-0.018
 grant-0.014
ers-0.012
idi-0.012
 finish-0.012
Token breaks
Token ID9457
Feature activation-1.49e-01

Pos logit contributions
und+0.040
idd+0.038
rous+0.036
rou+0.035
unch+0.035
Neg logit contributions
 before-0.026
 grant-0.024
 finish-0.021
idi-0.021
 had-0.020
Token into
Token ID656
Feature activation+7.92e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.003
ers+0.003
 finish+0.003
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
ays-0.007
rol-0.007
Token many
Token ID867
Feature activation+2.67e-01

Pos logit contributions
und+0.043
idd+0.040
rol+0.039
rous+0.039
rou+0.038
Neg logit contributions
 before-0.021
 grant-0.017
idi-0.016
 floor-0.016
ers-0.016
Token a
Token ID257
Feature activation-6.92e-01

Pos logit contributions
und+0.057
idd+0.054
rol+0.052
rous+0.052
rou+0.051
Neg logit contributions
 before-0.018
 grant-0.013
ers-0.011
idi-0.011
 had-0.010
Token rock
Token ID3881
Feature activation+1.26e+00

Pos logit contributions
 before+0.022
idi+0.019
 grant+0.019
ace+0.019
ers+0.018
Neg logit contributions
und-0.032
idd-0.030
iw-0.028
rou-0.028
 batch-0.027
Token and
Token ID290
Feature activation+2.28e-01

Pos logit contributions
und+0.081
idd+0.080
rous+0.078
rou+0.075
rol+0.075
Neg logit contributions
 before-0.021
 grant-0.013
ers-0.011
 finish-0.011
 had-0.011
Token fell
Token ID3214
Feature activation+4.86e-01

Pos logit contributions
und+0.011
idd+0.010
rous+0.009
rou+0.009
iw+0.009
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token on
Token ID319
Feature activation-1.04e-01

Pos logit contributions
und+0.026
idd+0.025
rous+0.024
rou+0.023
iw+0.023
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.010
ers-0.010
ace-0.009
Token the
Token ID262
Feature activation-3.17e+00

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.001
ace+0.001
Neg logit contributions
und-0.006
idd-0.006
rous-0.005
iw-0.005
rou-0.005
Token ground
Token ID2323
Feature activation+5.85e-01

Pos logit contributions
idi+0.117
etta+0.109
In+0.107
keys+0.102
 before+0.100
Neg logit contributions
und-0.095
 bur-0.088
rou-0.082
iw-0.078
idd-0.076
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
und+0.034
idd+0.032
rous+0.031
rou+0.030
iw+0.030
Neg logit contributions
 before-0.014
 grant-0.011
idi-0.010
ers-0.010
 finish-0.009
Token She
Token ID1375
Feature activation-4.94e-01

Pos logit contributions
und+0.020
idd+0.018
rou+0.017
rous+0.017
rol+0.017
Neg logit contributions
 before-0.014
 grant-0.013
idi-0.012
 finish-0.011
ers-0.011
Token scrap
Token ID15881
Feature activation+4.65e-01

Pos logit contributions
 before+0.019
 grant+0.018
idi+0.017
ace+0.016
ers+0.016
Neg logit contributions
und-0.020
idd-0.018
rou-0.016
iw-0.016
rous-0.016
Tokened
Token ID276
Feature activation+5.54e-01

Pos logit contributions
und+0.017
idd+0.015
rous+0.014
rou+0.014
iw+0.014
Neg logit contributions
 before-0.020
 grant-0.019
idi-0.018
ers-0.018
ace-0.017
Token an
Token ID281
Feature activation+6.79e-02

Pos logit contributions
und+0.036
idd+0.034
rol+0.032
iw+0.032
rou+0.032
Neg logit contributions
 before-0.014
 grant-0.012
idi-0.011
ers-0.010
 had-0.009
Token ordinary
Token ID8850
Feature activation+8.08e-01

Pos logit contributions
und+0.004
idd+0.003
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.001
ers-0.001
 finish-0.001
Token marble
Token ID30623
Feature activation+9.00e-02

Pos logit contributions
und+0.041
idd+0.037
rol+0.036
rous+0.036
ays+0.035
Neg logit contributions
 before-0.024
 grant-0.022
idi-0.020
 floor-0.019
 finish-0.019
Token lying
Token ID9105
Feature activation+6.70e-01

Pos logit contributions
und+0.005
idd+0.004
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token on
Token ID319
Feature activation-5.98e-01

Pos logit contributions
und+0.039
idd+0.036
rous+0.035
rou+0.034
iw+0.034
Neg logit contributions
 before-0.015
 grant-0.012
ers-0.011
idi-0.011
 had-0.011
Token the
Token ID262
Feature activation-3.16e+00

Pos logit contributions
 before+0.012
 grant+0.012
idi+0.010
ace+0.010
ers+0.010
Neg logit contributions
und-0.034
idd-0.031
rous-0.030
iw-0.029
 batch-0.029
Token ground
Token ID2323
Feature activation+1.45e-01

Pos logit contributions
idi+0.102
etta+0.087
 grant+0.086
 behold+0.082
ce+0.081
Neg logit contributions
und-0.110
iw-0.104
 bur-0.104
ho-0.099
idd-0.098
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
und+0.008
idd+0.007
rous+0.007
rou+0.007
iw+0.007
Neg logit contributions
 before-0.004
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
Token She
Token ID1375
Feature activation+6.28e-02

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
rol+0.012
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.009
ers-0.008
 finish-0.008
Token picked
Token ID6497
Feature activation+7.33e-01

Pos logit contributions
und+0.003
idd+0.003
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
 finish-0.002
Token it
Token ID340
Feature activation+8.01e-02

Pos logit contributions
und+0.036
idd+0.033
rou+0.031
rol+0.031
rous+0.031
Neg logit contributions
 before-0.024
 grant-0.021
idi-0.019
ers-0.019
 had-0.018
Token noticed
Token ID6810
Feature activation+5.78e-01

Pos logit contributions
und+0.004
idd+0.004
rou+0.003
rous+0.003
rol+0.003
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
ace-0.002
Token a
Token ID257
Feature activation+1.14e-01

Pos logit contributions
und+0.029
idd+0.028
iw+0.026
rous+0.026
rol+0.025
Neg logit contributions
 before-0.017
 grant-0.015
idi-0.014
ers-0.014
 had-0.013
Token penny
Token ID26369
Feature activation-1.94e-01

Pos logit contributions
und+0.006
idd+0.006
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
ace-0.002
Token lying
Token ID9105
Feature activation+4.86e-01

Pos logit contributions
 before+0.006
 grant+0.005
idi+0.005
ace+0.005
ers+0.005
Neg logit contributions
und-0.010
idd-0.009
rou-0.008
rous-0.008
iw-0.008
Token on
Token ID319
Feature activation-6.18e-01

Pos logit contributions
und+0.027
idd+0.026
rous+0.024
rou+0.024
iw+0.024
Neg logit contributions
 before-0.012
 grant-0.010
idi-0.009
ers-0.009
 had-0.008
Token the
Token ID262
Feature activation-3.15e+00

Pos logit contributions
 before+0.013
 grant+0.012
idi+0.011
ace+0.011
ers+0.011
Neg logit contributions
und-0.035
idd-0.031
rous-0.030
 batch-0.030
iw-0.030
Token ground
Token ID2323
Feature activation+1.28e-01

Pos logit contributions
idi+0.094
etta+0.085
 grant+0.085
In+0.081
ia+0.080
Neg logit contributions
und-0.114
 bur-0.109
idd-0.102
iw-0.098
ho-0.096
Token near
Token ID1474
Feature activation+8.80e-02

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
ace-0.002
Token the
Token ID262
Feature activation-2.29e+00

Pos logit contributions
und+0.004
idd+0.004
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
ace-0.002
Token edge
Token ID5743
Feature activation-6.27e-01

Pos logit contributions
idi+0.083
ace+0.077
etta+0.077
 before+0.075
 grant+0.074
Neg logit contributions
und-0.082
idd-0.079
iw-0.073
 bur-0.067
 batch-0.067
Token of
Token ID286
Feature activation+3.47e-01

Pos logit contributions
 grant+0.018
 before+0.017
idi+0.017
ace+0.014
etta+0.014
Neg logit contributions
und-0.031
idd-0.029
rol-0.027
ays-0.027
rou-0.027
Token
Token ID198
Feature activation-2.65e-01

Pos logit contributions
und+0.036
idd+0.034
rous+0.032
rol+0.032
rou+0.031
Neg logit contributions
 before-0.023
 grant-0.020
idi-0.020
 finish-0.018
 had-0.018
Token
Token ID198
Feature activation-4.87e-01

Pos logit contributions
 before+0.008
 grant+0.007
idi+0.007
ers+0.006
ace+0.006
Neg logit contributions
und-0.013
idd-0.012
rous-0.011
rou-0.011
iw-0.011
TokenShe
Token ID3347
Feature activation+3.30e-01

Pos logit contributions
 before+0.018
 grant+0.017
idi+0.016
ers+0.015
ace+0.015
Neg logit contributions
und-0.021
idd-0.018
rou-0.017
uck-0.017
rous-0.017
Token opened
Token ID4721
Feature activation+3.74e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.014
rol+0.014
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.008
ers-0.008
 finish-0.008
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
und+0.023
idd+0.021
rou+0.020
rous+0.020
rol+0.020
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
 finish-0.005
Token long
Token ID890
Feature activation-3.15e+00

Pos logit contributions
 before+0.042
idi+0.042
 grant+0.039
oster+0.038
etta+0.037
Neg logit contributions
und-0.036
idd-0.034
iw-0.034
rou-0.033
 batch-0.032
Token drawer
Token ID33451
Feature activation+7.49e-01

Pos logit contributions
 grant+0.119
 contain+0.119
idi+0.118
etta+0.116
oster+0.115
Neg logit contributions
 batch-0.105
und-0.096
idd-0.095
iw-0.092
uck-0.079
Token and
Token ID290
Feature activation+3.65e-01

Pos logit contributions
und+0.046
idd+0.044
rous+0.042
rol+0.041
rou+0.041
Neg logit contributions
 before-0.015
 grant-0.011
ers-0.010
idi-0.010
 had-0.009
Token there
Token ID612
Feature activation+5.32e-01

Pos logit contributions
und+0.018
idd+0.016
rou+0.015
rous+0.015
rol+0.015
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.009
 finish-0.009
Token was
Token ID373
Feature activation-5.46e-01

Pos logit contributions
und+0.029
idd+0.028
rous+0.026
rou+0.026
iw+0.026
Neg logit contributions
 before-0.014
 grant-0.012
idi-0.011
ers-0.010
 had-0.010
Token her
Token ID607
Feature activation-4.93e-01

Pos logit contributions
 before+0.017
 grant+0.016
idi+0.015
ace+0.015
ers+0.014
Neg logit contributions
und-0.025
idd-0.023
rou-0.022
rol-0.022
iw-0.021
Token hand
Token ID1021
Feature activation+3.77e-01

Pos logit contributions
idi+0.040
 before+0.037
 grant+0.036
ers+0.035
In+0.033
Neg logit contributions
und-0.055
idd-0.049
iw-0.048
rou-0.047
 batch-0.046
Token.
Token ID13
Feature activation+9.34e-02

Pos logit contributions
und+0.021
idd+0.020
rous+0.019
rou+0.019
iw+0.018
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.007
ers-0.007
 finish-0.007
Token It
Token ID632
Feature activation-2.30e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
ace-0.002
Token fell
Token ID3214
Feature activation+1.40e-01

Pos logit contributions
 before+0.007
 grant+0.007
idi+0.006
ers+0.006
ace+0.006
Neg logit contributions
und-0.011
idd-0.010
rou-0.009
rol-0.009
iw-0.009
Token on
Token ID319
Feature activation-6.30e-01

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.004
ers-0.003
 finish-0.003
Token the
Token ID262
Feature activation-3.14e+00

Pos logit contributions
 grant+0.012
 before+0.012
idi+0.011
ace+0.010
ers+0.010
Neg logit contributions
und-0.036
idd-0.033
iw-0.032
 batch-0.031
rous-0.031
Token floor
Token ID4314
Feature activation+7.04e-01

Pos logit contributions
idi+0.093
etta+0.090
ace+0.084
In+0.081
 grant+0.079
Neg logit contributions
 batch-0.115
und-0.114
iw-0.111
rou-0.103
idd-0.101
Token and
Token ID290
Feature activation+4.58e-01

Pos logit contributions
und+0.042
idd+0.040
rous+0.038
iw+0.037
rou+0.037
Neg logit contributions
 before-0.015
 grant-0.012
idi-0.011
ers-0.010
 finish-0.010
Token broke
Token ID6265
Feature activation-1.59e-01

Pos logit contributions
und+0.023
idd+0.021
rous+0.020
rou+0.020
iw+0.019
Neg logit contributions
 before-0.014
 grant-0.013
idi-0.012
ers-0.011
 finish-0.011
Token into
Token ID656
Feature activation+1.06e+00

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ers+0.003
 finish+0.003
Neg logit contributions
und-0.009
idd-0.008
rou-0.007
iw-0.007
ays-0.007
Token pieces
Token ID5207
Feature activation+3.70e-01

Pos logit contributions
und+0.059
idd+0.056
rol+0.055
rous+0.055
rou+0.054
Neg logit contributions
 before-0.025
 grant-0.020
 floor-0.020
 sides-0.019
ers-0.019
Token see
Token ID766
Feature activation-7.45e-02

Pos logit contributions
 before+0.008
 grant+0.006
idi+0.006
ers+0.006
ace+0.006
Neg logit contributions
und-0.014
idd-0.013
rous-0.012
iw-0.012
rou-0.012
Token a
Token ID257
Feature activation-1.53e+00

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.004
idd-0.003
rous-0.003
rou-0.003
ays-0.003
Token big
Token ID1263
Feature activation-7.96e-01

Pos logit contributions
ace+0.049
 before+0.048
ers+0.045
idi+0.044
 grant+0.043
Neg logit contributions
idd-0.065
und-0.064
iw-0.061
rou-0.061
 batch-0.060
Token paper
Token ID3348
Feature activation-1.04e+00

Pos logit contributions
 before+0.025
 grant+0.024
idi+0.024
ace+0.023
ers+0.022
Neg logit contributions
und-0.035
idd-0.034
iw-0.032
 batch-0.032
rous-0.032
Token on
Token ID319
Feature activation-1.28e+00

Pos logit contributions
 before+0.031
idi+0.031
 grant+0.030
ace+0.029
etta+0.026
Neg logit contributions
und-0.047
idd-0.044
ays-0.041
iw-0.040
rou-0.040
Token the
Token ID262
Feature activation-3.14e+00

Pos logit contributions
 grant+0.029
ace+0.028
 before+0.027
etta+0.027
idi+0.027
Neg logit contributions
und-0.065
rous-0.059
 batch-0.058
ays-0.057
idd-0.057
Token table
Token ID3084
Feature activation+1.02e-01

Pos logit contributions
idi+0.117
etta+0.105
In+0.095
ace+0.094
 forgot+0.094
Neg logit contributions
 batch-0.093
iw-0.091
idd-0.083
rous-0.082
und-0.081
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
und+0.006
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token It
Token ID632
Feature activation-3.69e-01

Pos logit contributions
 before+0.020
 grant+0.019
ace+0.018
idi+0.018
ers+0.018
Neg logit contributions
und-0.024
idd-0.022
ays-0.021
iw-0.020
rous-0.020
Token has
Token ID468
Feature activation-1.23e+00

Pos logit contributions
 before+0.014
 grant+0.012
idi+0.012
ace+0.012
ers+0.011
Neg logit contributions
und-0.015
idd-0.014
ays-0.013
iw-0.013
rous-0.013
Token a
Token ID257
Feature activation-6.03e-01

Pos logit contributions
 before+0.043
idi+0.040
 grant+0.040
etta+0.037
oster+0.035
Neg logit contributions
und-0.051
idd-0.046
rou-0.043
ays-0.043
rous-0.042
Token and
Token ID290
Feature activation-5.95e-02

Pos logit contributions
und+0.035
idd+0.034
rous+0.032
iw+0.032
rou+0.032
Neg logit contributions
 before-0.012
 grant-0.009
ers-0.008
idi-0.008
 finish-0.007
Token the
Token ID262
Feature activation-9.18e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.003
idd-0.003
rous-0.003
rou-0.003
iw-0.003
Token water
Token ID1660
Feature activation-1.13e-01

Pos logit contributions
 before+0.026
 grant+0.025
idi+0.025
ers+0.022
ace+0.021
Neg logit contributions
und-0.044
idd-0.041
rou-0.038
rous-0.038
iw-0.038
Token falls
Token ID8953
Feature activation+9.38e-02

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ers+0.003
ace+0.003
Neg logit contributions
und-0.005
idd-0.004
rou-0.004
rous-0.004
ays-0.004
Token on
Token ID319
Feature activation-1.05e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.004
rou+0.004
rol+0.004
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
ace-0.002
Token the
Token ID262
Feature activation-3.13e+00

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.001
Neg logit contributions
und-0.006
idd-0.006
rous-0.005
rou-0.005
iw-0.005
Token ground
Token ID2323
Feature activation+1.52e-01

Pos logit contributions
idi+0.101
 grant+0.087
etta+0.082
lot+0.077
 before+0.075
Neg logit contributions
und-0.125
idd-0.111
ays-0.105
 batch-0.103
rol-0.103
Token.
Token ID13
Feature activation+7.71e-02

Pos logit contributions
und+0.008
idd+0.008
rous+0.007
rou+0.007
iw+0.007
Neg logit contributions
 before-0.004
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
Token L
Token ID406
Feature activation+1.48e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.003
rou+0.003
rol+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Tokenila
Token ID10102
Feature activation+4.14e-02

Pos logit contributions
und+0.007
idd+0.007
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
 finish-0.004
Token and
Token ID290
Feature activation+8.90e-01

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token blue
Token ID4171
Feature activation-1.10e+00

Pos logit contributions
ace+0.103
 grant+0.102
 before+0.100
idi+0.100
oster+0.097
Neg logit contributions
und-0.077
idd-0.069
 batch-0.067
iw-0.067
 together-0.061
Token,
Token ID11
Feature activation-2.77e+00

Pos logit contributions
idi+0.036
 grant+0.035
 before+0.034
etta+0.031
ace+0.030
Neg logit contributions
und-0.051
idd-0.046
ays-0.044
iw-0.043
rol-0.041
Token yellow
Token ID7872
Feature activation-1.34e+00

Pos logit contributions
 grant+0.112
ace+0.110
idi+0.109
 before+0.109
 contain+0.106
Neg logit contributions
und-0.081
idd-0.070
iw-0.068
 batch-0.067
 together-0.067
Token,
Token ID11
Feature activation-3.01e+00

Pos logit contributions
idi+0.046
 grant+0.045
 before+0.042
etta+0.040
ace+0.039
Neg logit contributions
und-0.059
idd-0.053
iw-0.050
ays-0.050
 batch-0.048
Token green
Token ID4077
Feature activation-1.91e+00

Pos logit contributions
 grant+0.123
idi+0.122
ace+0.121
 before+0.119
 contain+0.119
Neg logit contributions
und-0.085
iw-0.071
idd-0.070
 together-0.070
 batch-0.068
Token,
Token ID11
Feature activation-3.12e+00

Pos logit contributions
idi+0.070
 grant+0.069
etta+0.063
 before+0.062
 contain+0.060
Neg logit contributions
und-0.079
idd-0.069
iw-0.066
ays-0.065
 batch-0.063
Token and
Token ID290
Feature activation-1.17e+00

Pos logit contributions
 grant+0.128
idi+0.127
ace+0.124
 contain+0.123
 before+0.122
Neg logit contributions
und-0.088
 together-0.073
iw-0.073
idd-0.071
 batch-0.069
Token more
Token ID517
Feature activation-1.31e+00

Pos logit contributions
 before+0.039
 grant+0.039
idi+0.038
ace+0.036
oster+0.034
Neg logit contributions
und-0.047
idd-0.044
iw-0.042
 batch-0.041
rous-0.040
Token.
Token ID13
Feature activation-9.36e-02

Pos logit contributions
 grant+0.050
idi+0.048
 before+0.042
ace+0.041
 contain+0.041
Neg logit contributions
und-0.052
idd-0.048
iw-0.043
rou-0.042
 together-0.042
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.005
idd-0.004
rous-0.004
iw-0.004
rou-0.004
Token
Token ID198
Feature activation+4.27e-01

Pos logit contributions
und+0.030
idd+0.029
rous+0.027
rou+0.027
iw+0.027
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.010
ers-0.009
 finish-0.009
Token,
Token ID11
Feature activation-5.07e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ers+0.003
ace+0.003
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
rous-0.007
iw-0.007
Token and
Token ID290
Feature activation-3.89e-02

Pos logit contributions
 grant+0.014
 before+0.013
idi+0.013
ace+0.012
ers+0.012
Neg logit contributions
und-0.025
idd-0.023
rou-0.022
iw-0.021
rous-0.021
Token it
Token ID340
Feature activation+1.79e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ace+0.001
ers+0.001
Neg logit contributions
und-0.002
idd-0.002
rou-0.002
rous-0.002
iw-0.002
Token fell
Token ID3214
Feature activation+8.69e-01

Pos logit contributions
und+0.009
idd+0.009
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
 finish-0.004
Token on
Token ID319
Feature activation-3.85e-01

Pos logit contributions
und+0.047
idd+0.045
rous+0.044
iw+0.042
rou+0.042
Neg logit contributions
 before-0.023
 grant-0.019
ers-0.017
 finish-0.017
ace-0.017
Token the
Token ID262
Feature activation-3.10e+00

Pos logit contributions
 before+0.008
 grant+0.008
idi+0.007
ace+0.006
ers+0.006
Neg logit contributions
und-0.022
idd-0.020
rous-0.019
iw-0.019
 batch-0.019
Token floor
Token ID4314
Feature activation+9.77e-01

Pos logit contributions
idi+0.104
etta+0.090
In+0.083
 behold+0.082
lot+0.081
Neg logit contributions
und-0.110
 batch-0.110
idd-0.099
 racket-0.096
iw-0.093
Token.
Token ID13
Feature activation+4.89e-02

Pos logit contributions
und+0.058
idd+0.056
rous+0.054
iw+0.052
rou+0.052
Neg logit contributions
 before-0.022
 grant-0.015
ers-0.015
 finish-0.014
idi-0.014
Token It
Token ID632
Feature activation-4.63e-02

Pos logit contributions
und+0.003
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token broke
Token ID6265
Feature activation-1.55e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.002
idd-0.002
rous-0.002
rou-0.002
iw-0.002
Token into
Token ID656
Feature activation+9.18e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
 finish+0.003
ers+0.003
Neg logit contributions
und-0.009
idd-0.008
rou-0.008
ays-0.008
rous-0.008
Token friends
Token ID2460
Feature activation+1.47e+00

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
 finish+0.003
Neg logit contributions
und-0.003
idd-0.003
rous-0.003
rou-0.003
iw-0.003
Token found
Token ID1043
Feature activation+7.61e-01

Pos logit contributions
und+0.084
iw+0.080
rou+0.080
idd+0.079
ays+0.079
Neg logit contributions
 had-0.035
 before-0.034
 finish-0.028
 grant-0.026
idi-0.025
Token some
Token ID617
Feature activation-1.06e-01

Pos logit contributions
und+0.046
idd+0.043
rou+0.042
iw+0.041
rol+0.041
Neg logit contributions
 before-0.015
 grant-0.012
ers-0.011
idi-0.011
 finish-0.010
Token sticks
Token ID16461
Feature activation+2.09e-01

Pos logit contributions
 before+0.004
 grant+0.003
idi+0.003
ers+0.003
ace+0.003
Neg logit contributions
und-0.005
idd-0.004
rous-0.004
rou-0.004
iw-0.004
Token on
Token ID319
Feature activation-9.21e-01

Pos logit contributions
und+0.012
idd+0.011
rous+0.010
rou+0.010
iw+0.010
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
 finish-0.004
Token the
Token ID262
Feature activation-3.10e+00

Pos logit contributions
 grant+0.020
 before+0.019
ace+0.018
idi+0.018
etta+0.016
Neg logit contributions
und-0.052
idd-0.046
rous-0.045
 batch-0.044
ays-0.043
Token ground
Token ID2323
Feature activation+5.42e-01

Pos logit contributions
idi+0.111
 grant+0.096
etta+0.095
 behold+0.093
 End+0.093
Neg logit contributions
und-0.103
 bur-0.098
cient-0.087
idd-0.084
 batch-0.082
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
und+0.031
idd+0.029
rous+0.028
rou+0.027
iw+0.027
Neg logit contributions
 before-0.013
 grant-0.010
idi-0.009
ers-0.009
 finish-0.009
Token
Token ID220
Feature activation+9.17e-03

Pos logit contributions
 before+0.015
 grant+0.015
idi+0.014
ace+0.014
ers+0.013
Neg logit contributions
und-0.018
idd-0.017
ays-0.015
rous-0.015
iw-0.015
Token
Token ID198
Feature activation-1.53e-01

Pos logit contributions
und+0.000
idd+0.000
rous+0.000
rou+0.000
rol+0.000
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
 finish-0.000
Token
Token ID198
Feature activation+1.20e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ers+0.003
ace+0.003
Neg logit contributions
und-0.008
idd-0.007
rous-0.007
rou-0.007
iw-0.007
Token-
Token ID12
Feature activation+1.06e+00

Pos logit contributions
und+0.066
idd+0.063
rous+0.061
iw+0.060
rou+0.058
Neg logit contributions
 before-0.039
 grant-0.034
 finish-0.030
ers-0.030
 had-0.030
Tokentap
Token ID44335
Feature activation+1.02e+00

Pos logit contributions
und+0.045
idd+0.042
ays+0.039
rous+0.039
rou+0.039
Neg logit contributions
 before-0.038
 grant-0.035
idi-0.034
ers-0.034
The-0.033
Token-
Token ID12
Feature activation+6.00e-01

Pos logit contributions
und+0.047
idd+0.045
rous+0.043
iw+0.043
rou+0.041
Neg logit contributions
 before-0.035
 grant-0.030
ers-0.029
idi-0.028
ace-0.028
Tokentap
Token ID44335
Feature activation+5.68e-01

Pos logit contributions
und+0.027
idd+0.025
rous+0.023
rou+0.023
iw+0.022
Neg logit contributions
 before-0.021
 grant-0.019
idi-0.019
ers-0.018
 finish-0.017
Token on
Token ID319
Feature activation-8.47e-01

Pos logit contributions
und+0.027
idd+0.025
rous+0.024
iw+0.024
rou+0.023
Neg logit contributions
 before-0.019
 grant-0.016
idi-0.015
ers-0.015
ace-0.015
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
 before+0.019
 grant+0.018
ers+0.017
idi+0.017
ace+0.017
Neg logit contributions
und-0.046
idd-0.040
iw-0.039
 batch-0.039
rous-0.038
Token leaf
Token ID12835
Feature activation+1.11e-01

Pos logit contributions
idi+0.104
In+0.097
 involve+0.094
etta+0.093
 grant+0.093
Neg logit contributions
und-0.105
 bur-0.102
uck-0.100
idd-0.099
 batch-0.094
Token.
Token ID13
Feature activation-2.32e-02

Pos logit contributions
und+0.006
idd+0.006
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token It
Token ID632
Feature activation-8.47e-02

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.001
idd-0.001
rous-0.001
rou-0.001
rol-0.001
Token was
Token ID373
Feature activation-4.19e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.004
idd-0.004
rous-0.004
rou-0.004
rol-0.004
Token a
Token ID257
Feature activation+1.79e-01

Pos logit contributions
 grant+0.012
 before+0.012
idi+0.011
ers+0.011
ace+0.011
Neg logit contributions
und-0.020
idd-0.018
rou-0.017
rous-0.017
rol-0.017
Token saw
Token ID2497
Feature activation+7.43e-01

Pos logit contributions
 before+0.008
 grant+0.008
idi+0.007
ers+0.007
ace+0.007
Neg logit contributions
und-0.011
idd-0.010
rous-0.009
rou-0.009
iw-0.009
Token a
Token ID257
Feature activation+3.65e-01

Pos logit contributions
und+0.044
idd+0.041
iw+0.039
rol+0.039
rou+0.039
Neg logit contributions
 before-0.016
 grant-0.013
idi-0.013
ers-0.012
 had-0.011
Token marble
Token ID30623
Feature activation+6.94e-03

Pos logit contributions
und+0.019
idd+0.018
rous+0.017
rol+0.017
rou+0.017
Neg logit contributions
 before-0.010
 grant-0.009
idi-0.008
ers-0.008
 finish-0.008
Token laying
Token ID16299
Feature activation+4.98e-01

Pos logit contributions
und+0.000
idd+0.000
rou+0.000
rous+0.000
iw+0.000
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ace-0.000
ers-0.000
Token on
Token ID319
Feature activation-1.02e+00

Pos logit contributions
und+0.029
idd+0.027
rous+0.025
rou+0.025
rol+0.025
Neg logit contributions
 before-0.012
 grant-0.009
ers-0.009
idi-0.009
ace-0.008
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
 grant+0.025
ace+0.022
 before+0.021
etta+0.021
idi+0.021
Neg logit contributions
und-0.055
rous-0.048
idd-0.048
 batch-0.047
iw-0.046
Token ground
Token ID2323
Feature activation-1.95e-01

Pos logit contributions
idi+0.098
etta+0.088
 grant+0.088
 granted+0.082
ves+0.081
Neg logit contributions
und-0.113
iw-0.112
idd-0.108
 bur-0.106
 batch-0.102
Token and
Token ID290
Feature activation-1.73e-01

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.005
ace+0.004
ers+0.004
Neg logit contributions
und-0.010
idd-0.009
rou-0.009
rous-0.009
iw-0.009
Token asked
Token ID1965
Feature activation+1.93e-01

Pos logit contributions
 before+0.006
 grant+0.005
ace+0.005
idi+0.005
ers+0.005
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
rous-0.007
iw-0.007
Token his
Token ID465
Feature activation+4.20e-02

Pos logit contributions
und+0.010
idd+0.009
rous+0.009
rou+0.009
iw+0.008
Neg logit contributions
 before-0.006
 grant-0.005
idi-0.005
ers-0.004
 finish-0.004
Token Dad
Token ID17415
Feature activation-3.14e-01

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token saw
Token ID2497
Feature activation+2.70e-01

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.008
ace+0.008
ers+0.008
Neg logit contributions
und-0.011
idd-0.010
rou-0.009
iw-0.009
rous-0.009
Token the
Token ID262
Feature activation-4.03e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
iw+0.012
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token shell
Token ID7582
Feature activation-7.86e-01

Pos logit contributions
 before+0.014
 grant+0.013
idi+0.012
ace+0.012
ers+0.012
Neg logit contributions
und-0.018
idd-0.017
rou-0.016
rous-0.016
iw-0.015
Token lying
Token ID9105
Feature activation+9.07e-01

Pos logit contributions
 grant+0.021
idi+0.020
 before+0.020
ace+0.019
etta+0.017
Neg logit contributions
und-0.039
idd-0.036
rou-0.034
ays-0.034
iw-0.033
Token on
Token ID319
Feature activation-8.65e-01

Pos logit contributions
und+0.052
idd+0.050
rous+0.048
rou+0.047
iw+0.047
Neg logit contributions
 before-0.021
ers-0.016
 grant-0.016
 had-0.015
idi-0.015
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
 grant+0.022
 before+0.020
etta+0.019
idi+0.018
ace+0.018
Neg logit contributions
und-0.046
idd-0.039
rous-0.038
iw-0.038
 batch-0.038
Token sand
Token ID6450
Feature activation+7.54e-01

Pos logit contributions
idi+0.091
etta+0.083
ace+0.083
In+0.081
 grant+0.078
Neg logit contributions
und-0.113
 bur-0.102
iw-0.099
ho-0.097
idd-0.097
Token.
Token ID13
Feature activation+3.14e-01

Pos logit contributions
und+0.045
idd+0.043
rous+0.041
rou+0.040
rol+0.040
Neg logit contributions
 before-0.016
 grant-0.012
ers-0.012
idi-0.011
 floor-0.011
Token He
Token ID679
Feature activation-3.55e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
rol+0.015
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token picked
Token ID6497
Feature activation+8.71e-01

Pos logit contributions
 before+0.012
 grant+0.011
ace+0.010
ers+0.010
idi+0.010
Neg logit contributions
und-0.016
idd-0.015
rou-0.014
iw-0.014
rous-0.014
Token it
Token ID340
Feature activation+3.08e-01

Pos logit contributions
und+0.045
idd+0.042
iw+0.039
rol+0.039
rous+0.039
Neg logit contributions
 before-0.027
 grant-0.022
idi-0.022
ers-0.021
 finish-0.020
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.005
ers+0.004
ace+0.004
Neg logit contributions
und-0.010
idd-0.010
iw-0.009
rol-0.009
rou-0.009
Token The
Token ID383
Feature activation-1.09e+00

Pos logit contributions
und+0.011
idd+0.010
rous+0.009
rou+0.009
iw+0.009
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.006
 finish-0.006
Token sponge
Token ID40206
Feature activation+6.74e-02

Pos logit contributions
 before+0.041
 grant+0.040
idi+0.040
ace+0.040
etta+0.039
Neg logit contributions
idd-0.038
und-0.037
 batch-0.035
ays-0.034
uck-0.033
Token fell
Token ID3214
Feature activation+5.26e-01

Pos logit contributions
und+0.003
idd+0.003
rou+0.003
rous+0.003
rol+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token on
Token ID319
Feature activation-4.90e-01

Pos logit contributions
und+0.029
idd+0.028
rous+0.026
iw+0.026
rou+0.026
Neg logit contributions
 before-0.013
 grant-0.011
idi-0.010
ers-0.010
 finish-0.010
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
 grant+0.010
 before+0.010
idi+0.009
ace+0.008
ers+0.008
Neg logit contributions
und-0.028
idd-0.026
iw-0.024
rous-0.024
 batch-0.024
Token floor
Token ID4314
Feature activation+7.31e-01

Pos logit contributions
etta+0.103
idi+0.103
 behold+0.101
ace+0.095
 grant+0.095
Neg logit contributions
und-0.101
 batch-0.097
idd-0.095
ays-0.094
uck-0.087
Token and
Token ID290
Feature activation-5.96e-03

Pos logit contributions
und+0.044
idd+0.042
rous+0.041
iw+0.040
rou+0.039
Neg logit contributions
 before-0.015
 grant-0.011
ers-0.010
idi-0.010
 finish-0.010
Token set
Token ID900
Feature activation-4.17e-01

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.000
idd-0.000
rou-0.000
rous-0.000
iw-0.000
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
 grant+0.013
 before+0.012
idi+0.012
etta+0.010
ace+0.010
Neg logit contributions
und-0.019
idd-0.018
uck-0.017
rou-0.017
rol-0.017
Token kitchen
Token ID9592
Feature activation+2.32e-01

Pos logit contributions
idi+0.064
ace+0.064
 grant+0.063
etta+0.063
 before+0.062
Neg logit contributions
idd-0.059
und-0.057
 batch-0.056
uck-0.051
ays-0.050
Token falls
Token ID8953
Feature activation+9.62e-01

Pos logit contributions
und+0.030
idd+0.028
rous+0.026
rol+0.025
rou+0.025
Neg logit contributions
 before-0.022
 grant-0.021
idi-0.019
ers-0.018
 finish-0.018
Token down
Token ID866
Feature activation+7.77e-01

Pos logit contributions
und+0.054
idd+0.053
rous+0.052
prise+0.050
iw+0.050
Neg logit contributions
 before-0.023
 grant-0.018
 finish-0.016
 had-0.015
ace-0.015
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
und+0.048
idd+0.046
rous+0.045
rol+0.044
rou+0.043
Neg logit contributions
 before-0.016
 grant-0.011
ers-0.009
 finish-0.009
idi-0.009
Token lands
Token ID8604
Feature activation+1.23e+00

Pos logit contributions
und+0.086
idd+0.084
unch+0.080
aman+0.079
rous+0.079
Neg logit contributions
 before-0.052
 grant-0.047
 had-0.042
 finish-0.040
 the-0.039
Token on
Token ID319
Feature activation-4.60e-01

Pos logit contributions
und+0.075
rous+0.071
aman+0.070
idd+0.070
 batch+0.069
Neg logit contributions
 before-0.026
ers-0.019
 grant-0.017
 had-0.016
 finish-0.014
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.009
ers+0.008
ace+0.008
Neg logit contributions
und-0.026
idd-0.024
iw-0.023
rous-0.023
ays-0.022
Token ground
Token ID2323
Feature activation+8.21e-01

Pos logit contributions
idi+0.106
 grant+0.090
 before+0.089
In+0.086
etta+0.084
Neg logit contributions
und-0.106
idd-0.100
iw-0.090
 batch-0.090
udd-0.088
Token.
Token ID13
Feature activation+3.61e-01

Pos logit contributions
und+0.049
idd+0.047
rous+0.045
rou+0.043
rol+0.043
Neg logit contributions
 before-0.018
 grant-0.014
ers-0.012
 finish-0.012
idi-0.011
Token It
Token ID632
Feature activation+5.99e-01

Pos logit contributions
und+0.020
idd+0.019
rous+0.018
rou+0.018
rol+0.018
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token is
Token ID318
Feature activation-6.18e-01

Pos logit contributions
und+0.027
idd+0.026
rous+0.023
rou+0.023
rol+0.023
Neg logit contributions
 before-0.021
 grant-0.019
idi-0.018
 finish-0.017
ers-0.017
Token wet
Token ID9583
Feature activation+8.71e-01

Pos logit contributions
 grant+0.021
 before+0.021
idi+0.020
ers+0.019
ace+0.018
Neg logit contributions
und-0.026
idd-0.024
rou-0.024
rous-0.023
ays-0.022
Token.
Token ID13
Feature activation-5.74e-01

Pos logit contributions
und+0.015
idd+0.014
rous+0.013
rou+0.013
iw+0.013
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
 finish-0.005
Token The
Token ID383
Feature activation-4.40e-01

Pos logit contributions
 before+0.019
 grant+0.019
ers+0.018
idi+0.018
ace+0.017
Neg logit contributions
und-0.026
idd-0.023
ays-0.021
rous-0.021
uck-0.021
Token coin
Token ID10752
Feature activation-1.82e-01

Pos logit contributions
 before+0.015
idi+0.014
 grant+0.014
ace+0.013
etta+0.012
Neg logit contributions
und-0.019
idd-0.018
iw-0.017
rou-0.016
rous-0.016
Token falls
Token ID8953
Feature activation+7.35e-01

Pos logit contributions
 before+0.007
 grant+0.006
idi+0.006
ace+0.006
ers+0.005
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
ays-0.007
rous-0.007
Token on
Token ID319
Feature activation-5.49e-01

Pos logit contributions
und+0.040
idd+0.038
rous+0.037
iw+0.036
rou+0.036
Neg logit contributions
 before-0.020
 grant-0.016
ers-0.015
 finish-0.014
idi-0.014
Token the
Token ID262
Feature activation-3.08e+00

Pos logit contributions
 before+0.011
 grant+0.011
idi+0.010
ace+0.009
ers+0.009
Neg logit contributions
und-0.031
idd-0.028
rous-0.027
ays-0.027
 batch-0.026
Token floor
Token ID4314
Feature activation+7.35e-01

Pos logit contributions
idi+0.095
In+0.087
etta+0.086
 grant+0.080
ary+0.079
Neg logit contributions
und-0.114
iw-0.103
idd-0.102
 batch-0.102
ays-0.090
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
und+0.043
idd+0.041
rous+0.040
iw+0.039
rou+0.039
Neg logit contributions
 before-0.016
 grant-0.012
ers-0.011
idi-0.011
 finish-0.011
Token It
Token ID632
Feature activation+4.37e-01

Pos logit contributions
 before+0.005
 grant+0.004
idi+0.004
ers+0.004
ace+0.004
Neg logit contributions
und-0.008
idd-0.008
ays-0.007
rous-0.007
iw-0.007
Token rolls
Token ID14088
Feature activation+8.80e-01

Pos logit contributions
und+0.020
idd+0.019
rous+0.018
rou+0.017
iw+0.017
Neg logit contributions
 before-0.015
 grant-0.014
idi-0.013
ers-0.012
 finish-0.012
Token under
Token ID739
Feature activation-7.66e-01

Pos logit contributions
und+0.049
idd+0.047
rous+0.045
unch+0.045
rou+0.044
Neg logit contributions
 before-0.023
 grant-0.017
ers-0.017
 had-0.016
 finish-0.016
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
und+0.005
idd+0.005
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token stones
Token ID14966
Feature activation-1.84e-02

Pos logit contributions
 before+0.042
idi+0.041
 grant+0.039
etta+0.036
ers+0.034
Neg logit contributions
und-0.062
idd-0.056
rous-0.056
iw-0.055
rou-0.054
Token fell
Token ID3214
Feature activation-2.62e-01

Pos logit contributions
 before+0.001
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.001
idd-0.001
rous-0.001
rou-0.001
iw-0.001
Token back
Token ID736
Feature activation+1.28e-01

Pos logit contributions
 before+0.008
 grant+0.008
idi+0.007
ers+0.006
 finish+0.006
Neg logit contributions
und-0.013
idd-0.012
rou-0.011
rol-0.011
ays-0.011
Token on
Token ID319
Feature activation-4.75e-01

Pos logit contributions
und+0.007
idd+0.007
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
 finish-0.002
Token the
Token ID262
Feature activation-3.08e+00

Pos logit contributions
 grant+0.009
 before+0.009
idi+0.008
ace+0.007
ers+0.007
Neg logit contributions
und-0.028
idd-0.026
rous-0.025
iw-0.024
 batch-0.024
Token ground
Token ID2323
Feature activation-1.10e-01

Pos logit contributions
idi+0.115
etta+0.094
 before+0.092
 grant+0.092
workers+0.087
Neg logit contributions
und-0.105
 bur-0.090
ho-0.089
iw-0.088
udd-0.086
Token,
Token ID11
Feature activation-9.12e-02

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ace+0.002
ers+0.002
Neg logit contributions
und-0.006
idd-0.005
rou-0.005
rous-0.005
iw-0.005
Token or
Token ID393
Feature activation-8.50e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.005
idd-0.004
rous-0.004
rou-0.004
iw-0.004
Token on
Token ID319
Feature activation-4.51e-01

Pos logit contributions
 grant+0.022
idi+0.021
 before+0.021
ers+0.021
ace+0.020
Neg logit contributions
und-0.041
idd-0.038
rous-0.038
iw-0.036
rou-0.036
Token the
Token ID262
Feature activation-2.56e+00

Pos logit contributions
 before+0.008
 grant+0.008
idi+0.007
ace+0.006
ers+0.006
Neg logit contributions
und-0.027
idd-0.025
rous-0.024
rou-0.023
iw-0.023
Token spend
Token ID4341
Feature activation-4.34e-01

Pos logit contributions
 before+0.006
 grant+0.005
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.011
idd-0.010
rous-0.009
rou-0.009
iw-0.009
Token the
Token ID262
Feature activation-2.31e-01

Pos logit contributions
 before+0.010
 grant+0.010
idi+0.008
ace+0.007
ers+0.007
Neg logit contributions
und-0.025
idd-0.022
rous-0.022
iw-0.021
rol-0.021
Token night
Token ID1755
Feature activation-5.93e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ace+0.005
ers+0.005
Neg logit contributions
und-0.012
idd-0.011
rous-0.011
rol-0.010
rou-0.010
Token in
Token ID287
Feature activation+6.71e-01

Pos logit contributions
 grant+0.018
 before+0.018
idi+0.017
ace+0.016
ers+0.016
Neg logit contributions
und-0.028
idd-0.026
rous-0.024
rou-0.024
rol-0.023
Token the
Token ID262
Feature activation+5.18e-01

Pos logit contributions
und+0.044
idd+0.043
rou+0.041
rol+0.040
ays+0.040
Neg logit contributions
 before-0.010
 grant-0.008
idi-0.006
 finish-0.005
 had-0.005
Token k
Token ID479
Feature activation+2.31e+00

Pos logit contributions
und+0.024
idd+0.023
rol+0.021
rou+0.021
iw+0.021
Neg logit contributions
 before-0.017
 grant-0.015
idi-0.015
 finish-0.015
ers-0.014
Tokenenn
Token ID1697
Feature activation+2.96e-01

Pos logit contributions
 Enjoy+0.074
und+0.071
 Sorry+0.071
haw+0.067
aman+0.067
Neg logit contributions
The-0.088
ers-0.080
 before-0.079
In-0.078
 finish-0.074
Tokenel
Token ID417
Feature activation+8.65e-02

Pos logit contributions
und+0.008
idd+0.007
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.016
 grant-0.015
idi-0.014
ers-0.014
ace-0.014
Token.
Token ID13
Feature activation-9.98e-02

Pos logit contributions
und+0.004
idd+0.004
rous+0.003
rou+0.003
rol+0.003
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
 finish-0.002
Token
Token ID198
Feature activation-3.38e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
ace+0.002
Neg logit contributions
und-0.005
idd-0.005
rous-0.004
rol-0.004
rou-0.004
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
 before+0.010
 grant+0.010
idi+0.009
ace+0.008
ers+0.008
Neg logit contributions
und-0.017
idd-0.015
rou-0.014
rous-0.014
rol-0.014
Token "
Token ID366
Feature activation+3.73e-01

Pos logit contributions
und+0.006
idd+0.006
rou+0.006
rous+0.006
iw+0.006
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
TokenHey
Token ID10814
Feature activation+9.35e-01

Pos logit contributions
und+0.015
idd+0.014
rous+0.013
rou+0.013
rol+0.013
Neg logit contributions
 before-0.015
 grant-0.014
idi-0.013
ers-0.012
 finish-0.012
Token Billy
Token ID15890
Feature activation-6.69e-02

Pos logit contributions
und+0.044
idd+0.039
rol+0.039
rous+0.038
ays+0.037
Neg logit contributions
 before-0.033
 grant-0.028
 had-0.026
idi-0.026
 finish-0.025
Token,
Token ID11
Feature activation+7.86e-01

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.003
idd-0.003
rou-0.003
iw-0.003
rous-0.003
Token your
Token ID534
Feature activation+1.35e+00

Pos logit contributions
und+0.039
idd+0.037
ays+0.034
rous+0.034
rol+0.034
Neg logit contributions
 before-0.025
 grant-0.023
 had-0.020
idi-0.020
 finish-0.020
Token t
Token ID256
Feature activation+1.94e+00

Pos logit contributions
und+0.072
rous+0.066
idd+0.065
rol+0.064
ays+0.064
Neg logit contributions
 before-0.035
 grant-0.032
 floor-0.030
 head-0.029
idi-0.029
Tokeneddy
Token ID21874
Feature activation+2.59e-01

Pos logit contributions
und+0.081
rous+0.076
 Enjoy+0.069
idd+0.069
 batch+0.067
Neg logit contributions
 before-0.063
ace-0.062
ers-0.057
 grant-0.057
 entire-0.053
Token bear
Token ID6842
Feature activation+1.74e+00

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
rol+0.012
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
ace-0.005
Token matches
Token ID7466
Feature activation+1.55e+00

Pos logit contributions
und+0.083
rous+0.080
idd+0.078
rol+0.077
ipt+0.076
Neg logit contributions
 before-0.054
 had-0.049
 grant-0.048
ers-0.045
 finish-0.044
Token my
Token ID616
Feature activation+4.51e-01

Pos logit contributions
und+0.070
idd+0.068
rous+0.065
iw+0.064
unch+0.062
Neg logit contributions
 before-0.053
 grant-0.047
ers-0.043
 had-0.043
 finish-0.042
Token ball
Token ID2613
Feature activation+1.57e+00

Pos logit contributions
und+0.021
idd+0.019
rous+0.018
rou+0.018
rol+0.018
Neg logit contributions
 before-0.015
 grant-0.014
idi-0.013
ers-0.013
ace-0.012
Token we
Token ID356
Feature activation+4.62e-01

Pos logit contributions
 grant+0.023
idi+0.022
 before+0.022
ace+0.021
ers+0.021
Neg logit contributions
und-0.032
idd-0.029
rou-0.028
rous-0.027
unch-0.026
Token can
Token ID460
Feature activation+5.61e-01

Pos logit contributions
und+0.023
idd+0.022
rous+0.020
rou+0.020
iw+0.020
Neg logit contributions
 before-0.014
 grant-0.013
idi-0.011
 finish-0.011
ers-0.011
Token brush
Token ID14093
Feature activation+7.33e-01

Pos logit contributions
und+0.032
idd+0.030
rous+0.029
iw+0.028
rou+0.028
Neg logit contributions
 before-0.014
 grant-0.012
 finish-0.010
idi-0.010
ace-0.009
Token him
Token ID683
Feature activation+2.81e-01

Pos logit contributions
und+0.034
idd+0.032
rous+0.030
iw+0.030
rol+0.029
Neg logit contributions
 before-0.025
 grant-0.022
idi-0.020
ers-0.020
 finish-0.020
Token and
Token ID290
Feature activation-6.18e-01

Pos logit contributions
und+0.014
idd+0.014
rous+0.013
rou+0.013
iw+0.013
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token make
Token ID787
Feature activation+1.76e+00

Pos logit contributions
 before+0.015
idi+0.014
 grant+0.014
ers+0.013
ace+0.013
Neg logit contributions
und-0.032
idd-0.029
rou-0.028
rous-0.028
iw-0.027
Token him
Token ID683
Feature activation+4.26e-02

Pos logit contributions
und+0.078
idd+0.076
iw+0.072
rol+0.069
unch+0.066
Neg logit contributions
 before-0.065
 grant-0.055
 finish-0.054
idi-0.054
ers-0.054
Token look
Token ID804
Feature activation+4.87e-02

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token handsome
Token ID22665
Feature activation-3.29e-01

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
rol+0.002
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.001
ers-0.001
ace-0.001
Token."
Token ID526
Feature activation+7.38e-01

Pos logit contributions
 before+0.009
 grant+0.009
idi+0.009
ers+0.008
ace+0.008
Neg logit contributions
und-0.016
idd-0.015
rou-0.014
rous-0.014
iw-0.014
Token
Token ID198
Feature activation-1.57e-01

Pos logit contributions
und+0.040
idd+0.039
rous+0.037
rou+0.036
rol+0.036
Neg logit contributions
 before-0.018
 grant-0.015
idi-0.014
 had-0.013
 finish-0.013
Token She
Token ID1375
Feature activation+2.40e-01

Pos logit contributions
 before+0.013
 grant+0.012
idi+0.011
ers+0.011
ace+0.011
Neg logit contributions
und-0.022
idd-0.020
iw-0.018
rol-0.018
rous-0.018
Token had
Token ID550
Feature activation-9.69e-02

Pos logit contributions
und+0.013
idd+0.012
rous+0.011
rou+0.011
iw+0.011
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.006
ers-0.005
 finish-0.005
Token brought
Token ID3181
Feature activation+2.69e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.002
ace+0.002
Neg logit contributions
und-0.005
idd-0.004
rous-0.004
rou-0.004
rol-0.004
Token a
Token ID257
Feature activation+5.39e-01

Pos logit contributions
und+0.014
idd+0.013
rous+0.012
rou+0.012
iw+0.012
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token very
Token ID845
Feature activation+5.10e-01

Pos logit contributions
und+0.029
idd+0.027
ays+0.026
rol+0.025
rous+0.025
Neg logit contributions
 before-0.014
 grant-0.013
idi-0.012
 finish-0.011
ers-0.010
Token y
Token ID331
Feature activation+2.02e+00

Pos logit contributions
und+0.028
idd+0.026
rol+0.024
ays+0.024
rou+0.024
Neg logit contributions
 before-0.013
 grant-0.012
idi-0.011
 finish-0.010
ers-0.010
Tokenummy
Token ID13513
Feature activation+2.98e-01

Pos logit contributions
und+0.086
idd+0.084
rol+0.074
yles+0.071
rou+0.071
Neg logit contributions
 before-0.069
 finish-0.064
 grant-0.060
 sides-0.059
 entire-0.059
Token treat
Token ID2190
Feature activation+3.40e-01

Pos logit contributions
und+0.013
idd+0.012
rous+0.011
rou+0.011
rol+0.011
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
 finish-0.009
Token for
Token ID329
Feature activation+5.38e-01

Pos logit contributions
und+0.018
idd+0.017
rous+0.016
rou+0.015
iw+0.015
Neg logit contributions
 before-0.010
 grant-0.008
idi-0.008
ers-0.007
 finish-0.007
Token the
Token ID262
Feature activation-7.07e-01

Pos logit contributions
und+0.030
idd+0.028
rou+0.026
rous+0.026
rol+0.026
Neg logit contributions
 before-0.015
 grant-0.013
idi-0.011
ers-0.011
 finish-0.010
Token star
Token ID3491
Feature activation-6.89e-01

Pos logit contributions
 before+0.021
idi+0.020
 grant+0.019
ers+0.019
ace+0.018
Neg logit contributions
und-0.031
idd-0.030
rous-0.029
iw-0.028
rou-0.028
Token.
Token ID13
Feature activation-7.94e-01

Pos logit contributions
 grant+0.009
 before+0.009
idi+0.009
ace+0.008
ers+0.008
Neg logit contributions
und-0.017
idd-0.015
rol-0.015
rou-0.014
iw-0.014
Token Lily
Token ID20037
Feature activation-7.49e-01

Pos logit contributions
 grant+0.027
 before+0.027
 contain+0.024
ers+0.023
ace+0.023
Neg logit contributions
und-0.035
idd-0.031
 batch-0.028
 Sorry-0.028
rou-0.027
Token gave
Token ID2921
Feature activation+3.79e-01

Pos logit contributions
 before+0.022
 grant+0.022
idi+0.019
ers+0.019
ace+0.019
Neg logit contributions
und-0.035
idd-0.033
rou-0.031
iw-0.030
uck-0.029
Token him
Token ID683
Feature activation-4.46e-01

Pos logit contributions
und+0.019
idd+0.017
rou+0.016
rous+0.016
iw+0.016
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.010
ace-0.009
Token a
Token ID257
Feature activation+5.25e-01

Pos logit contributions
 before+0.013
 grant+0.013
idi+0.012
ers+0.011
ace+0.010
Neg logit contributions
und-0.021
idd-0.020
rous-0.019
rou-0.019
rol-0.018
Token big
Token ID1263
Feature activation+1.94e+00

Pos logit contributions
und+0.030
idd+0.028
rous+0.026
rol+0.026
iw+0.026
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
 finish-0.009
 had-0.009
Token hug
Token ID16225
Feature activation+1.13e-01

Pos logit contributions
und+0.126
idd+0.115
rol+0.114
yles+0.112
rous+0.110
Neg logit contributions
 before-0.035
 finish-0.030
 grant-0.030
 be-0.025
 had-0.025
Token and
Token ID290
Feature activation+6.68e-01

Pos logit contributions
und+0.006
idd+0.006
rou+0.006
rous+0.006
iw+0.006
Neg logit contributions
 before-0.003
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token they
Token ID484
Feature activation+4.30e-01

Pos logit contributions
und+0.032
idd+0.030
rol+0.028
rous+0.028
iw+0.028
Neg logit contributions
 before-0.022
 grant-0.019
idi-0.019
 had-0.018
 finish-0.017
Token sn
Token ID3013
Feature activation+1.30e+00

Pos logit contributions
und+0.021
idd+0.020
rous+0.019
iw+0.018
rou+0.018
Neg logit contributions
 before-0.013
 grant-0.012
idi-0.011
 finish-0.010
ers-0.010
Tokenugg
Token ID6837
Feature activation-3.73e-01

Pos logit contributions
und+0.036
idd+0.032
rous+0.030
iw+0.029
 sorts+0.028
Neg logit contributions
 before-0.064
ers-0.058
 finish-0.057
idi-0.055
 had-0.055
Token eyes
Token ID2951
Feature activation+8.15e-01

Pos logit contributions
 before+0.040
idi+0.037
 grant+0.037
ers+0.036
The+0.033
Neg logit contributions
und-0.026
idd-0.022
rou-0.022
ays-0.021
iw-0.021
Token and
Token ID290
Feature activation+3.89e-01

Pos logit contributions
und+0.050
idd+0.048
rous+0.046
iw+0.045
rou+0.045
Neg logit contributions
 before-0.017
 grant-0.012
idi-0.011
 finish-0.010
ers-0.010
Token slid
Token ID27803
Feature activation-2.59e-01

Pos logit contributions
und+0.020
idd+0.019
rous+0.017
rou+0.017
rol+0.017
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.010
ers-0.009
 finish-0.009
Token down
Token ID866
Feature activation+3.70e-01

Pos logit contributions
 grant+0.011
 before+0.011
idi+0.011
ers+0.010
 finish+0.010
Neg logit contributions
und-0.009
idd-0.008
rol-0.007
rou-0.007
rous-0.007
Token the
Token ID262
Feature activation-1.93e+00

Pos logit contributions
und+0.022
idd+0.021
rous+0.019
rou+0.019
iw+0.019
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token slide
Token ID10649
Feature activation+7.10e-01

Pos logit contributions
 grant+0.093
idi+0.092
etta+0.087
ace+0.087
 before+0.085
Neg logit contributions
und-0.051
iw-0.044
idd-0.042
rou-0.038
rous-0.037
Token.
Token ID13
Feature activation-6.35e-01

Pos logit contributions
und+0.041
idd+0.039
rous+0.038
rou+0.037
iw+0.037
Neg logit contributions
 before-0.017
 grant-0.012
ers-0.011
 finish-0.011
idi-0.011
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
 grant+0.020
 before+0.020
idi+0.018
ers+0.018
ace+0.018
Neg logit contributions
und-0.029
idd-0.026
 Enjoy-0.025
iw-0.024
unch-0.024
Token
Token ID198
Feature activation-4.04e-01

Pos logit contributions
 before+0.007
 grant+0.007
idi+0.006
ers+0.006
ace+0.006
Neg logit contributions
und-0.012
idd-0.011
rou-0.011
rous-0.010
iw-0.010
TokenHe
Token ID1544
Feature activation-1.22e-01

Pos logit contributions
 before+0.014
 grant+0.014
idi+0.012
ace+0.012
ers+0.011
Neg logit contributions
und-0.018
idd-0.017
rou-0.015
iw-0.015
rous-0.015
Token felt
Token ID2936
Feature activation-8.27e-01

Pos logit contributions
 before+0.004
 grant+0.003
idi+0.003
ace+0.003
ers+0.003
Neg logit contributions
und-0.006
idd-0.006
rou-0.005
rous-0.005
rol-0.005
Token,
Token ID11
Feature activation-3.65e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.010
idd-0.009
iw-0.009
rous-0.009
uck-0.009
Token she
Token ID673
Feature activation+2.59e-01

Pos logit contributions
 before+0.014
 grant+0.013
ers+0.013
idi+0.013
ace+0.013
Neg logit contributions
und-0.014
idd-0.012
iw-0.012
rous-0.012
 batch-0.012
Token had
Token ID550
Feature activation+1.68e-01

Pos logit contributions
und+0.013
idd+0.012
rous+0.011
rou+0.011
iw+0.011
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token a
Token ID257
Feature activation+5.45e-01

Pos logit contributions
und+0.009
idd+0.008
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
ace-0.003
Token surprise
Token ID5975
Feature activation+8.09e-02

Pos logit contributions
und+0.029
idd+0.027
rol+0.026
ays+0.025
rou+0.025
Neg logit contributions
 before-0.015
 grant-0.014
idi-0.013
 finish-0.012
 had-0.012
Token for
Token ID329
Feature activation+3.91e-02

Pos logit contributions
und+0.004
idd+0.003
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.002
ers-0.002
ace-0.002
Token her
Token ID607
Feature activation-2.99e-02

Pos logit contributions
und+0.002
idd+0.001
rous+0.001
rou+0.001
iw+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
 finish-0.001
Token mom
Token ID1995
Feature activation-9.55e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.001
idd-0.001
rou-0.001
rous-0.001
iw-0.001
Token!
Token ID0
Feature activation+2.42e-02

Pos logit contributions
 grant+0.040
idi+0.038
 before+0.037
 sides+0.036
ace+0.035
Neg logit contributions
und-0.033
idd-0.028
 batch-0.027
rou-0.027
iw-0.027
Token She
Token ID1375
Feature activation-5.53e-01

Pos logit contributions
und+0.001
idd+0.001
rous+0.001
iw+0.001
rou+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token wanted
Token ID2227
Feature activation-4.01e-01

Pos logit contributions
 before+0.016
 grant+0.015
ers+0.013
ace+0.013
idi+0.013
Neg logit contributions
und-0.027
idd-0.026
rou-0.024
 batch-0.023
iw-0.023
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
und+0.001
idd+0.001
rous+0.001
rou+0.001
iw+0.001
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
ace-0.000
Token Lucky
Token ID27963
Feature activation-7.48e-01

Pos logit contributions
 before+0.007
 grant+0.006
idi+0.006
ers+0.006
ace+0.006
Neg logit contributions
und-0.010
idd-0.009
rous-0.009
rou-0.008
iw-0.008
Token went
Token ID1816
Feature activation-1.20e-02

Pos logit contributions
 before+0.025
 grant+0.024
ace+0.022
ers+0.022
 contain+0.021
Neg logit contributions
und-0.033
idd-0.029
uck-0.027
rous-0.027
rou-0.027
Token for
Token ID329
Feature activation-4.79e-01

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.001
idd-0.001
rous-0.001
rou-0.001
iw-0.000
Token a
Token ID257
Feature activation+2.68e-01

Pos logit contributions
 before+0.014
 grant+0.014
idi+0.012
ers+0.012
ace+0.012
Neg logit contributions
und-0.023
idd-0.021
rous-0.020
rou-0.019
 Enjoy-0.019
Token walk
Token ID2513
Feature activation+1.49e-01

Pos logit contributions
und+0.013
idd+0.013
rous+0.012
rou+0.012
rol+0.012
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.007
ers-0.006
 finish-0.006
Token and
Token ID290
Feature activation+3.63e-01

Pos logit contributions
und+0.009
idd+0.008
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.002
 finish-0.002
Token got
Token ID1392
Feature activation+5.65e-01

Pos logit contributions
und+0.017
idd+0.016
rou+0.015
rous+0.015
iw+0.015
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.010
 finish-0.010
Token lost
Token ID2626
Feature activation+2.78e-01

Pos logit contributions
und+0.028
idd+0.025
rou+0.023
rous+0.023
ays+0.023
Neg logit contributions
 before-0.019
 grant-0.016
idi-0.015
 finish-0.015
 had-0.015
Token.
Token ID13
Feature activation-2.86e-01

Pos logit contributions
und+0.016
idd+0.015
rous+0.014
rou+0.014
iw+0.014
Neg logit contributions
 before-0.007
 grant-0.006
idi-0.005
ers-0.005
 finish-0.005
Token He
Token ID679
Feature activation+2.13e-01

Pos logit contributions
 before+0.008
 grant+0.008
ers+0.007
idi+0.007
ace+0.007
Neg logit contributions
und-0.014
idd-0.013
rous-0.012
rou-0.012
uck-0.012
Token too
Token ID1165
Feature activation+6.89e-01

Pos logit contributions
 grant+0.026
 before+0.025
idi+0.024
ers+0.023
 contain+0.023
Neg logit contributions
und-0.026
rou-0.024
idd-0.024
rous-0.023
iw-0.022
Token late
Token ID2739
Feature activation-8.05e-03

Pos logit contributions
und+0.030
idd+0.028
rol+0.027
iw+0.025
rous+0.025
Neg logit contributions
 before-0.026
 grant-0.022
idi-0.022
 finish-0.021
 had-0.021
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.000
idd-0.000
rou-0.000
rous-0.000
iw-0.000
Token Anna
Token ID11735
Feature activation-5.57e-01

Pos logit contributions
und+0.001
idd+0.001
rous+0.001
iw+0.001
rou+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
 finish-0.001
Token had
Token ID550
Feature activation+1.20e-01

Pos logit contributions
 before+0.015
 grant+0.014
idi+0.013
ace+0.012
ers+0.012
Neg logit contributions
und-0.028
idd-0.027
rou-0.025
ays-0.024
iw-0.024
Token no
Token ID645
Feature activation+1.07e+00

Pos logit contributions
und+0.006
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.004
 grant-0.004
idi-0.004
ers-0.003
ace-0.003
Token more
Token ID517
Feature activation+4.13e-01

Pos logit contributions
und+0.057
idd+0.052
rou+0.049
rol+0.049
rous+0.048
Neg logit contributions
 before-0.033
 grant-0.028
 finish-0.026
 floor-0.026
idi-0.026
Token stories
Token ID3923
Feature activation-3.03e-01

Pos logit contributions
und+0.020
idd+0.018
rous+0.017
rou+0.017
rol+0.017
Neg logit contributions
 before-0.013
 grant-0.012
idi-0.011
ers-0.011
ace-0.011
Token to
Token ID284
Feature activation+2.14e-01

Pos logit contributions
 before+0.008
 grant+0.007
idi+0.007
ace+0.006
ers+0.006
Neg logit contributions
und-0.016
idd-0.014
rou-0.014
rol-0.014
rous-0.013
Token tell
Token ID1560
Feature activation+2.85e-02

Pos logit contributions
und+0.012
idd+0.011
rous+0.010
rou+0.010
iw+0.010
Neg logit contributions
 before-0.005
 grant-0.005
idi-0.004
ers-0.004
 finish-0.004
Token.
Token ID13
Feature activation+6.04e-02

Pos logit contributions
und+0.001
idd+0.001
rous+0.001
rou+0.001
rol+0.001
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
 finish-0.001
Token be
Token ID307
Feature activation-2.61e-01

Pos logit contributions
idi+0.023
 before+0.023
ers+0.022
 grant+0.021
ace+0.019
Neg logit contributions
und-0.036
idd-0.032
uck-0.031
rous-0.031
 Sorry-0.031
Token friends
Token ID2460
Feature activation+1.82e-01

Pos logit contributions
 before+0.009
 grant+0.009
idi+0.008
ers+0.008
 finish+0.007
Neg logit contributions
und-0.011
idd-0.011
rous-0.010
rou-0.010
iw-0.009
Token with
Token ID351
Feature activation+6.50e-01

Pos logit contributions
und+0.010
idd+0.009
rous+0.008
rou+0.008
iw+0.008
Neg logit contributions
 before-0.005
 grant-0.004
idi-0.004
ers-0.004
 finish-0.004
Token the
Token ID262
Feature activation-8.52e-02

Pos logit contributions
und+0.031
idd+0.030
rou+0.027
rol+0.027
iw+0.027
Neg logit contributions
 before-0.022
 grant-0.019
idi-0.018
ers-0.017
 finish-0.017
Token little
Token ID1310
Feature activation+7.88e-02

Pos logit contributions
 before+0.002
 grant+0.002
idi+0.002
ers+0.002
ace+0.002
Neg logit contributions
und-0.004
idd-0.004
rou-0.004
rous-0.004
iw-0.004
Token boy
Token ID2933
Feature activation+2.27e-03

Pos logit contributions
und+0.004
idd+0.004
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token.
Token ID13
Feature activation-5.17e-02

Pos logit contributions
und+0.000
idd+0.000
rou+0.000
rous+0.000
iw+0.000
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
 finish-0.000
Token The
Token ID383
Feature activation-7.50e-01

Pos logit contributions
 before+0.002
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.003
idd-0.002
iw-0.002
rous-0.002
rou-0.002
Token little
Token ID1310
Feature activation-2.15e-01

Pos logit contributions
 before+0.021
 grant+0.019
idi+0.019
ace+0.019
ers+0.018
Neg logit contributions
idd-0.034
und-0.034
rou-0.032
iw-0.031
 batch-0.031
Token boy
Token ID2933
Feature activation-3.23e-01

Pos logit contributions
 before+0.007
 grant+0.007
idi+0.007
ace+0.006
ers+0.006
Neg logit contributions
und-0.009
idd-0.009
iw-0.008
rous-0.008
rou-0.008
Token felt
Token ID2936
Feature activation-4.20e-01

Pos logit contributions
 before+0.011
 grant+0.010
idi+0.009
ers+0.009
ace+0.009
Neg logit contributions
und-0.014
idd-0.013
rou-0.012
rous-0.012
iw-0.012
Token rushed
Token ID13999
Feature activation+4.02e-01

Pos logit contributions
und+0.040
idd+0.038
rous+0.036
iw+0.036
rou+0.035
Neg logit contributions
 before-0.024
 grant-0.021
idi-0.020
 finish-0.019
ers-0.019
Token to
Token ID284
Feature activation+2.70e-01

Pos logit contributions
und+0.021
idd+0.020
rous+0.019
rou+0.019
iw+0.018
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
 finish-0.008
Token set
Token ID900
Feature activation-3.39e-01

Pos logit contributions
und+0.016
idd+0.015
rous+0.014
rou+0.014
iw+0.014
Neg logit contributions
 before-0.006
 grant-0.005
idi-0.004
ers-0.004
 finish-0.004
Token up
Token ID510
Feature activation+7.09e-02

Pos logit contributions
 before+0.010
 grant+0.010
idi+0.009
ace+0.009
ers+0.009
Neg logit contributions
und-0.016
idd-0.015
rous-0.014
rou-0.013
rol-0.013
Token their
Token ID511
Feature activation-7.85e-01

Pos logit contributions
und+0.004
idd+0.004
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token camp
Token ID1413
Feature activation-1.06e+00

Pos logit contributions
 grant+0.027
 before+0.027
idi+0.024
ers+0.024
ace+0.023
Neg logit contributions
und-0.033
idd-0.031
rous-0.030
rou-0.029
 batch-0.028
Token before
Token ID878
Feature activation+5.92e-01

Pos logit contributions
 grant+0.026
 before+0.022
idi+0.022
ace+0.020
 ends+0.018
Neg logit contributions
und-0.057
idd-0.052
rou-0.048
rol-0.048
 batch-0.048
Token the
Token ID262
Feature activation-6.20e-01

Pos logit contributions
und+0.030
idd+0.028
rous+0.027
iw+0.026
rou+0.026
Neg logit contributions
 before-0.018
 grant-0.015
idi-0.014
ers-0.013
 finish-0.013
Token sun
Token ID4252
Feature activation-9.12e-01

Pos logit contributions
 before+0.019
 grant+0.018
idi+0.017
ace+0.017
ers+0.016
Neg logit contributions
und-0.028
idd-0.027
rou-0.025
rous-0.024
rol-0.024
Token set
Token ID900
Feature activation-4.37e-01

Pos logit contributions
 grant+0.026
 before+0.026
idi+0.025
ace+0.023
ers+0.022
Neg logit contributions
und-0.044
idd-0.040
rol-0.037
ays-0.037
rou-0.036
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
 before+0.012
 grant+0.011
idi+0.011
ace+0.009
ers+0.009
Neg logit contributions
und-0.022
idd-0.020
rol-0.019
rou-0.019
rous-0.019
Token glove
Token ID29144
Feature activation-2.34e-02

Pos logit contributions
und+0.018
idd+0.016
rol+0.015
rous+0.015
rou+0.015
Neg logit contributions
 before-0.015
 grant-0.014
idi-0.013
ers-0.013
 finish-0.012
Token and
Token ID290
Feature activation-4.49e-02

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.001
idd-0.001
rou-0.001
rous-0.001
iw-0.001
Token put
Token ID1234
Feature activation+3.45e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.002
idd-0.002
rous-0.002
rou-0.002
iw-0.002
Token it
Token ID340
Feature activation-2.44e-01

Pos logit contributions
und+0.016
idd+0.014
rous+0.013
rou+0.013
iw+0.013
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.011
ers-0.010
 finish-0.010
Token in
Token ID287
Feature activation+3.25e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.004
 finish+0.004
Neg logit contributions
und-0.013
idd-0.012
rou-0.012
rol-0.012
rous-0.011
Token her
Token ID607
Feature activation-3.22e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
rol+0.015
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.007
ers-0.007
 finish-0.006
Token pocket
Token ID10000
Feature activation+5.21e-01

Pos logit contributions
 before+0.012
 grant+0.012
idi+0.011
ers+0.011
ace+0.010
Neg logit contributions
und-0.013
idd-0.012
rous-0.011
iw-0.011
rou-0.011
Token.
Token ID13
Feature activation+4.87e-01

Pos logit contributions
und+0.030
idd+0.028
rous+0.027
rou+0.026
rol+0.026
Neg logit contributions
 before-0.012
 grant-0.010
ers-0.009
idi-0.009
 finish-0.008
Token She
Token ID1375
Feature activation+4.32e-01

Pos logit contributions
und+0.023
idd+0.022
rous+0.020
rou+0.020
rol+0.020
Neg logit contributions
 before-0.016
 grant-0.015
idi-0.014
 finish-0.013
ace-0.013
Token had
Token ID550
Feature activation+3.73e-02

Pos logit contributions
und+0.022
idd+0.021
rous+0.020
rou+0.019
rol+0.019
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.010
 had-0.009
Token two
Token ID734
Feature activation-6.86e-01

Pos logit contributions
und+0.002
idd+0.002
rous+0.002
rou+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token "
Token ID366
Feature activation+1.05e+00

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.000
idd-0.000
rou-0.000
rous-0.000
iw-0.000
TokenMom
Token ID29252
Feature activation+7.95e-01

Pos logit contributions
und+0.056
idd+0.052
rou+0.051
rous+0.049
iw+0.049
Neg logit contributions
 before-0.028
The-0.025
 grant-0.025
idi-0.024
In-0.023
Token,
Token ID11
Feature activation+1.03e-01

Pos logit contributions
und+0.046
idd+0.043
rous+0.042
rol+0.041
iw+0.040
Neg logit contributions
 before-0.019
 grant-0.015
idi-0.013
 had-0.013
ers-0.013
Token storm
Token ID6388
Feature activation+1.61e-01

Pos logit contributions
und+0.005
idd+0.004
rous+0.004
rou+0.004
iw+0.004
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
ace-0.003
Token!"
Token ID2474
Feature activation+4.05e-01

Pos logit contributions
und+0.007
idd+0.006
rous+0.006
rou+0.006
iw+0.006
Neg logit contributions
 before-0.006
 grant-0.006
idi-0.005
ers-0.005
 finish-0.005
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
und+0.023
idd+0.022
rous+0.021
rou+0.021
iw+0.020
Neg logit contributions
 before-0.010
 grant-0.008
idi-0.008
 finish-0.007
ers-0.007
Token
Token ID198
Feature activation-4.18e-01

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.008
ers+0.008
ace+0.008
Neg logit contributions
und-0.016
idd-0.015
rous-0.014
rou-0.013
iw-0.013
TokenThey
Token ID2990
Feature activation+7.66e-01

Pos logit contributions
 before+0.013
 grant+0.012
ers+0.010
ace+0.010
idi+0.010
Neg logit contributions
und-0.021
idd-0.019
uck-0.018
rou-0.017
unch-0.017
Token ran
Token ID4966
Feature activation-4.42e-01

Pos logit contributions
und+0.040
idd+0.038
iw+0.036
rous+0.036
rou+0.036
Neg logit contributions
 before-0.022
 grant-0.018
 had-0.018
idi-0.018
 finish-0.017
Token back
Token ID736
Feature activation+1.10e-01

Pos logit contributions
 grant+0.014
 before+0.013
idi+0.012
ers+0.011
ace+0.011
Neg logit contributions
und-0.021
idd-0.019
rous-0.018
rol-0.018
rou-0.017
Token to
Token ID284
Feature activation+4.78e-01

Pos logit contributions
und+0.005
idd+0.005
rous+0.005
rou+0.005
iw+0.005
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.003
ers-0.003
 finish-0.003
Token and
Token ID290
Feature activation-7.38e-01

Pos logit contributions
 before+0.005
 grant+0.004
idi+0.004
 finish+0.004
ers+0.004
Neg logit contributions
und-0.008
idd-0.007
rou-0.007
rous-0.007
rol-0.007
Token liked
Token ID8288
Feature activation+2.84e-01

Pos logit contributions
 before+0.025
 grant+0.024
idi+0.022
 finish+0.021
ers+0.020
Neg logit contributions
und-0.032
idd-0.030
iw-0.028
rou-0.027
 batch-0.027
Token to
Token ID284
Feature activation-4.72e-01

Pos logit contributions
und+0.015
idd+0.014
rous+0.013
rou+0.013
rol+0.013
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token eat
Token ID4483
Feature activation+1.19e+00

Pos logit contributions
 before+0.016
idi+0.014
 grant+0.014
ers+0.013
ace+0.013
Neg logit contributions
und-0.021
idd-0.019
rous-0.018
iw-0.017
 batch-0.017
Token a
Token ID257
Feature activation+2.19e+00

Pos logit contributions
und+0.062
idd+0.061
rou+0.057
rol+0.055
rous+0.054
Neg logit contributions
 before-0.036
ers-0.028
 grant-0.027
idi-0.026
 floor-0.026
Token lot
Token ID1256
Feature activation-5.88e-01

Pos logit contributions
und+0.131
idd+0.117
rol+0.117
ays+0.111
rous+0.109
Neg logit contributions
 before-0.053
 shelf-0.046
 sun-0.045
 third-0.044
 finish-0.043
Token.
Token ID13
Feature activation-2.43e-02

Pos logit contributions
 grant+0.017
idi+0.016
 before+0.016
ace+0.014
 finish+0.014
Neg logit contributions
und-0.028
idd-0.026
iw-0.025
rou-0.025
rol-0.024
Token
Token ID220
Feature activation+3.50e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
 finish+0.001
Neg logit contributions
und-0.001
idd-0.001
rous-0.001
iw-0.001
rol-0.001
Token
Token ID198
Feature activation+3.57e-01

Pos logit contributions
und+0.019
idd+0.018
rous+0.017
rou+0.017
iw+0.017
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.007
ers-0.007
ace-0.006
TokenEvery
Token ID6109
Feature activation+1.45e+00

Pos logit contributions
und+0.020
idd+0.018
rou+0.017
rous+0.017
iw+0.017
Neg logit contributions
 before-0.009
 grant-0.008
idi-0.007
ers-0.007
 finish-0.006
Token day
Token ID1110
Feature activation-1.22e+00

Pos logit contributions
und+0.099
idd+0.096
rol+0.091
rou+0.090
iw+0.088
Neg logit contributions
 before-0.024
 time-0.017
 end-0.016
 had-0.016
 finish-0.015
Token.
Token ID13
Feature activation-9.48e-02

Pos logit contributions
und+0.004
idd+0.004
rou+0.004
rous+0.004
iw+0.004
Neg logit contributions
 before-0.002
 grant-0.002
idi-0.002
ers-0.002
ace-0.002
Token She
Token ID1375
Feature activation+1.90e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ers+0.003
 finish+0.003
Neg logit contributions
und-0.004
idd-0.004
rous-0.004
iw-0.004
rou-0.004
Token wears
Token ID17326
Feature activation-3.62e-01

Pos logit contributions
und+0.008
idd+0.007
rous+0.007
rou+0.007
iw+0.007
Neg logit contributions
 before-0.007
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token a
Token ID257
Feature activation-1.79e-01

Pos logit contributions
 before+0.011
 grant+0.010
idi+0.009
ace+0.008
ers+0.008
Neg logit contributions
und-0.017
idd-0.016
rous-0.016
rou-0.015
iw-0.015
Token hat
Token ID6877
Feature activation+7.22e-01

Pos logit contributions
 before+0.006
 grant+0.006
idi+0.005
ers+0.005
ace+0.005
Neg logit contributions
und-0.008
idd-0.007
rous-0.007
rou-0.007
iw-0.007
Token.
Token ID13
Feature activation-1.36e-01

Pos logit contributions
und+0.043
idd+0.041
rous+0.039
iw+0.038
rou+0.038
Neg logit contributions
 before-0.016
 grant-0.013
ers-0.011
idi-0.011
 finish-0.011
Token
Token ID198
Feature activation-2.58e-02

Pos logit contributions
 before+0.005
 grant+0.005
idi+0.004
ers+0.004
ace+0.004
Neg logit contributions
und-0.006
idd-0.005
rous-0.005
iw-0.005
rou-0.005
Token
Token ID198
Feature activation+4.24e-01

Pos logit contributions
 before+0.001
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.001
idd-0.001
rous-0.001
rou-0.001
iw-0.001
Token"
Token ID1
Feature activation-1.06e-02

Pos logit contributions
und+0.022
idd+0.020
rol+0.019
rous+0.019
rou+0.019
Neg logit contributions
 before-0.012
 grant-0.011
idi-0.010
ers-0.009
 finish-0.009
TokenB
Token ID33
Feature activation+9.99e-01

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.000
idd-0.000
rous-0.000
iw-0.000
rou-0.000
Tokenoys
Token ID19417
Feature activation+8.48e-01

Pos logit contributions
und+0.047
rous+0.042
idd+0.042
rol+0.040
 batch+0.039
Neg logit contributions
 before-0.032
 grant-0.028
ace-0.026
ers-0.026
 finish-0.025
Token play
Token ID711
Feature activation+4.49e-01

Pos logit contributions
 before+0.043
ers+0.039
idi+0.039
 grant+0.038
ace+0.036
Neg logit contributions
und-0.033
idd-0.028
rous-0.027
 Enjoy-0.025
iw-0.025
Token with
Token ID351
Feature activation-4.57e-01

Pos logit contributions
und+0.022
idd+0.021
rou+0.019
rol+0.019
rous+0.019
Neg logit contributions
 before-0.014
 grant-0.012
idi-0.012
ers-0.012
 finish-0.011
Token dolls
Token ID36062
Feature activation-5.05e-01

Pos logit contributions
 before+0.016
 grant+0.016
idi+0.015
ace+0.014
 finish+0.013
Neg logit contributions
und-0.020
idd-0.019
rous-0.018
iw-0.017
 batch-0.017
Token and
Token ID290
Feature activation-1.74e+00

Pos logit contributions
 grant+0.014
idi+0.014
 before+0.013
ace+0.012
 entire+0.011
Neg logit contributions
und-0.025
idd-0.023
iw-0.022
rou-0.022
ays-0.022
Token cars
Token ID5006
Feature activation-1.67e-01

Pos logit contributions
ers+0.063
 before+0.063
idi+0.062
ace+0.062
 entire+0.061
Neg logit contributions
und-0.055
 batch-0.051
idd-0.051
iw-0.051
 Enjoy-0.047
Token and
Token ID290
Feature activation-1.71e+00

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ace+0.003
 finish+0.003
Neg logit contributions
und-0.009
idd-0.008
iw-0.007
rou-0.007
rous-0.007
Token books
Token ID3835
Feature activation-1.18e-01

Pos logit contributions
idi+0.066
 before+0.064
ers+0.064
 grant+0.063
ace+0.063
Neg logit contributions
und-0.050
idd-0.046
iw-0.046
 batch-0.045
rous-0.041
Token.
Token ID13
Feature activation-5.61e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ace+0.002
ers+0.002
Neg logit contributions
und-0.006
idd-0.006
rous-0.005
rou-0.005
iw-0.005
Token They
Token ID1119
Feature activation-8.00e-01

Pos logit contributions
 grant+0.023
 before+0.023
ers+0.021
idi+0.021
ace+0.020
Neg logit contributions
und-0.021
idd-0.019
ays-0.018
iw-0.017
rous-0.017
Token always
Token ID1464
Feature activation+4.12e-01

Pos logit contributions
 before+0.020
 grant+0.018
idi+0.017
ers+0.016
 entire+0.014
Neg logit contributions
und-0.041
idd-0.039
iw-0.037
rous-0.036
rou-0.036
Token shared
Token ID4888
Feature activation-1.56e-01

Pos logit contributions
und+0.022
idd+0.021
rous+0.020
rou+0.020
rol+0.019
Neg logit contributions
 before-0.011
 grant-0.009
idi-0.009
ers-0.008
 had-0.008
Token They
Token ID1119
Feature activation-1.16e-03

Pos logit contributions
 grant+0.018
 before+0.018
ers+0.016
ace+0.016
idi+0.015
Neg logit contributions
und-0.024
idd-0.022
ays-0.021
uck-0.020
rous-0.020
Token pour
Token ID12797
Feature activation-1.45e-01

Pos logit contributions
 before+0.000
 grant+0.000
idi+0.000
ers+0.000
ace+0.000
Neg logit contributions
und-0.000
idd-0.000
rous-0.000
rou-0.000
iw-0.000
Token some
Token ID617
Feature activation-7.68e-01

Pos logit contributions
 before+0.004
 grant+0.003
idi+0.003
ace+0.003
ers+0.003
Neg logit contributions
und-0.008
idd-0.007
rous-0.007
ays-0.007
rol-0.007
Token oil
Token ID3056
Feature activation-1.30e-01

Pos logit contributions
 grant+0.026
 before+0.026
idi+0.026
etta+0.024
ace+0.023
Neg logit contributions
und-0.033
idd-0.031
iw-0.028
 batch-0.028
rol-0.028
Token on
Token ID319
Feature activation-7.93e-01

Pos logit contributions
 before+0.003
 grant+0.003
idi+0.003
ace+0.003
ers+0.003
Neg logit contributions
und-0.007
idd-0.006
rou-0.006
rous-0.006
rol-0.006
Token the
Token ID262
Feature activation-1.88e+00

Pos logit contributions
 grant+0.018
 before+0.016
idi+0.016
ace+0.015
 contain+0.013
Neg logit contributions
und-0.044
idd-0.040
 batch-0.038
rous-0.038
iw-0.038
Token floor
Token ID4314
Feature activation+5.42e-01

Pos logit contributions
idi+0.058
 grant+0.051
ace+0.047
 contain+0.047
etta+0.046
Neg logit contributions
und-0.082
idd-0.080
 batch-0.078
ays-0.071
uck-0.070
Token and
Token ID290
Feature activation-6.97e-01

Pos logit contributions
und+0.031
idd+0.030
rous+0.028
rou+0.028
iw+0.028
Neg logit contributions
 before-0.012
 grant-0.010
idi-0.009
ers-0.009
 finish-0.008
Token on
Token ID319
Feature activation-7.55e-01

Pos logit contributions
 before+0.017
idi+0.016
 grant+0.016
ace+0.016
ers+0.015
Neg logit contributions
und-0.036
idd-0.033
rous-0.031
ays-0.031
iw-0.030
Token their
Token ID511
Feature activation-1.36e+00

Pos logit contributions
 grant+0.018
 before+0.016
idi+0.016
ace+0.015
 contain+0.013
Neg logit contributions
und-0.041
idd-0.037
 batch-0.036
rous-0.035
rou-0.035
Token cars
Token ID5006
Feature activation+1.46e-01

Pos logit contributions
 grant+0.052
 before+0.051
idi+0.048
ers+0.043
etta+0.042
Neg logit contributions
und-0.050
idd-0.046
 batch-0.043
rous-0.042
ays-0.039
Token "
Token ID366
Feature activation+4.96e-01

Pos logit contributions
und+0.001
idd+0.001
rou+0.001
rous+0.001
iw+0.001
Neg logit contributions
 before-0.000
 grant-0.000
idi-0.000
ers-0.000
ace-0.000
TokenI
Token ID40
Feature activation+1.32e+00

Pos logit contributions
und+0.023
idd+0.022
rous+0.020
rou+0.020
rol+0.020
Neg logit contributions
 before-0.016
 grant-0.015
idi-0.014
ers-0.013
 had-0.013
Token found
Token ID1043
Feature activation+1.32e+00

Pos logit contributions
und+0.068
rol+0.066
idd+0.064
ipt+0.064
ays+0.063
Neg logit contributions
 grant-0.036
 before-0.036
 had-0.035
 have-0.029
 finish-0.029
Token it
Token ID340
Feature activation-3.50e-01

Pos logit contributions
und+0.072
idd+0.066
unch+0.066
rou+0.066
rous+0.064
Neg logit contributions
 before-0.036
 grant-0.029
ers-0.028
 the-0.025
ace-0.024
Token on
Token ID319
Feature activation-5.31e-01

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.009
ace+0.008
ers+0.008
Neg logit contributions
und-0.017
idd-0.016
rou-0.015
rol-0.015
rous-0.015
Token the
Token ID262
Feature activation-1.86e+00

Pos logit contributions
 before+0.011
 grant+0.011
idi+0.010
ace+0.009
ers+0.009
Neg logit contributions
und-0.030
idd-0.027
rous-0.026
iw-0.026
 batch-0.025
Token ground
Token ID2323
Feature activation+9.29e-01

Pos logit contributions
idi+0.048
 grant+0.044
ce+0.042
 before+0.040
ia+0.040
Neg logit contributions
und-0.082
idd-0.074
 batch-0.073
 Woo-0.071
aman-0.071
Token.
Token ID13
Feature activation+7.82e-02

Pos logit contributions
und+0.050
idd+0.047
rous+0.045
iw+0.044
rou+0.044
Neg logit contributions
 before-0.026
 grant-0.020
ers-0.019
idi-0.018
 finish-0.018
Token Do
Token ID2141
Feature activation-4.50e-01

Pos logit contributions
und+0.003
idd+0.003
rous+0.003
rou+0.003
iw+0.003
Neg logit contributions
 before-0.003
 grant-0.003
idi-0.002
ers-0.002
 finish-0.002
Token you
Token ID345
Feature activation-2.09e-01

Pos logit contributions
 before+0.022
idi+0.021
 grant+0.021
ers+0.020
ace+0.020
Neg logit contributions
und-0.013
idd-0.011
rous-0.010
rou-0.010
iw-0.010
Token want
Token ID765
Feature activation-8.36e-03

Pos logit contributions
 before+0.010
 grant+0.009
idi+0.009
ers+0.009
 floor+0.008
Neg logit contributions
und-0.007
idd-0.006
rous-0.005
rou-0.005
iw-0.005
TokenYes
Token ID5297
Feature activation+3.58e-02

Pos logit contributions
und+0.024
idd+0.022
rou+0.020
ays+0.019
rol+0.019
Neg logit contributions
 before-0.024
 grant-0.023
idi-0.021
The-0.020
 finish-0.020
Token,
Token ID11
Feature activation-4.85e-01

Pos logit contributions
und+0.002
idd+0.002
rou+0.002
rous+0.002
iw+0.002
Neg logit contributions
 before-0.001
 grant-0.001
idi-0.001
ers-0.001
ace-0.001
Token Anna
Token ID11735
Feature activation+5.76e-01

Pos logit contributions
idi+0.018
 before+0.018
ers+0.018
 grant+0.018
ace+0.017
Neg logit contributions
und-0.017
idd-0.016
rou-0.015
iw-0.015
rous-0.015
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
und+0.033
idd+0.031
rous+0.030
rol+0.029
rou+0.029
Neg logit contributions
 before-0.013
 grant-0.011
ers-0.010
idi-0.010
 had-0.010
Token That
Token ID1320
Feature activation+1.05e+00

Pos logit contributions
 before+0.007
 grant+0.007
idi+0.007
ers+0.006
 finish+0.006
Neg logit contributions
und-0.009
idd-0.008
iw-0.007
rous-0.007
rou-0.007
Token sounds
Token ID5238
Feature activation-2.36e+00

Pos logit contributions
und+0.058
idd+0.055
rol+0.053
rous+0.052
iw+0.051
Neg logit contributions
 before-0.027
 grant-0.024
 had-0.023
 floor-0.022
 finish-0.022
Token fun
Token ID1257
Feature activation+3.09e-01

Pos logit contributions
idi+0.133
etta+0.126
 grant+0.122
asts+0.121
ce+0.121
Neg logit contributions
und-0.034
 together-0.031
rous-0.029
 Enjoy-0.027
 sorts-0.027
Token."
Token ID526
Feature activation-4.65e-02

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.015
Neg logit contributions
 before-0.008
 grant-0.007
idi-0.006
ers-0.006
 finish-0.006
Token
Token ID198
Feature activation-4.26e-01

Pos logit contributions
 before+0.002
 grant+0.001
idi+0.001
ers+0.001
ace+0.001
Neg logit contributions
und-0.002
idd-0.002
iw-0.002
rous-0.002
rou-0.002
Token
Token ID198
Feature activation-4.19e-01

Pos logit contributions
 before+0.014
 grant+0.013
idi+0.012
ers+0.011
ace+0.011
Neg logit contributions
und-0.020
idd-0.018
rou-0.017
rous-0.017
iw-0.017
TokenAnna
Token ID31160
Feature activation-1.48e-01

Pos logit contributions
 before+0.016
 grant+0.015
idi+0.014
ace+0.014
ers+0.013
Neg logit contributions
und-0.018
idd-0.016
rous-0.015
rou-0.014
iw-0.014
Token bowl
Token ID9396
Feature activation-6.95e-01

Pos logit contributions
 before+0.028
 grant+0.027
idi+0.026
ace+0.025
etta+0.025
Neg logit contributions
und-0.023
idd-0.022
 batch-0.021
iw-0.020
rous-0.019
Token slipped
Token ID18859
Feature activation-1.65e-01

Pos logit contributions
 before+0.021
 grant+0.021
idi+0.019
ace+0.018
etta+0.017
Neg logit contributions
und-0.033
idd-0.031
ays-0.028
uck-0.028
iw-0.028
Token and
Token ID290
Feature activation+3.51e-01

Pos logit contributions
 before+0.004
 grant+0.004
idi+0.004
ers+0.003
ace+0.003
Neg logit contributions
und-0.009
idd-0.008
rou-0.008
rol-0.008
ays-0.008
Token fell
Token ID3214
Feature activation+2.36e-01

Pos logit contributions
und+0.017
idd+0.016
rous+0.015
rou+0.015
iw+0.014
Neg logit contributions
 before-0.011
 grant-0.010
idi-0.009
ers-0.009
 finish-0.009
Token on
Token ID319
Feature activation-6.89e-01

Pos logit contributions
und+0.012
idd+0.012
rous+0.011
rou+0.011
iw+0.011
Neg logit contributions
 before-0.006
 grant-0.006
idi-0.005
ers-0.005
 finish-0.005
Token the
Token ID262
Feature activation-2.97e+00

Pos logit contributions
 grant+0.014
 before+0.014
idi+0.012
ace+0.012
 contain+0.011
Neg logit contributions
und-0.039
idd-0.036
iw-0.034
 batch-0.033
rous-0.033
Token floor
Token ID4314
Feature activation+4.76e-01

Pos logit contributions
idi+0.093
etta+0.092
 grant+0.089
In+0.082
ace+0.081
Neg logit contributions
 batch-0.107
und-0.103
iw-0.092
idd-0.091
ays-0.089
Token.
Token ID13
Feature activation-4.04e-01

Pos logit contributions
und+0.027
idd+0.025
rous+0.024
rou+0.024
iw+0.024
Neg logit contributions
 before-0.011
 grant-0.009
idi-0.009
ers-0.008
 finish-0.008
Token The
Token ID383
Feature activation-9.78e-01

Pos logit contributions
 before+0.011
 grant+0.010
idi+0.010
ers+0.009
ace+0.009
Neg logit contributions
und-0.021
idd-0.019
iw-0.018
ays-0.018
rous-0.018
Token dough
Token ID15756
Feature activation-4.84e-01

Pos logit contributions
 before+0.041
 grant+0.040
idi+0.040
etta+0.038
ace+0.038
Neg logit contributions
idd-0.031
und-0.030
 batch-0.029
iw-0.028
ays-0.026
Token spl
Token ID4328
Feature activation+7.49e-01

Pos logit contributions
 before+0.016
 grant+0.015
idi+0.014
ace+0.013
ers+0.013
Neg logit contributions
und-0.022
idd-0.021
ays-0.019
uck-0.018
iw-0.018