TOP ACTIVATIONS
MAX = 0.101

Can we share the cr ay on ?" They
to fight over the cr ay ons . They yelled and
and tug at the cr ay ons . They make a
tries to grab the cr ay on from Mia 's hand
. She likes the cr ay ons . She does not
and tug on the cr ay on . They are angry
She threw the broken cr ay on on the floor and
picked up the pink cr ay on and drew a big
Give me the orange cr ay on !" Tim said .
. He threw the cr ay ons and the scissors .
wanted to throw the cr ay on away , but her
They pick up the cr ay ons and the paper .
decide to share the cr ay ons . They color the
. He dropped the cr ay on and the folder .
to play with the cr ay ons too . She took
tried to remove the cr ay on marks , but it
did not remove the cr ay on marks . You made
He takes the cr ay ons from them . He
I use the red cr ay on ? I want to
trying to get the cr ay ons from the cabinet ,

MIN ACTIVATIONS
MIN = -0.140

, she would bring a stool so she could see on
. Lily stepped on a stool to reach the top of
, Amy got a little stool from her house and put
pron and climbed on a stool . She wanted to weigh
grabbed a broom and dust pan and swept up the ash
a broom and a dust pan . She sweeps the cereal
his lucky stars he was able to observe it . <|endoftext|>
a broom and a dust pan . She said , "
pron and climbed on a stool . She saw mom take
put flour , water , yeast and salt in a big
. He stepped onto a stool and held the spoon while
ice and cl ove and cinnamon and cass ia and sa
small broom and a dust pan . She sweeps the floor
- it was bigger and ju ic ier than any he
a broom and a dust pan to clean up the mess
you ." She got a stool and fixed the cabinet so
back and her family was able to enjoy it . The
self , will she be able to fly as high as
a broom and a dust pan . They help him sweep
a broom and a dust pan from the closet ."

INTERVAL 0.041 - 0.101
CONTAINS 0.498%

gave the money to the old man and he was very
a sweet tune , a mis chie vous fox appeared .
knows to avoid big p udd les of oil and go
He did not know where to go . Tom
seen it . G ret a decided to try

INTERVAL -0.020 - 0.041
CONTAINS 89.184%

things are not toys . They learn that playing with lasers
build a huge tower . They use all the blocks they
his broken zipper . They tried to help him , but
dug . It was an old toy that Jack used to
down . It makes a loud noise . It breaks into

INTERVAL -0.080 - -0.020
CONTAINS 10.312%

a new friend and was never frustrated again . <|endoftext|> Once
bear ? It 's just a toy . You should share
to lock the door so no monsters can come in ,"
walked back to their small house . As they
, and the boys included everything that could make their day

INTERVAL -0.140 - -0.080
CONTAINS 0.007%

pron and climbed on a stool . She saw mom take
and determination , anything is possible . The two friends smiled
were very thankful they were able to replace the old rug
, she would bring a stool so she could see on
, Amy got a little stool from her house and put
Token Can
Token ID1680
Feature activation-7.05e-03

Pos logit contributions
arter+0.051
 robber+0.047
 trigger+0.044
 pawn+0.044
 rook+0.042
Neg logit contributions
So-0.031
aw-0.030
 about-0.027
Ab-0.027
 together-0.027
Token we
Token ID356
Feature activation+9.11e-03

Pos logit contributions
aw+0.009
So+0.009
 about+0.008
Ab+0.008
 such+0.008
Neg logit contributions
arter-0.017
 robber-0.016
 trigger-0.015
 pawn-0.015
 rook-0.014
Token share
Token ID2648
Feature activation-2.18e-03

Pos logit contributions
arter+0.020
 robber+0.019
 trigger+0.018
 pawn+0.017
 battlefield+0.017
Neg logit contributions
So-0.014
aw-0.013
-0.013
 together-0.012
 about-0.012
Token the
Token ID262
Feature activation+3.73e-02

Pos logit contributions
So+0.002
Ab+0.002
aw+0.002
Ph+0.002
+0.002
Neg logit contributions
arter-0.006
 robber-0.005
 pawn-0.005
 trigger-0.005
 rook-0.005
Token cr
Token ID1067
Feature activation+4.99e-02

Pos logit contributions
arter+0.081
 robber+0.074
 trigger+0.070
 battlefield+0.066
 robbers+0.065
Neg logit contributions
So-0.058
's-0.055
aw-0.055
-0.054
 together-0.053
Tokenay
Token ID323
Feature activation+1.01e-01

Pos logit contributions
arter+0.106
 robber+0.106
 trigger+0.099
 robbers+0.097
 battlefield+0.090
Neg logit contributions
So-0.079
aw-0.074
 about-0.073
-0.072
's-0.071
Tokenon
Token ID261
Feature activation+3.73e-02

Pos logit contributions
arter+0.238
 robber+0.229
 trigger+0.218
 robbers+0.205
 battlefield+0.204
Neg logit contributions
So-0.135
aw-0.134
 together-0.127
's-0.127
-0.124
Token?"
Token ID1701
Feature activation-5.06e-03

Pos logit contributions
arter+0.107
 robber+0.103
 trigger+0.101
 robbers+0.096
 pawn+0.095
Neg logit contributions
So-0.030
 together-0.030
aw-0.028
 about-0.028
's-0.027
Token
Token ID198
Feature activation+9.38e-03

Pos logit contributions
aw+0.004
So+0.004
 such+0.003
+0.003
 about+0.003
Neg logit contributions
arter-0.014
 robber-0.013
 pawn-0.013
alks-0.012
 trigger-0.012
Token
Token ID198
Feature activation+2.01e-02

Pos logit contributions
arter+0.024
 pawn+0.022
alks+0.022
 trigger+0.021
 robber+0.021
Neg logit contributions
 enough-0.008
aw-0.008
 such-0.008
 about-0.007
So-0.007
TokenThey
Token ID2990
Feature activation+1.03e-02

Pos logit contributions
arter+0.046
 pawn+0.046
 robber+0.044
 rook+0.043
 trigger+0.043
Neg logit contributions
 about-0.024
 such-0.021
 enough-0.020
aw-0.019
uct-0.017
Token to
Token ID284
Feature activation+6.93e-04

Pos logit contributions
aw+0.006
So+0.006
Ab+0.005
+0.004
Ph+0.004
Neg logit contributions
arter-0.017
 robber-0.016
 pawn-0.015
 robbers-0.015
 trigger-0.015
Token fight
Token ID1907
Feature activation+1.87e-02

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 pawn+0.001
 rook+0.001
Neg logit contributions
So-0.001
aw-0.001
-0.001
 about-0.001
 together-0.001
Token over
Token ID625
Feature activation+8.90e-03

Pos logit contributions
arter+0.049
 robber+0.046
 trigger+0.045
 pawn+0.044
 battlefield+0.043
Neg logit contributions
So-0.018
aw-0.018
Ab-0.017
Ph-0.015
-0.015
Token the
Token ID262
Feature activation+3.11e-02

Pos logit contributions
arter+0.027
 robber+0.025
 trigger+0.025
 pawn+0.024
 rook+0.023
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
-0.005
 together-0.004
Token cr
Token ID1067
Feature activation+4.73e-02

Pos logit contributions
arter+0.062
 robber+0.052
alks+0.049
 trigger+0.049
 pawn+0.048
Neg logit contributions
So-0.051
aw-0.050
-0.049
's-0.049
 by-0.049
Tokenay
Token ID323
Feature activation+9.95e-02

Pos logit contributions
arter+0.100
 robber+0.097
 robbers+0.091
 trigger+0.090
 pawn+0.084
Neg logit contributions
So-0.076
aw-0.074
 about-0.070
 of-0.068
-0.067
Tokenons
Token ID684
Feature activation+1.42e-02

Pos logit contributions
arter+0.253
 robber+0.243
 trigger+0.228
 robbers+0.223
 battlefield+0.217
Neg logit contributions
aw-0.118
So-0.117
's-0.115
 together-0.115
-0.112
Token.
Token ID13
Feature activation+2.99e-02

Pos logit contributions
arter+0.041
 robber+0.039
 trigger+0.038
 pawn+0.037
 rook+0.036
Neg logit contributions
So-0.011
aw-0.010
Ab-0.009
Ph-0.008
 such-0.008
Token They
Token ID1119
Feature activation+2.20e-02

Pos logit contributions
arter+0.070
 robber+0.066
 trigger+0.063
 pawn+0.061
 battlefield+0.060
Neg logit contributions
So-0.040
aw-0.038
-0.036
 about-0.035
 such-0.035
Token yelled
Token ID22760
Feature activation+2.91e-02

Pos logit contributions
arter+0.056
 robber+0.052
 trigger+0.050
 pawn+0.049
 rook+0.047
Neg logit contributions
So-0.026
aw-0.024
 about-0.022
-0.022
 together-0.022
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
arter+0.089
 robber+0.084
 trigger+0.081
 pawn+0.079
 rook+0.078
Neg logit contributions
So-0.019
aw-0.017
-0.014
 about-0.013
 such-0.013
Token and
Token ID290
Feature activation+2.82e-02

Pos logit contributions
arter+0.047
 robber+0.044
 trigger+0.043
 pawn+0.041
 rook+0.040
Neg logit contributions
So-0.013
aw-0.012
 about-0.011
-0.011
 together-0.010
Token tug
Token ID27762
Feature activation+3.22e-02

Pos logit contributions
arter+0.057
 robber+0.051
 trigger+0.047
 pawn+0.045
 battlefield+0.045
Neg logit contributions
So-0.048
-0.046
aw-0.046
 together-0.045
's-0.045
Token at
Token ID379
Feature activation+3.13e-03

Pos logit contributions
arter+0.094
 robber+0.090
 trigger+0.087
 pawn+0.084
 rook+0.082
Neg logit contributions
So-0.024
aw-0.022
 about-0.019
-0.019
 such-0.018
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
arter+0.010
 robber+0.010
 trigger+0.009
 battlefield+0.009
 robbers+0.009
Neg logit contributions
aw-0.001
 together-0.001
So-0.001
 about-0.001
 such-0.001
Token cr
Token ID1067
Feature activation+4.07e-02

Pos logit contributions
arter+0.040
 robber+0.033
 battlefield+0.032
 robbers+0.031
 lobster+0.031
Neg logit contributions
's-0.025
aw-0.024
So-0.023
 right-0.023
 by-0.023
Tokenay
Token ID323
Feature activation+9.90e-02

Pos logit contributions
arter+0.085
 robber+0.084
 robbers+0.078
 trigger+0.078
 battlefield+0.073
Neg logit contributions
So-0.065
aw-0.064
 about-0.059
's-0.058
-0.057
Tokenons
Token ID684
Feature activation-5.18e-05

Pos logit contributions
arter+0.254
 robber+0.246
 trigger+0.231
 robbers+0.227
 battlefield+0.223
Neg logit contributions
aw-0.112
So-0.112
's-0.109
 together-0.107
 about-0.104
Token.
Token ID13
Feature activation+2.09e-02

Pos logit contributions
So+0.000
aw+0.000
Ab+0.000
 such+0.000
 about+0.000
Neg logit contributions
arter-0.000
 robber-0.000
 trigger-0.000
 pawn-0.000
 rook-0.000
Token They
Token ID1119
Feature activation+1.72e-02

Pos logit contributions
arter+0.052
 robber+0.048
 trigger+0.046
 pawn+0.045
 rook+0.044
Neg logit contributions
So-0.026
aw-0.024
 about-0.022
-0.022
 together-0.022
Token make
Token ID787
Feature activation+1.17e-02

Pos logit contributions
arter+0.040
 robber+0.035
 trigger+0.033
 battlefield+0.033
alks+0.033
Neg logit contributions
So-0.025
-0.024
's-0.023
aw-0.023
 about-0.022
Token a
Token ID257
Feature activation-1.34e-03

Pos logit contributions
arter+0.031
 robber+0.030
 trigger+0.029
 pawn+0.028
 battlefield+0.027
Neg logit contributions
So-0.012
aw-0.011
-0.010
 about-0.010
Ab-0.009
Token tries
Token ID8404
Feature activation+1.42e-03

Pos logit contributions
arter+0.044
 robber+0.043
 trigger+0.041
 pawn+0.039
 rook+0.037
Neg logit contributions
So-0.035
aw-0.033
Ab-0.032
 such-0.032
 together-0.031
Token to
Token ID284
Feature activation+2.75e-02

Pos logit contributions
arter+0.004
 robber+0.004
 pawn+0.004
 trigger+0.004
 rook+0.004
Neg logit contributions
aw-0.001
So-0.001
Ab-0.001
Ph-0.001
-0.001
Token grab
Token ID5552
Feature activation-5.40e-03

Pos logit contributions
arter+0.062
 robber+0.054
 trigger+0.052
alks+0.051
 battlefield+0.051
Neg logit contributions
So-0.044
-0.040
 together-0.038
's-0.038
 such-0.038
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
So+0.003
aw+0.003
 about+0.003
+0.002
 together+0.002
Neg logit contributions
arter-0.017
 robber-0.016
 trigger-0.015
 pawn-0.015
 battlefield-0.015
Token cr
Token ID1067
Feature activation+4.22e-02

Pos logit contributions
arter+0.051
 robber+0.046
 battlefield+0.042
 trigger+0.042
 robbers+0.041
Neg logit contributions
's-0.031
So-0.030
-0.028
 by-0.027
aw-0.027
Tokenay
Token ID323
Feature activation+9.89e-02

Pos logit contributions
arter+0.090
 robber+0.090
 robbers+0.084
 trigger+0.083
 battlefield+0.079
Neg logit contributions
So-0.066
aw-0.063
-0.060
 about-0.059
's-0.059
Tokenon
Token ID261
Feature activation+3.12e-02

Pos logit contributions
arter+0.245
 robber+0.237
 trigger+0.221
 robbers+0.217
 battlefield+0.217
Neg logit contributions
's-0.120
So-0.120
aw-0.120
 together-0.119
-0.116
Token from
Token ID422
Feature activation-6.09e-03

Pos logit contributions
arter+0.101
 robber+0.095
 trigger+0.091
 battlefield+0.090
 robbers+0.089
Neg logit contributions
So-0.016
-0.013
 together-0.013
's-0.013
aw-0.012
Token Mia
Token ID32189
Feature activation-8.51e-03

Pos logit contributions
 it+0.005
 together+0.004
aw+0.004
 by+0.004
 about+0.004
Neg logit contributions
arter-0.018
 robber-0.016
 trigger-0.016
 battlefield-0.016
 pawn-0.016
Token's
Token ID338
Feature activation-1.39e-02

Pos logit contributions
So+0.006
aw+0.005
Ab+0.005
Ph+0.005
 about+0.004
Neg logit contributions
arter-0.025
 robber-0.024
 trigger-0.023
 pawn-0.023
 rook-0.022
Token hand
Token ID1021
Feature activation-8.72e-03

Pos logit contributions
So+0.023
aw+0.021
's+0.021
+0.021
 together+0.020
Neg logit contributions
arter-0.029
 robber-0.026
 trigger-0.025
 battlefield-0.023
 pawn-0.023
Token.
Token ID13
Feature activation+2.49e-02

Pos logit contributions
arter+0.000
 trigger+0.000
 robber+0.000
sing+0.000
 pawn+0.000
Neg logit contributions
Ab-0.000
So-0.000
aw-0.000
Ph-0.000
 such-0.000
Token She
Token ID1375
Feature activation+1.30e-02

Pos logit contributions
arter+0.066
 robber+0.064
 trigger+0.061
 pawn+0.060
 rook+0.058
Neg logit contributions
aw-0.023
So-0.023
 such-0.020
Ab-0.019
 about-0.019
Token likes
Token ID7832
Feature activation+2.16e-02

Pos logit contributions
arter+0.029
 robber+0.028
 trigger+0.026
 pawn+0.026
 rook+0.025
Neg logit contributions
So-0.018
aw-0.017
 together-0.016
Ab-0.016
 about-0.016
Token the
Token ID262
Feature activation+2.67e-02

Pos logit contributions
arter+0.062
 trigger+0.057
 robber+0.057
 spine+0.054
sing+0.053
Neg logit contributions
 about-0.018
aw-0.017
 it-0.017
 such-0.017
 together-0.016
Token cr
Token ID1067
Feature activation+4.36e-02

Pos logit contributions
arter+0.062
 robber+0.052
 trigger+0.050
 battlefield+0.050
 robbers+0.048
Neg logit contributions
's-0.038
So-0.038
aw-0.037
 right-0.036
 more-0.036
Tokenay
Token ID323
Feature activation+9.75e-02

Pos logit contributions
arter+0.096
 robber+0.095
 robbers+0.090
 trigger+0.089
 battlefield+0.085
Neg logit contributions
So-0.065
aw-0.063
 about-0.060
 of-0.059
-0.058
Tokenons
Token ID684
Feature activation+8.70e-03

Pos logit contributions
arter+0.246
 robber+0.233
 trigger+0.223
 battlefield+0.215
 robbers+0.214
Neg logit contributions
aw-0.118
So-0.114
's-0.112
 together-0.111
 about-0.107
Token.
Token ID13
Feature activation+2.84e-02

Pos logit contributions
arter+0.024
 robber+0.023
 trigger+0.022
 pawn+0.022
 rook+0.021
Neg logit contributions
So-0.007
aw-0.007
Ab-0.006
Ph-0.006
 such-0.005
Token She
Token ID1375
Feature activation+7.65e-03

Pos logit contributions
arter+0.082
 robber+0.078
 trigger+0.075
 pawn+0.073
 battlefield+0.072
Neg logit contributions
So-0.023
aw-0.021
 about-0.018
-0.018
 together-0.018
Token does
Token ID857
Feature activation+1.65e-02

Pos logit contributions
arter+0.018
 robber+0.016
 trigger+0.016
 pawn+0.015
 battlefield+0.015
Neg logit contributions
So-0.011
aw-0.010
 about-0.009
-0.009
 together-0.009
Token not
Token ID407
Feature activation+1.24e-02

Pos logit contributions
arter+0.045
 robber+0.042
 trigger+0.041
 pawn+0.040
 battlefield+0.039
Neg logit contributions
So-0.016
 about-0.015
aw-0.014
 together-0.014
-0.013
Token and
Token ID290
Feature activation+2.37e-02

Pos logit contributions
arter+0.041
 robber+0.038
 trigger+0.037
 pawn+0.036
 rook+0.035
Neg logit contributions
So-0.009
aw-0.009
 about-0.007
-0.007
 together-0.007
Token tug
Token ID27762
Feature activation+2.79e-02

Pos logit contributions
arter+0.049
 robber+0.046
 trigger+0.044
 pawn+0.042
 rook+0.041
Neg logit contributions
So-0.038
aw-0.037
 about-0.035
-0.034
 such-0.034
Token on
Token ID319
Feature activation+1.89e-02

Pos logit contributions
arter+0.074
 robber+0.071
 trigger+0.069
 pawn+0.067
 rook+0.065
Neg logit contributions
So-0.027
aw-0.025
-0.023
 about-0.023
Ab-0.022
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
arter+0.057
 robber+0.054
 trigger+0.053
 pawn+0.051
 rook+0.050
Neg logit contributions
So-0.012
aw-0.011
 about-0.009
-0.009
 together-0.009
Token cr
Token ID1067
Feature activation+4.48e-02

Pos logit contributions
arter+0.069
 robber+0.062
 robbers+0.055
 battlefield+0.055
 trigger+0.054
Neg logit contributions
's-0.044
So-0.043
-0.042
aw-0.042
 by-0.041
Tokenay
Token ID323
Feature activation+9.70e-02

Pos logit contributions
arter+0.091
 robber+0.089
 robbers+0.082
 trigger+0.081
 battlefield+0.077
Neg logit contributions
So-0.076
aw-0.073
 about-0.068
-0.068
's-0.067
Tokenon
Token ID261
Feature activation+3.52e-02

Pos logit contributions
arter+0.232
 robber+0.223
 trigger+0.209
 robbers+0.205
 battlefield+0.200
Neg logit contributions
So-0.129
aw-0.126
's-0.119
-0.118
 about-0.118
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
arter+0.117
 robber+0.111
 trigger+0.105
 robbers+0.104
 battlefield+0.103
Neg logit contributions
So-0.016
 together-0.014
's-0.012
aw-0.012
-0.012
Token They
Token ID1119
Feature activation+1.69e-02

Pos logit contributions
arter+0.050
 robber+0.047
 trigger+0.045
 pawn+0.044
 rook+0.043
Neg logit contributions
So-0.029
aw-0.028
 about-0.025
-0.025
 such-0.025
Token are
Token ID389
Feature activation+1.84e-03

Pos logit contributions
arter+0.040
 robber+0.035
 trigger+0.033
 battlefield+0.032
 robbers+0.032
Neg logit contributions
So-0.024
-0.023
aw-0.022
's-0.022
 together-0.021
Token angry
Token ID7954
Feature activation-4.52e-03

Pos logit contributions
arter+0.004
 robber+0.004
 trigger+0.004
 pawn+0.004
 battlefield+0.004
Neg logit contributions
So-0.003
aw-0.002
 about-0.002
-0.002
 together-0.002
Token She
Token ID1375
Feature activation-8.20e-03

Pos logit contributions
So+0.002
aw+0.002
 about+0.001
 such+0.001
 together+0.001
Neg logit contributions
arter-0.005
 robber-0.005
 trigger-0.005
 pawn-0.005
 battlefield-0.004
Token threw
Token ID9617
Feature activation-9.03e-04

Pos logit contributions
So+0.009
aw+0.008
 about+0.007
+0.007
 together+0.007
Neg logit contributions
arter-0.022
 robber-0.020
 trigger-0.020
 pawn-0.019
 rook-0.019
Token the
Token ID262
Feature activation+2.27e-02

Pos logit contributions
So+0.001
aw+0.000
 about+0.000
+0.000
 together+0.000
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 pawn-0.002
 battlefield-0.002
Token broken
Token ID5445
Feature activation+5.68e-02

Pos logit contributions
arter+0.054
 robber+0.047
 battlefield+0.044
 trigger+0.043
 robbers+0.042
Neg logit contributions
's-0.033
So-0.032
-0.031
aw-0.030
 by-0.029
Token cr
Token ID1067
Feature activation+3.52e-02

Pos logit contributions
arter+0.132
 robber+0.118
 trigger+0.107
 battlefield+0.106
 robbers+0.105
Neg logit contributions
's-0.082
So-0.079
aw-0.078
-0.077
 together-0.075
Tokenay
Token ID323
Feature activation+9.69e-02

Pos logit contributions
arter+0.079
 robber+0.077
 robbers+0.072
 battlefield+0.069
 trigger+0.069
Neg logit contributions
So-0.052
aw-0.051
 of-0.049
-0.048
 about-0.047
Tokenon
Token ID261
Feature activation+2.29e-02

Pos logit contributions
arter+0.244
 robber+0.230
 trigger+0.215
 battlefield+0.213
 robbers+0.211
Neg logit contributions
aw-0.121
So-0.117
's-0.113
-0.112
 together-0.111
Token on
Token ID319
Feature activation+8.08e-03

Pos logit contributions
arter+0.071
 robber+0.066
 trigger+0.063
 battlefield+0.062
 pawn+0.061
Neg logit contributions
So-0.016
 together-0.014
aw-0.014
-0.013
's-0.013
Token the
Token ID262
Feature activation+6.07e-03

Pos logit contributions
arter+0.026
 robber+0.025
 trigger+0.024
 pawn+0.023
 battlefield+0.023
Neg logit contributions
So-0.004
aw-0.004
 about-0.003
 such-0.003
-0.003
Token floor
Token ID4314
Feature activation-2.18e-03

Pos logit contributions
arter+0.011
 robber+0.010
 trigger+0.009
alks+0.009
 robbers+0.008
Neg logit contributions
So-0.011
's-0.011
-0.011
aw-0.011
 by-0.010
Token and
Token ID290
Feature activation+7.25e-03

Pos logit contributions
So+0.002
aw+0.002
+0.001
 about+0.001
 such+0.001
Neg logit contributions
arter-0.006
 robber-0.006
 trigger-0.006
 pawn-0.005
 rook-0.005
Token picked
Token ID6497
Feature activation+7.91e-03

Pos logit contributions
So+0.009
aw+0.008
 about+0.008
 such+0.008
+0.007
Neg logit contributions
arter-0.014
 robber-0.013
 pawn-0.013
 trigger-0.013
 rook-0.012
Token up
Token ID510
Feature activation-7.46e-03

Pos logit contributions
arter+0.022
 robber+0.021
 trigger+0.020
 pawn+0.020
 rook+0.019
Neg logit contributions
So-0.007
aw-0.006
-0.006
 about-0.006
 together-0.005
Token the
Token ID262
Feature activation+2.41e-02

Pos logit contributions
So+0.005
aw+0.004
 about+0.004
+0.004
 together+0.004
Neg logit contributions
arter-0.023
 robber-0.022
 trigger-0.021
 pawn-0.020
 battlefield-0.020
Token pink
Token ID11398
Feature activation+5.36e-02

Pos logit contributions
arter+0.053
 robber+0.048
 trigger+0.046
 battlefield+0.043
 robbers+0.043
Neg logit contributions
So-0.037
aw-0.036
-0.035
's-0.035
 such-0.034
Token cr
Token ID1067
Feature activation+3.85e-02

Pos logit contributions
arter+0.130
 robber+0.118
 trigger+0.109
 battlefield+0.107
 robbers+0.105
Neg logit contributions
's-0.075
aw-0.073
 was-0.072
 together-0.071
-0.071
Tokenay
Token ID323
Feature activation+9.63e-02

Pos logit contributions
arter+0.085
 robber+0.084
 robbers+0.078
 trigger+0.077
 battlefield+0.074
Neg logit contributions
So-0.058
aw-0.057
-0.055
 about-0.055
 of-0.053
Tokenon
Token ID261
Feature activation+2.46e-02

Pos logit contributions
arter+0.234
 robber+0.224
 trigger+0.212
 battlefield+0.206
 robbers+0.203
Neg logit contributions
aw-0.124
So-0.121
 together-0.121
-0.120
's-0.117
Token and
Token ID290
Feature activation+4.63e-03

Pos logit contributions
arter+0.072
 robber+0.068
 trigger+0.066
 pawn+0.064
 battlefield+0.063
Neg logit contributions
So-0.019
aw-0.017
 about-0.016
-0.016
 together-0.015
Token drew
Token ID9859
Feature activation+5.70e-03

Pos logit contributions
arter+0.011
 robber+0.010
 pawn+0.010
 trigger+0.010
 rook+0.009
Neg logit contributions
So-0.006
aw-0.006
 about-0.005
-0.005
Ph-0.005
Token a
Token ID257
Feature activation-6.51e-03

Pos logit contributions
arter+0.014
 robber+0.014
 trigger+0.013
 pawn+0.013
 rook+0.013
Neg logit contributions
So-0.006
aw-0.005
Ph-0.005
Ab-0.005
-0.005
Token big
Token ID1263
Feature activation-4.64e-03

Pos logit contributions
So+0.010
aw+0.010
+0.009
 together+0.009
 about+0.009
Neg logit contributions
arter-0.014
 robber-0.013
 trigger-0.012
 battlefield-0.012
 pawn-0.011
TokenGive
Token ID23318
Feature activation-4.59e-03

Pos logit contributions
 about+0.005
aw+0.005
So+0.005
 together+0.005
 such+0.004
Neg logit contributions
 robber-0.009
arter-0.008
 trigger-0.008
 robbers-0.008
 pawn-0.008
Token me
Token ID502
Feature activation+2.91e-02

Pos logit contributions
So+0.005
aw+0.005
 about+0.004
+0.004
Ab+0.004
Neg logit contributions
arter-0.011
 robber-0.011
 trigger-0.011
 pawn-0.010
 robbers-0.010
Token the
Token ID262
Feature activation+3.03e-02

Pos logit contributions
arter+0.088
 robber+0.083
 trigger+0.081
 pawn+0.079
 rook+0.077
Neg logit contributions
So-0.019
aw-0.018
 about-0.015
-0.015
 together-0.014
Token orange
Token ID10912
Feature activation+5.51e-02

Pos logit contributions
arter+0.068
 robber+0.063
 trigger+0.059
 battlefield+0.057
 robbers+0.057
Neg logit contributions
So-0.044
's-0.044
-0.042
aw-0.041
 such-0.041
Token cr
Token ID1067
Feature activation+4.07e-02

Pos logit contributions
arter+0.147
 robber+0.139
 trigger+0.130
 robbers+0.129
 battlefield+0.129
Neg logit contributions
's-0.059
-0.058
 together-0.057
So-0.056
aw-0.054
Tokenay
Token ID323
Feature activation+9.63e-02

Pos logit contributions
arter+0.089
 robber+0.087
 robbers+0.082
 trigger+0.081
 battlefield+0.077
Neg logit contributions
So-0.062
-0.060
aw-0.058
 about-0.057
's-0.056
Tokenon
Token ID261
Feature activation+3.09e-02

Pos logit contributions
arter+0.225
 robber+0.213
 trigger+0.202
 robbers+0.195
 battlefield+0.195
Neg logit contributions
So-0.131
aw-0.130
-0.128
 together-0.127
's-0.126
Token!"
Token ID2474
Feature activation-8.08e-03

Pos logit contributions
arter+0.089
 robber+0.084
 trigger+0.081
 pawn+0.079
 battlefield+0.077
Neg logit contributions
So-0.025
aw-0.023
 about-0.020
-0.020
 together-0.020
Token Tim
Token ID5045
Feature activation+2.49e-03

Pos logit contributions
So+0.010
aw+0.009
 about+0.009
 such+0.008
+0.008
Neg logit contributions
arter-0.019
 robber-0.018
 trigger-0.018
 pawn-0.017
 robbers-0.017
Token said
Token ID531
Feature activation-2.11e-03

Pos logit contributions
 robber+0.006
arter+0.006
 robbers+0.006
 trigger+0.006
 pawn+0.005
Neg logit contributions
aw-0.002
 such-0.002
Ab-0.002
Ph-0.002
So-0.002
Token.
Token ID13
Feature activation+1.05e-02

Pos logit contributions
aw+0.002
So+0.002
Ab+0.002
 such+0.002
Ph+0.002
Neg logit contributions
arter-0.005
 robber-0.005
 trigger-0.005
 pawn-0.005
 rook-0.005
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
So+0.013
aw+0.012
Ab+0.012
Ph+0.010
 such+0.010
Neg logit contributions
arter-0.035
 trigger-0.033
 robber-0.033
 pawn-0.031
 rook-0.031
Token He
Token ID679
Feature activation+2.20e-02

Pos logit contributions
arter+0.040
 robber+0.037
 trigger+0.036
 pawn+0.034
 battlefield+0.034
Neg logit contributions
So-0.014
aw-0.013
 about-0.012
 together-0.012
-0.012
Token threw
Token ID9617
Feature activation+4.55e-03

Pos logit contributions
arter+0.052
 robber+0.050
 trigger+0.047
 pawn+0.046
 rook+0.045
Neg logit contributions
So-0.028
aw-0.027
 about-0.025
-0.025
 such-0.024
Token the
Token ID262
Feature activation+1.85e-02

Pos logit contributions
arter+0.014
 robber+0.013
 trigger+0.012
 battlefield+0.012
 pawn+0.012
Neg logit contributions
aw-0.003
So-0.003
 together-0.002
 about-0.002
 such-0.002
Token cr
Token ID1067
Feature activation+3.25e-02

Pos logit contributions
arter+0.039
 robber+0.035
 trigger+0.032
 battlefield+0.032
 pawn+0.031
Neg logit contributions
So-0.029
aw-0.029
 together-0.027
 about-0.027
-0.027
Tokenay
Token ID323
Feature activation+9.56e-02

Pos logit contributions
arter+0.068
 robber+0.066
 robbers+0.060
 trigger+0.060
 battlefield+0.058
Neg logit contributions
So-0.052
aw-0.052
 about-0.049
 of-0.047
-0.047
Tokenons
Token ID684
Feature activation-1.14e-02

Pos logit contributions
arter+0.249
 robber+0.236
 trigger+0.222
 battlefield+0.218
 robbers+0.215
Neg logit contributions
aw-0.110
So-0.105
 together-0.101
's-0.100
 about-0.098
Token and
Token ID290
Feature activation+1.69e-02

Pos logit contributions
So+0.011
aw+0.010
 about+0.009
Ab+0.009
 such+0.009
Neg logit contributions
arter-0.031
 robber-0.029
 trigger-0.028
 pawn-0.027
 rook-0.027
Token the
Token ID262
Feature activation+4.89e-04

Pos logit contributions
arter+0.044
 robber+0.039
 trigger+0.038
 battlefield+0.036
 pawn+0.036
Neg logit contributions
So-0.019
aw-0.019
 together-0.018
's-0.017
 such-0.017
Token scissors
Token ID41786
Feature activation-2.93e-02

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 battlefield+0.001
 pawn+0.001
Neg logit contributions
aw-0.001
So-0.001
's-0.001
-0.001
 together-0.001
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
So+0.025
aw+0.023
Ab+0.020
 about+0.019
+0.019
Neg logit contributions
arter-0.082
 robber-0.077
 trigger-0.076
 pawn-0.073
 rook-0.072
Token wanted
Token ID2227
Feature activation+3.10e-02

Pos logit contributions
So+0.010
aw+0.010
 about+0.009
 such+0.009
+0.009
Neg logit contributions
arter-0.024
 robber-0.023
 trigger-0.022
 pawn-0.021
 rook-0.020
Token to
Token ID284
Feature activation+1.25e-02

Pos logit contributions
arter+0.098
 robber+0.093
 trigger+0.090
 pawn+0.088
 rook+0.087
Neg logit contributions
So-0.017
aw-0.014
-0.011
 about-0.011
 together-0.011
Token throw
Token ID3714
Feature activation+1.06e-02

Pos logit contributions
arter+0.029
 robber+0.026
 trigger+0.026
 battlefield+0.024
 robbers+0.024
Neg logit contributions
So-0.019
-0.018
 such-0.018
 about-0.017
's-0.017
Token the
Token ID262
Feature activation+3.05e-02

Pos logit contributions
arter+0.034
 robber+0.032
 trigger+0.031
 pawn+0.030
 battlefield+0.030
Neg logit contributions
So-0.005
aw-0.005
 together-0.004
 such-0.004
 about-0.004
Token cr
Token ID1067
Feature activation+3.89e-02

Pos logit contributions
arter+0.070
 robber+0.064
 trigger+0.058
 robbers+0.057
 battlefield+0.057
Neg logit contributions
's-0.045
So-0.044
-0.043
aw-0.043
 such-0.042
Tokenay
Token ID323
Feature activation+9.55e-02

Pos logit contributions
arter+0.088
 robber+0.087
 robbers+0.082
 trigger+0.079
 battlefield+0.077
Neg logit contributions
So-0.057
aw-0.054
-0.053
 of-0.053
 about-0.052
Tokenon
Token ID261
Feature activation+2.67e-02

Pos logit contributions
arter+0.244
 robber+0.232
 trigger+0.215
 battlefield+0.214
 robbers+0.213
Neg logit contributions
aw-0.114
's-0.114
 together-0.113
So-0.110
-0.109
Token away
Token ID1497
Feature activation+2.85e-02

Pos logit contributions
arter+0.082
 robber+0.076
 trigger+0.073
 battlefield+0.072
 robbers+0.071
Neg logit contributions
 together-0.020
So-0.019
's-0.019
 by-0.018
-0.018
Token,
Token ID11
Feature activation-3.53e-03

Pos logit contributions
arter+0.078
 robber+0.074
 trigger+0.071
 pawn+0.070
 rook+0.068
Neg logit contributions
So-0.026
aw-0.024
-0.020
Ab-0.020
Ph-0.020
Token but
Token ID475
Feature activation-8.77e-03

Pos logit contributions
So+0.004
aw+0.004
Ab+0.004
+0.004
Ph+0.004
Neg logit contributions
arter-0.008
 robber-0.008
 trigger-0.008
 pawn-0.007
 battlefield-0.007
Token her
Token ID607
Feature activation-3.24e-02

Pos logit contributions
So+0.009
aw+0.008
Ab+0.007
Ph+0.006
 about+0.006
Neg logit contributions
arter-0.023
 robber-0.022
 trigger-0.021
 pawn-0.020
 robbers-0.020
Token They
Token ID1119
Feature activation+1.35e-02

Pos logit contributions
arter+0.049
 robber+0.046
 trigger+0.043
 pawn+0.043
 battlefield+0.042
Neg logit contributions
So-0.031
aw-0.030
 such-0.028
-0.028
Ab-0.027
Token pick
Token ID2298
Feature activation-4.27e-04

Pos logit contributions
arter+0.031
 robber+0.028
 trigger+0.027
 pawn+0.026
 battlefield+0.026
Neg logit contributions
So-0.019
aw-0.018
-0.018
 about-0.017
 together-0.017
Token up
Token ID510
Feature activation-3.99e-03

Pos logit contributions
So+0.001
Ph+0.000
Ab+0.000
 about+0.000
aw+0.000
Neg logit contributions
arter-0.001
 robber-0.001
 trigger-0.001
 pawn-0.001
 rook-0.001
Token the
Token ID262
Feature activation+2.43e-02

Pos logit contributions
So+0.004
aw+0.003
+0.003
 about+0.003
Ph+0.003
Neg logit contributions
arter-0.011
 robber-0.010
 trigger-0.010
 pawn-0.010
 rook-0.009
Token cr
Token ID1067
Feature activation+3.65e-02

Pos logit contributions
arter+0.051
 robber+0.046
 trigger+0.044
 pawn+0.042
 battlefield+0.042
Neg logit contributions
So-0.039
aw-0.038
 about-0.036
-0.036
 together-0.035
Tokenay
Token ID323
Feature activation+9.55e-02

Pos logit contributions
arter+0.076
 robber+0.073
 trigger+0.068
 robbers+0.067
 battlefield+0.064
Neg logit contributions
So-0.059
aw-0.059
 about-0.056
-0.054
 of-0.053
Tokenons
Token ID684
Feature activation-4.60e-04

Pos logit contributions
arter+0.243
 robber+0.230
 trigger+0.221
 battlefield+0.210
 robbers+0.208
Neg logit contributions
aw-0.113
So-0.111
's-0.104
 about-0.104
-0.103
Token and
Token ID290
Feature activation+1.83e-02

Pos logit contributions
So+0.001
aw+0.000
Ab+0.000
Ph+0.000
 such+0.000
Neg logit contributions
arter-0.001
 robber-0.001
 pawn-0.001
 trigger-0.001
 rook-0.001
Token the
Token ID262
Feature activation+5.26e-03

Pos logit contributions
arter+0.041
 robber+0.038
 trigger+0.036
 pawn+0.035
 rook+0.034
Neg logit contributions
So-0.027
aw-0.026
 about-0.024
-0.024
 together-0.024
Token paper
Token ID3348
Feature activation+4.81e-03

Pos logit contributions
arter+0.011
 robber+0.009
 trigger+0.009
 battlefield+0.009
 pawn+0.008
Neg logit contributions
So-0.009
aw-0.008
-0.008
's-0.008
 together-0.008
Token.
Token ID13
Feature activation+2.15e-02

Pos logit contributions
arter+0.013
 robber+0.013
 trigger+0.012
 pawn+0.012
 rook+0.012
Neg logit contributions
So-0.004
aw-0.004
 about-0.004
-0.004
 such-0.003
Token decide
Token ID5409
Feature activation-1.71e-02

Pos logit contributions
arter+0.020
 robber+0.019
 trigger+0.018
 pawn+0.017
 rook+0.017
Neg logit contributions
So-0.015
aw-0.015
 about-0.014
-0.014
 together-0.014
Token to
Token ID284
Feature activation+2.91e-03

Pos logit contributions
aw+0.024
So+0.020
liv+0.018
Ph+0.017
+0.017
Neg logit contributions
 robber-0.038
arter-0.038
 robbers-0.037
 pawn-0.035
 tablet-0.034
Token share
Token ID2648
Feature activation-1.37e-02

Pos logit contributions
arter+0.006
 robber+0.005
 trigger+0.005
 pawn+0.005
 battlefield+0.005
Neg logit contributions
So-0.005
aw-0.005
-0.004
 together-0.004
 about-0.004
Token the
Token ID262
Feature activation+2.19e-02

Pos logit contributions
So+0.017
Ab+0.017
Ph+0.017
aw+0.015
Alice+0.015
Neg logit contributions
arter-0.031
 pawn-0.029
 rook-0.028
 tablet-0.028
 trigger-0.027
Token cr
Token ID1067
Feature activation+4.31e-02

Pos logit contributions
arter+0.046
 robber+0.042
 trigger+0.039
 pawn+0.037
 battlefield+0.037
Neg logit contributions
So-0.036
aw-0.034
-0.033
 together-0.033
's-0.033
Tokenay
Token ID323
Feature activation+9.53e-02

Pos logit contributions
arter+0.087
 robber+0.087
 trigger+0.079
 robbers+0.078
 battlefield+0.074
Neg logit contributions
So-0.072
aw-0.070
 about-0.067
-0.066
 together-0.065
Tokenons
Token ID684
Feature activation-2.36e-03

Pos logit contributions
arter+0.218
 robber+0.208
 trigger+0.197
 pawn+0.186
 battlefield+0.185
Neg logit contributions
So-0.133
aw-0.131
 together-0.122
 about-0.121
-0.120
Token.
Token ID13
Feature activation+7.75e-03

Pos logit contributions
So+0.002
aw+0.002
Ph+0.002
Ab+0.002
Alice+0.002
Neg logit contributions
arter-0.006
 robber-0.006
 pawn-0.006
 rook-0.006
 trigger-0.005
Token They
Token ID1119
Feature activation+8.49e-03

Pos logit contributions
arter+0.014
 robber+0.013
 trigger+0.013
 pawn+0.013
 battlefield+0.012
Neg logit contributions
aw-0.012
Ab-0.012
So-0.012
 such-0.012
-0.011
Token color
Token ID3124
Feature activation+4.10e-03

Pos logit contributions
arter+0.017
 robber+0.016
 trigger+0.015
 pawn+0.015
 rook+0.014
Neg logit contributions
So-0.014
aw-0.013
 about-0.013
-0.012
 together-0.012
Token the
Token ID262
Feature activation-2.40e-03

Pos logit contributions
arter+0.012
 robber+0.011
 trigger+0.011
 pawn+0.010
 rook+0.010
Neg logit contributions
So-0.004
aw-0.003
-0.003
Ab-0.003
Ph-0.003
Token.
Token ID13
Feature activation+1.93e-02

Pos logit contributions
So+0.003
aw+0.003
Ab+0.003
 such+0.003
+0.003
Neg logit contributions
arter-0.010
 robber-0.009
 trigger-0.009
 pawn-0.008
 robbers-0.008
Token He
Token ID679
Feature activation+1.18e-02

Pos logit contributions
arter+0.039
 robber+0.036
 trigger+0.034
 pawn+0.033
 rook+0.032
Neg logit contributions
So-0.032
aw-0.031
-0.029
 about-0.029
 together-0.029
Token dropped
Token ID5710
Feature activation+5.13e-03

Pos logit contributions
arter+0.029
 robber+0.028
 trigger+0.026
 pawn+0.025
 battlefield+0.025
Neg logit contributions
So-0.014
aw-0.013
 about-0.012
-0.012
 together-0.012
Token the
Token ID262
Feature activation+1.59e-02

Pos logit contributions
arter+0.014
 robber+0.014
 trigger+0.013
 pawn+0.013
 rook+0.013
Neg logit contributions
So-0.004
aw-0.004
-0.003
 about-0.003
 together-0.003
Token cr
Token ID1067
Feature activation+3.41e-02

Pos logit contributions
arter+0.030
 robber+0.023
sing+0.023
 battlefield+0.023
alks+0.021
Neg logit contributions
's-0.030
 by-0.029
So-0.029
 right-0.028
-0.028
Tokenay
Token ID323
Feature activation+9.51e-02

Pos logit contributions
arter+0.080
 robber+0.076
 robbers+0.074
sing+0.071
 battlefield+0.070
Neg logit contributions
aw-0.046
So-0.045
 of-0.044
-0.041
 about-0.041
Tokenon
Token ID261
Feature activation+2.61e-02

Pos logit contributions
arter+0.265
 robber+0.250
sing+0.241
 battlefield+0.236
 trigger+0.233
Neg logit contributions
aw-0.094
's-0.089
 together-0.087
 of-0.086
So-0.083
Token and
Token ID290
Feature activation+1.03e-02

Pos logit contributions
arter+0.082
 robber+0.077
 trigger+0.073
 battlefield+0.072
 robbers+0.072
Neg logit contributions
So-0.015
 together-0.013
-0.013
's-0.013
aw-0.013
Token the
Token ID262
Feature activation-3.90e-03

Pos logit contributions
arter+0.024
 robber+0.023
 trigger+0.022
 pawn+0.022
 robbers+0.021
Neg logit contributions
So-0.013
aw-0.012
 about-0.012
-0.012
Ab-0.011
Token folder
Token ID9483
Feature activation-3.88e-03

Pos logit contributions
So+0.006
's+0.006
aw+0.006
+0.006
 by+0.006
Neg logit contributions
arter-0.008
 robber-0.007
 battlefield-0.006
 trigger-0.006
sing-0.006
Token.
Token ID13
Feature activation+1.87e-02

Pos logit contributions
So+0.004
aw+0.003
Ab+0.003
 such+0.003
Ph+0.003
Neg logit contributions
arter-0.010
 robber-0.010
 trigger-0.010
 pawn-0.009
 rook-0.009
Token to
Token ID284
Feature activation+9.86e-03

Pos logit contributions
arter+0.058
 robber+0.056
 pawn+0.054
 trigger+0.054
 rook+0.053
Neg logit contributions
So-0.015
aw-0.014
Ph-0.011
-0.011
Ab-0.010
Token play
Token ID711
Feature activation+2.60e-02

Pos logit contributions
arter+0.023
 robber+0.021
 trigger+0.021
 battlefield+0.020
 pawn+0.019
Neg logit contributions
So-0.015
-0.014
 about-0.013
's-0.013
 such-0.013
Token with
Token ID351
Feature activation+1.87e-02

Pos logit contributions
arter+0.079
 robber+0.075
 trigger+0.072
 pawn+0.071
 rook+0.069
Neg logit contributions
So-0.017
aw-0.015
-0.012
Ab-0.012
Ph-0.011
Token the
Token ID262
Feature activation+2.33e-02

Pos logit contributions
arter+0.061
 robber+0.057
 trigger+0.055
 battlefield+0.054
 pawn+0.053
Neg logit contributions
aw-0.008
 such-0.008
So-0.008
 together-0.007
 about-0.007
Token cr
Token ID1067
Feature activation+4.43e-02

Pos logit contributions
arter+0.048
 robber+0.044
 trigger+0.041
 pawn+0.039
 battlefield+0.039
Neg logit contributions
So-0.039
aw-0.037
 about-0.036
-0.035
 together-0.035
Tokenay
Token ID323
Feature activation+9.45e-02

Pos logit contributions
arter+0.094
 robber+0.093
 trigger+0.087
 robbers+0.085
 battlefield+0.081
Neg logit contributions
So-0.070
aw-0.066
 about-0.066
-0.064
 of-0.063
Tokenons
Token ID684
Feature activation+7.63e-05

Pos logit contributions
arter+0.229
 robber+0.219
 trigger+0.209
 battlefield+0.199
 robbers+0.198
Neg logit contributions
aw-0.119
So-0.119
 together-0.114
 about-0.113
's-0.113
Token too
Token ID1165
Feature activation+1.62e-02

Pos logit contributions
arter+0.000
 robber+0.000
 trigger+0.000
 pawn+0.000
 rook+0.000
Neg logit contributions
So-0.000
aw-0.000
Ab-0.000
Ph-0.000
It-0.000
Token.
Token ID13
Feature activation+2.69e-03

Pos logit contributions
arter+0.048
 robber+0.045
 trigger+0.043
 pawn+0.042
 rook+0.041
Neg logit contributions
So-0.012
aw-0.011
 such-0.009
-0.009
Ab-0.009
Token She
Token ID1375
Feature activation-6.53e-03

Pos logit contributions
arter+0.007
 robber+0.007
 trigger+0.006
 pawn+0.006
 battlefield+0.006
Neg logit contributions
So-0.003
aw-0.003
 about-0.002
-0.002
 such-0.002
Token took
Token ID1718
Feature activation+7.77e-03

Pos logit contributions
So+0.007
aw+0.007
 such+0.007
 about+0.007
 together+0.006
Neg logit contributions
arter-0.016
 robber-0.016
 trigger-0.014
 pawn-0.014
 robbers-0.014
Token tried
Token ID3088
Feature activation+1.36e-02

Pos logit contributions
arter+0.032
 robber+0.031
 pawn+0.029
 trigger+0.029
 rook+0.029
Neg logit contributions
So-0.017
aw-0.016
 about-0.015
 such-0.015
-0.014
Token to
Token ID284
Feature activation+3.36e-02

Pos logit contributions
arter+0.039
 robber+0.036
 pawn+0.035
 trigger+0.035
 rook+0.035
Neg logit contributions
So-0.011
aw-0.010
Ph-0.008
-0.008
Ab-0.008
Token remove
Token ID4781
Feature activation-1.37e-02

Pos logit contributions
arter+0.078
 robber+0.070
 trigger+0.067
 battlefield+0.065
 pawn+0.065
Neg logit contributions
So-0.050
-0.045
 together-0.045
 by-0.043
 such-0.043
Token the
Token ID262
Feature activation+1.71e-02

Pos logit contributions
So+0.010
aw+0.008
 about+0.007
+0.007
Ab+0.007
Neg logit contributions
arter-0.040
 robber-0.038
 trigger-0.038
 pawn-0.036
 rook-0.035
Token cr
Token ID1067
Feature activation+4.11e-02

Pos logit contributions
arter+0.039
 robber+0.036
 battlefield+0.032
 robbers+0.031
 trigger+0.031
Neg logit contributions
's-0.024
So-0.024
-0.024
 by-0.023
 together-0.023
Tokenay
Token ID323
Feature activation+9.38e-02

Pos logit contributions
 robber+0.092
arter+0.090
 robbers+0.085
 trigger+0.080
 battlefield+0.078
Neg logit contributions
So-0.062
aw-0.059
-0.058
 of-0.057
's-0.056
Tokenon
Token ID261
Feature activation+3.25e-02

Pos logit contributions
arter+0.237
 robber+0.231
 trigger+0.210
 robbers+0.210
 battlefield+0.208
Neg logit contributions
aw-0.112
So-0.112
 together-0.110
's-0.110
-0.107
Token marks
Token ID8849
Feature activation+2.36e-02

Pos logit contributions
arter+0.103
 robber+0.098
 trigger+0.092
 robbers+0.091
 battlefield+0.091
Neg logit contributions
So-0.019
 together-0.018
's-0.017
-0.016
 about-0.015
Token,
Token ID11
Feature activation+3.02e-03

Pos logit contributions
arter+0.064
 robber+0.060
 trigger+0.060
 pawn+0.057
 rook+0.056
Neg logit contributions
So-0.022
aw-0.020
Ab-0.018
Ph-0.017
 such-0.017
Token but
Token ID475
Feature activation+6.81e-03

Pos logit contributions
arter+0.008
 robber+0.007
 trigger+0.007
 pawn+0.007
 battlefield+0.007
Neg logit contributions
So-0.003
aw-0.003
 about-0.003
-0.003
 together-0.003
Token it
Token ID340
Feature activation-1.24e-03

Pos logit contributions
arter+0.019
 robber+0.018
 trigger+0.018
 pawn+0.017
 rook+0.017
Neg logit contributions
So-0.006
aw-0.006
Ab-0.005
Ph-0.004
-0.004
Token did
Token ID750
Feature activation+2.79e-02

Pos logit contributions
arter+0.013
 robber+0.011
 trigger+0.011
 battlefield+0.011
 pawn+0.011
Neg logit contributions
So-0.004
-0.004
's-0.004
aw-0.004
 together-0.004
Token not
Token ID407
Feature activation+1.54e-02

Pos logit contributions
arter+0.081
 robber+0.077
 trigger+0.074
 pawn+0.072
 rook+0.070
Neg logit contributions
So-0.022
aw-0.020
 about-0.018
-0.018
 together-0.018
Token remove
Token ID4781
Feature activation-8.58e-03

Pos logit contributions
arter+0.037
 trigger+0.036
 robber+0.033
 battlefield+0.032
sing+0.032
Neg logit contributions
-0.020
So-0.019
 about-0.019
 such-0.018
aw-0.018
Token the
Token ID262
Feature activation+1.88e-02

Pos logit contributions
So+0.006
aw+0.005
 about+0.004
+0.004
Ab+0.004
Neg logit contributions
arter-0.026
 robber-0.024
 trigger-0.024
 pawn-0.023
 rook-0.023
Token cr
Token ID1067
Feature activation+4.25e-02

Pos logit contributions
arter+0.033
 robber+0.030
 trigger+0.026
 pawn+0.026
 robbers+0.026
Neg logit contributions
's-0.035
aw-0.035
 by-0.034
-0.034
 about-0.034
Tokenay
Token ID323
Feature activation+9.34e-02

Pos logit contributions
 robber+0.095
arter+0.094
 robbers+0.089
 trigger+0.085
 pawn+0.082
Neg logit contributions
So-0.062
aw-0.061
-0.058
 of-0.058
's-0.058
Tokenon
Token ID261
Feature activation+3.30e-02

Pos logit contributions
arter+0.256
 robber+0.247
 robbers+0.228
 trigger+0.228
sing+0.226
Neg logit contributions
aw-0.098
's-0.095
 together-0.090
So-0.089
-0.089
Token marks
Token ID8849
Feature activation+2.56e-02

Pos logit contributions
arter+0.104
 robber+0.100
 trigger+0.095
 robbers+0.093
 pawn+0.093
Neg logit contributions
So-0.018
-0.017
 together-0.017
's-0.017
aw-0.015
Token.
Token ID13
Feature activation+2.24e-02

Pos logit contributions
arter+0.074
 robber+0.070
 trigger+0.067
 pawn+0.065
 rook+0.064
Neg logit contributions
So-0.021
aw-0.018
Ab-0.015
 about-0.015
-0.015
Token You
Token ID921
Feature activation+6.49e-03

Pos logit contributions
arter+0.056
 robber+0.053
 trigger+0.050
 pawn+0.049
 rook+0.048
Neg logit contributions
So-0.027
aw-0.025
 about-0.023
-0.023
 together-0.023
Token made
Token ID925
Feature activation+2.06e-02

Pos logit contributions
arter+0.018
 robber+0.017
 trigger+0.016
 battlefield+0.016
 pawn+0.016
Neg logit contributions
So-0.006
aw-0.006
-0.006
's-0.006
 about-0.005
Token
Token ID198
Feature activation+1.60e-02

Pos logit contributions
arter+0.012
 robber+0.012
 trigger+0.011
 pawn+0.011
 battlefield+0.011
Neg logit contributions
aw-0.003
So-0.002
 such-0.002
 about-0.002
Ab-0.002
TokenHe
Token ID1544
Feature activation+1.32e-02

Pos logit contributions
arter+0.041
 robber+0.040
 trigger+0.037
 pawn+0.037
 robbers+0.036
Neg logit contributions
aw-0.016
So-0.016
 about-0.016
 such-0.015
 together-0.014
Token takes
Token ID2753
Feature activation+5.35e-03

Pos logit contributions
arter+0.031
 robber+0.029
 trigger+0.027
 pawn+0.026
 rook+0.026
Neg logit contributions
So-0.018
aw-0.017
 about-0.016
-0.016
 together-0.016
Token the
Token ID262
Feature activation+1.06e-02

Pos logit contributions
arter+0.016
 robber+0.015
 trigger+0.014
 pawn+0.014
 battlefield+0.014
Neg logit contributions
So-0.004
aw-0.004
 together-0.003
 such-0.003
 about-0.003
Token cr
Token ID1067
Feature activation+3.04e-02

Pos logit contributions
arter+0.025
 robber+0.021
 battlefield+0.020
alks+0.019
 trigger+0.019
Neg logit contributions
's-0.015
-0.014
 right-0.014
 by-0.014
So-0.014
Tokenay
Token ID323
Feature activation+9.34e-02

Pos logit contributions
arter+0.068
 robber+0.067
 robbers+0.063
 trigger+0.061
 battlefield+0.059
Neg logit contributions
So-0.045
aw-0.045
 of-0.041
's-0.040
-0.040
Tokenons
Token ID684
Feature activation-1.76e-02

Pos logit contributions
arter+0.249
 robber+0.237
 trigger+0.223
 robbers+0.217
 battlefield+0.215
Neg logit contributions
aw-0.103
's-0.101
So-0.100
-0.094
 together-0.094
Token from
Token ID422
Feature activation-3.79e-03

Pos logit contributions
So+0.015
aw+0.014
 about+0.012
+0.012
 such+0.012
Neg logit contributions
arter-0.049
 robber-0.047
 trigger-0.045
 pawn-0.044
 rook-0.043
Token them
Token ID606
Feature activation-6.89e-03

Pos logit contributions
 it+0.002
 the+0.002
 together+0.001
 such+0.001
 by+0.001
Neg logit contributions
arter-0.012
 robber-0.011
 pawn-0.011
 trigger-0.011
 rook-0.011
Token.
Token ID13
Feature activation+2.08e-02

Pos logit contributions
So+0.004
aw+0.004
 about+0.003
+0.003
 together+0.003
Neg logit contributions
arter-0.021
 robber-0.020
 trigger-0.019
 pawn-0.019
 rook-0.018
Token He
Token ID679
Feature activation+1.30e-02

Pos logit contributions
arter+0.048
 robber+0.044
 trigger+0.044
 pawn+0.041
 rook+0.041
Neg logit contributions
So-0.028
 about-0.027
aw-0.026
-0.026
 together-0.025
Token I
Token ID314
Feature activation+7.35e-03

Pos logit contributions
aw+0.016
So+0.015
 about+0.014
 such+0.013
Ab+0.013
Neg logit contributions
arter-0.028
 robber-0.027
 trigger-0.025
 pawn-0.025
 rook-0.024
Token use
Token ID779
Feature activation+1.12e-02

Pos logit contributions
arter+0.017
 trigger+0.016
 robber+0.015
 battlefield+0.015
alks+0.014
Neg logit contributions
So-0.011
-0.011
's-0.010
 together-0.010
-0.009
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
arter+0.034
 robber+0.032
 trigger+0.031
 pawn+0.029
 battlefield+0.029
Neg logit contributions
So-0.008
aw-0.007
 together-0.007
 such-0.007
 about-0.007
Token red
Token ID2266
Feature activation+5.74e-02

Pos logit contributions
arter+0.059
 robber+0.052
 trigger+0.049
 battlefield+0.047
 robbers+0.046
Neg logit contributions
's-0.035
So-0.035
-0.033
 by-0.033
aw-0.033
Token cr
Token ID1067
Feature activation+3.63e-02

Pos logit contributions
arter+0.151
 robber+0.133
 robbers+0.123
 battlefield+0.123
 trigger+0.121
Neg logit contributions
's-0.076
 together-0.070
aw-0.068
 by-0.067
 to-0.065
Tokenay
Token ID323
Feature activation+9.33e-02

Pos logit contributions
arter+0.083
 robber+0.081
 trigger+0.077
 robbers+0.076
 battlefield+0.071
Neg logit contributions
So-0.051
aw-0.050
 about-0.048
 of-0.048
-0.047
Tokenon
Token ID261
Feature activation+2.55e-02

Pos logit contributions
arter+0.251
 robber+0.237
 trigger+0.230
 battlefield+0.219
 robbers+0.219
Neg logit contributions
aw-0.102
's-0.101
 together-0.100
So-0.096
 of-0.094
Token?
Token ID30
Feature activation+1.71e-02

Pos logit contributions
arter+0.074
 trigger+0.069
 robber+0.069
 robbers+0.065
 battlefield+0.064
Neg logit contributions
 together-0.023
 about-0.021
's-0.021
 by-0.020
So-0.020
Token I
Token ID314
Feature activation-1.15e-02

Pos logit contributions
arter+0.041
 robber+0.038
 trigger+0.036
 pawn+0.035
 rook+0.034
Neg logit contributions
So-0.022
aw-0.021
 about-0.019
-0.019
 together-0.019
Token want
Token ID765
Feature activation+1.84e-02

Pos logit contributions
So+0.013
+0.013
 together+0.012
aw+0.012
 about+0.012
Neg logit contributions
arter-0.030
 robber-0.027
 trigger-0.027
 battlefield-0.026
 pawn-0.025
Token to
Token ID284
Feature activation+2.21e-02

Pos logit contributions
arter+0.055
 robber+0.052
 pawn+0.051
 trigger+0.050
 rook+0.050
Neg logit contributions
So-0.012
aw-0.011
Ph-0.009
-0.009
Ab-0.008
Token trying
Token ID2111
Feature activation+1.49e-02

Pos logit contributions
arter+0.034
 robber+0.032
 trigger+0.031
 pawn+0.030
 battlefield+0.029
Neg logit contributions
So-0.019
aw-0.019
 about-0.018
-0.018
 together-0.018
Token to
Token ID284
Feature activation+2.38e-02

Pos logit contributions
arter+0.046
 robber+0.044
 trigger+0.042
 pawn+0.042
 rook+0.041
Neg logit contributions
So-0.008
aw-0.008
-0.006
 about-0.006
Ab-0.005
Token get
Token ID651
Feature activation-4.19e-03

Pos logit contributions
arter+0.054
 robber+0.049
 trigger+0.047
 battlefield+0.044
 robbers+0.044
Neg logit contributions
So-0.037
-0.035
 such-0.034
's-0.034
 together-0.033
Token the
Token ID262
Feature activation+1.21e-02

Pos logit contributions
So+0.003
aw+0.002
 together+0.002
 about+0.002
 such+0.002
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.012
 pawn-0.011
 battlefield-0.011
Token cr
Token ID1067
Feature activation+3.79e-02

Pos logit contributions
arter+0.029
alks+0.023
 battlefield+0.021
sing+0.021
 lobster+0.021
Neg logit contributions
 right-0.018
's-0.017
 together-0.017
 by-0.017
 more-0.016
Tokenay
Token ID323
Feature activation+9.33e-02

Pos logit contributions
arter+0.088
 robber+0.088
 robbers+0.084
 trigger+0.082
 battlefield+0.078
Neg logit contributions
So-0.050
 of-0.049
 about-0.047
-0.046
aw-0.046
Tokenons
Token ID684
Feature activation-3.80e-03

Pos logit contributions
arter+0.259
 robber+0.241
 trigger+0.232
 spine+0.227
 battlefield+0.226
Neg logit contributions
 together-0.100
's-0.098
aw-0.089
-0.088
 of-0.088
Token from
Token ID422
Feature activation-1.29e-02

Pos logit contributions
So+0.003
aw+0.003
+0.003
 together+0.003
 about+0.003
Neg logit contributions
arter-0.011
 robber-0.010
 trigger-0.010
 pawn-0.010
 battlefield-0.010
Token the
Token ID262
Feature activation-1.83e-02

Pos logit contributions
 such+0.005
 together+0.005
 by+0.004
 about+0.004
 it+0.004
Neg logit contributions
arter-0.043
 trigger-0.040
 robber-0.040
 pawn-0.038
 rook-0.037
Token cabinet
Token ID13447
Feature activation-1.72e-02

Pos logit contributions
 right+0.033
 by+0.032
's+0.031
So+0.031
+0.031
Neg logit contributions
arter-0.035
 trigger-0.029
alks-0.029
 robber-0.027
sing-0.027
Token,
Token ID11
Feature activation-3.68e-03

Pos logit contributions
So+0.015
aw+0.014
 about+0.012
+0.012
 together+0.012
Neg logit contributions
arter-0.048
 robber-0.046
 trigger-0.044
 pawn-0.043
 rook-0.042
Token,
Token ID11
Feature activation-1.61e-02

Pos logit contributions
So+0.014
aw+0.012
Ab+0.011
Ph+0.011
uct+0.010
Neg logit contributions
 robber-0.024
arter-0.024
 robbers-0.023
 pawn-0.023
 rook-0.022
Token she
Token ID673
Feature activation-3.82e-02

Pos logit contributions
So+0.015
aw+0.014
Ph+0.012
Ab+0.012
 about+0.011
Neg logit contributions
arter-0.043
 robber-0.041
 pawn-0.039
 trigger-0.038
 robbers-0.038
Token would
Token ID561
Feature activation-1.54e-02

Pos logit contributions
So+0.037
aw+0.035
 about+0.031
+0.031
 together+0.030
Neg logit contributions
arter-0.104
 robber-0.098
 trigger-0.094
 pawn-0.091
 rook-0.089
Token bring
Token ID2222
Feature activation-1.65e-02

Pos logit contributions
So+0.020
+0.018
 about+0.018
aw+0.018
 together+0.018
Neg logit contributions
arter-0.037
 robber-0.034
 trigger-0.033
 pawn-0.032
 rook-0.031
Token a
Token ID257
Feature activation-1.38e-02

Pos logit contributions
So+0.015
aw+0.014
+0.012
Ab+0.012
 about+0.011
Neg logit contributions
arter-0.044
 robber-0.043
 trigger-0.040
 pawn-0.040
 rook-0.039
Token stool
Token ID38753
Feature activation-9.70e-02

Pos logit contributions
So+0.018
aw+0.017
+0.016
 about+0.016
 together+0.016
Neg logit contributions
arter-0.033
 robber-0.030
 trigger-0.029
 pawn-0.028
 battlefield-0.027
Token so
Token ID523
Feature activation+1.07e-04

Pos logit contributions
So+0.078
aw+0.072
Ab+0.062
Ph+0.058
+0.056
Neg logit contributions
arter-0.273
 robber-0.264
 trigger-0.250
 pawn-0.248
 rook-0.243
Token she
Token ID673
Feature activation-4.58e-02

Pos logit contributions
arter+0.000
 robber+0.000
 trigger+0.000
alks+0.000
 pawn+0.000
Neg logit contributions
So-0.000
aw-0.000
 such-0.000
Ph-0.000
's-0.000
Token could
Token ID714
Feature activation-1.05e-02

Pos logit contributions
So+0.051
aw+0.048
 about+0.043
Ab+0.042
 such+0.042
Neg logit contributions
arter-0.115
 robber-0.110
 trigger-0.105
 pawn-0.103
 rook-0.100
Token see
Token ID766
Feature activation+2.67e-03

Pos logit contributions
So+0.017
aw+0.016
+0.016
 about+0.016
 together+0.015
Neg logit contributions
arter-0.022
 robber-0.020
 trigger-0.019
 pawn-0.018
 battlefield-0.018
Token on
Token ID319
Feature activation-1.87e-02

Pos logit contributions
arter+0.006
 robber+0.006
 pawn+0.006
 trigger+0.006
 robbers+0.005
Neg logit contributions
So-0.003
Ph-0.002
Ab-0.002
aw-0.002
-0.002
Token.
Token ID13
Feature activation-1.41e-03

Pos logit contributions
arter+0.050
 robber+0.046
 trigger+0.045
 pawn+0.045
 battlefield+0.044
Neg logit contributions
aw-0.016
So-0.016
Ab-0.015
Ph-0.014
 such-0.013
Token Lily
Token ID20037
Feature activation-2.21e-02

Pos logit contributions
aw+0.002
So+0.002
 such+0.002
+0.002
Ab+0.002
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 pawn-0.003
 battlefield-0.003
Token stepped
Token ID10764
Feature activation-1.69e-02

Pos logit contributions
aw+0.025
Ab+0.025
 such+0.024
Ph+0.023
So+0.023
Neg logit contributions
 pawn-0.046
 robber-0.046
arter-0.045
 tablet-0.044
 rook-0.043
Token on
Token ID319
Feature activation-8.84e-03

Pos logit contributions
So+0.021
aw+0.020
Ab+0.019
Ph+0.018
 about+0.017
Neg logit contributions
arter-0.038
 robber-0.037
 trigger-0.037
 pawn-0.035
 robbers-0.034
Token a
Token ID257
Feature activation-5.16e-04

Pos logit contributions
So+0.007
aw+0.007
Ab+0.005
 about+0.005
+0.005
Neg logit contributions
arter-0.024
 robber-0.024
 trigger-0.023
 pawn-0.023
 rook-0.022
Token stool
Token ID38753
Feature activation-8.93e-02

Pos logit contributions
So+0.001
aw+0.001
 about+0.001
 together+0.001
+0.001
Neg logit contributions
arter-0.001
 robber-0.001
 trigger-0.001
 pawn-0.001
 rook-0.001
Token to
Token ID284
Feature activation-1.03e-02

Pos logit contributions
So+0.096
aw+0.090
Ab+0.088
Ph+0.081
 such+0.076
Neg logit contributions
arter-0.220
 robber-0.216
 trigger-0.206
 pawn-0.199
 battlefield-0.198
Token reach
Token ID3151
Feature activation-1.19e-02

Pos logit contributions
So+0.015
aw+0.014
+0.014
 about+0.013
 such+0.013
Neg logit contributions
arter-0.024
 robber-0.022
 trigger-0.021
 pawn-0.020
 battlefield-0.020
Token the
Token ID262
Feature activation-3.94e-03

Pos logit contributions
So+0.011
aw+0.010
Ab+0.008
Ph+0.008
+0.007
Neg logit contributions
arter-0.033
 robber-0.031
 trigger-0.030
 pawn-0.029
alks-0.029
Token top
Token ID1353
Feature activation+2.09e-03

Pos logit contributions
aw+0.007
So+0.007
's+0.007
+0.007
 about+0.007
Neg logit contributions
arter-0.007
 robber-0.007
 pawn-0.006
 trigger-0.006
 battlefield-0.006
Token of
Token ID286
Feature activation-2.11e-02

Pos logit contributions
arter+0.006
 robber+0.005
 trigger+0.005
 pawn+0.005
 rook+0.005
Neg logit contributions
So-0.002
aw-0.002
Ab-0.001
Ph-0.001
 such-0.001
Token,
Token ID11
Feature activation+9.69e-04

Pos logit contributions
arter+0.041
 robber+0.040
 trigger+0.037
 pawn+0.036
 robbers+0.036
Neg logit contributions
aw-0.029
So-0.027
Ph-0.026
Ab-0.025
It-0.023
Token Amy
Token ID14235
Feature activation-4.25e-02

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.002
 pawn+0.002
 robbers+0.002
Neg logit contributions
aw-0.001
So-0.001
Ph-0.001
Ab-0.001
-0.001
Token got
Token ID1392
Feature activation-9.31e-03

Pos logit contributions
 such+0.053
So+0.051
Ph+0.051
aw+0.050
Ab+0.050
Neg logit contributions
 robber-0.086
arter-0.083
 pawn-0.081
 robbers-0.078
 trigger-0.078
Token a
Token ID257
Feature activation-1.54e-02

Pos logit contributions
So+0.012
aw+0.012
Ph+0.010
Alice+0.010
 about+0.010
Neg logit contributions
 robber-0.020
arter-0.020
 trigger-0.019
 robbers-0.019
 pawn-0.018
Token little
Token ID1310
Feature activation+1.66e-02

Pos logit contributions
So+0.027
aw+0.025
+0.025
 about+0.025
 together+0.024
Neg logit contributions
arter-0.030
 robber-0.027
 trigger-0.026
 pawn-0.024
 battlefield-0.024
Token stool
Token ID38753
Feature activation-8.85e-02

Pos logit contributions
arter+0.031
 robber+0.031
 trigger+0.029
 pawn+0.028
 robbers+0.027
Neg logit contributions
aw-0.027
So-0.027
Ab-0.025
 such-0.025
Ph-0.025
Token from
Token ID422
Feature activation-2.10e-02

Pos logit contributions
So+0.097
Ab+0.095
aw+0.095
Ph+0.089
 such+0.081
Neg logit contributions
arter-0.209
 robber-0.207
 trigger-0.197
 pawn-0.191
 rook-0.187
Token her
Token ID607
Feature activation-3.01e-02

Pos logit contributions
So+0.016
aw+0.015
+0.013
 about+0.012
 together+0.012
Neg logit contributions
arter-0.061
 robber-0.058
 trigger-0.056
 pawn-0.054
 battlefield-0.053
Token house
Token ID2156
Feature activation-2.56e-02

Pos logit contributions
So+0.054
aw+0.053
 about+0.049
+0.049
 together+0.049
Neg logit contributions
arter-0.057
 robber-0.052
 trigger-0.049
 pawn-0.047
 rook-0.046
Token and
Token ID290
Feature activation-8.37e-03

Pos logit contributions
So+0.025
aw+0.024
Ab+0.023
Ph+0.022
+0.020
Neg logit contributions
arter-0.066
 robber-0.063
 trigger-0.060
 pawn-0.059
 battlefield-0.058
Token put
Token ID1234
Feature activation-2.10e-02

Pos logit contributions
aw+0.013
So+0.013
Ph+0.012
Ab+0.011
 such+0.011
Neg logit contributions
 robber-0.015
 robbers-0.015
 pawn-0.015
arter-0.015
 trigger-0.014
Tokenpron
Token ID31186
Feature activation-3.36e-02

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.002
 battlefield+0.002
alks+0.002
Neg logit contributions
So-0.001
-0.001
's-0.001
 together-0.001
aw-0.001
Token and
Token ID290
Feature activation+2.97e-04

Pos logit contributions
So+0.027
aw+0.024
+0.021
 about+0.020
 such+0.020
Neg logit contributions
arter-0.097
 robber-0.092
 trigger-0.089
 pawn-0.086
 rook-0.084
Token climbed
Token ID19952
Feature activation-2.60e-02

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 pawn+0.001
 rook+0.001
Neg logit contributions
So-0.000
aw-0.000
 about-0.000
 such-0.000
-0.000
Token on
Token ID319
Feature activation-8.00e-03

Pos logit contributions
So+0.037
aw+0.032
Ph+0.030
Ab+0.028
 about+0.027
Neg logit contributions
arter-0.055
 robber-0.054
 trigger-0.053
alks-0.053
 pawn-0.052
Token a
Token ID257
Feature activation+3.61e-03

Pos logit contributions
So+0.007
aw+0.007
 about+0.006
Ph+0.006
+0.006
Neg logit contributions
arter-0.021
 robber-0.020
 pawn-0.019
 trigger-0.019
 rook-0.019
Token stool
Token ID38753
Feature activation-8.79e-02

Pos logit contributions
arter+0.006
 robber+0.006
 trigger+0.006
 pawn+0.005
 rook+0.005
Neg logit contributions
So-0.007
aw-0.007
 about-0.006
 such-0.006
-0.006
Token.
Token ID13
Feature activation-4.70e-03

Pos logit contributions
So+0.092
aw+0.081
Ab+0.080
Ph+0.077
 such+0.073
Neg logit contributions
arter-0.215
 robber-0.212
 trigger-0.209
 pawn-0.199
 battlefield-0.198
Token She
Token ID1375
Feature activation-6.60e-03

Pos logit contributions
So+0.005
aw+0.004
 about+0.004
+0.004
 together+0.004
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.012
 pawn-0.011
 rook-0.011
Token wanted
Token ID2227
Feature activation+3.19e-02

Pos logit contributions
So+0.010
 such+0.009
aw+0.009
Ph+0.009
Ab+0.008
Neg logit contributions
 robber-0.012
 pawn-0.012
arter-0.012
 rook-0.012
 robbers-0.011
Token to
Token ID284
Feature activation+9.65e-03

Pos logit contributions
arter+0.080
 robber+0.079
 pawn+0.076
 robbers+0.075
 rook+0.074
Neg logit contributions
So-0.032
aw-0.028
Ph-0.026
-0.022
Ab-0.022
Token weigh
Token ID10164
Feature activation+3.88e-04

Pos logit contributions
arter+0.022
 trigger+0.020
 robber+0.020
 battlefield+0.019
 pawn+0.018
Neg logit contributions
-0.014
So-0.014
 such-0.013
's-0.013
 about-0.013
Token grabbed
Token ID13176
Feature activation-2.99e-03

Pos logit contributions
aw+0.020
So+0.020
 such+0.019
 about+0.018
Ab+0.018
Neg logit contributions
arter-0.048
 robber-0.046
 pawn-0.044
 trigger-0.044
 rook-0.043
Token a
Token ID257
Feature activation+8.36e-03

Pos logit contributions
 such+0.001
 together+0.001
 about+0.001
+0.001
So+0.001
Neg logit contributions
arter-0.010
 robber-0.009
 battlefield-0.009
 trigger-0.009
 pawn-0.009
Token broom
Token ID47085
Feature activation-5.27e-02

Pos logit contributions
arter+0.016
 robber+0.015
 trigger+0.014
 pawn+0.013
 battlefield+0.013
Neg logit contributions
So-0.015
aw-0.014
-0.014
 about-0.014
 together-0.013
Token and
Token ID290
Feature activation-5.31e-04

Pos logit contributions
So+0.046
aw+0.043
 about+0.038
+0.038
 together+0.036
Neg logit contributions
arter-0.148
 robber-0.140
 trigger-0.135
 pawn-0.131
 rook-0.128
Token dust
Token ID8977
Feature activation-4.08e-02

Pos logit contributions
aw+0.001
So+0.001
 about+0.001
Ab+0.001
Ph+0.001
Neg logit contributions
arter-0.001
 robber-0.001
 trigger-0.001
 pawn-0.001
 robbers-0.001
Tokenpan
Token ID6839
Feature activation-8.70e-02

Pos logit contributions
So+0.085
aw+0.079
+0.076
Ab+0.075
Ph+0.072
Neg logit contributions
arter-0.065
 trigger-0.063
 robber-0.062
 pawn-0.054
alks-0.051
Token and
Token ID290
Feature activation+6.75e-04

Pos logit contributions
So+0.107
Ab+0.103
aw+0.102
+0.101
We+0.092
Neg logit contributions
arter-0.187
 robber-0.179
 trigger-0.179
sing-0.179
 spine-0.177
Token swept
Token ID17676
Feature activation-2.71e-02

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 pawn+0.001
 robbers+0.001
Neg logit contributions
aw-0.001
So-0.001
Ab-0.001
Ph-0.001
 about-0.001
Token up
Token ID510
Feature activation-2.31e-02

Pos logit contributions
So+0.030
aw+0.027
 about+0.024
Ab+0.024
+0.024
Neg logit contributions
arter-0.066
 trigger-0.064
 robber-0.064
 pawn-0.061
alks-0.058
Token the
Token ID262
Feature activation+7.28e-03

Pos logit contributions
So+0.017
aw+0.016
 about+0.013
+0.012
Ab+0.011
Neg logit contributions
arter-0.068
 robber-0.065
 trigger-0.062
 pawn-0.061
 rook-0.060
Token ash
Token ID12530
Feature activation+9.29e-04

Pos logit contributions
arter+0.013
 robber+0.012
 trigger+0.011
 pawn+0.010
 battlefield+0.010
Neg logit contributions
So-0.014
aw-0.014
 about-0.013
-0.013
 together-0.013
Token a
Token ID257
Feature activation-1.49e-02

Pos logit contributions
So+0.019
aw+0.018
Ab+0.016
Ph+0.016
Alice+0.015
Neg logit contributions
 robber-0.031
arter-0.030
 trigger-0.030
 pawn-0.029
 robbers-0.028
Token broom
Token ID47085
Feature activation-6.21e-02

Pos logit contributions
So+0.026
aw+0.024
 about+0.024
+0.024
 together+0.024
Neg logit contributions
arter-0.029
 robber-0.026
 trigger-0.025
 pawn-0.024
 battlefield-0.023
Token and
Token ID290
Feature activation+8.21e-04

Pos logit contributions
So+0.055
aw+0.051
 about+0.045
+0.044
 together+0.043
Neg logit contributions
arter-0.174
 robber-0.165
 trigger-0.159
 pawn-0.154
 rook-0.151
Token a
Token ID257
Feature activation-2.19e-02

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.002
 pawn+0.002
 battlefield+0.002
Neg logit contributions
So-0.001
aw-0.001
-0.001
 about-0.001
 together-0.001
Token dust
Token ID8977
Feature activation-5.09e-02

Pos logit contributions
So+0.042
aw+0.040
+0.040
 about+0.039
 together+0.039
Neg logit contributions
arter-0.038
 robber-0.033
 trigger-0.032
 pawn-0.030
 battlefield-0.029
Tokenpan
Token ID6839
Feature activation-8.61e-02

Pos logit contributions
So+0.102
aw+0.096
+0.092
 about+0.091
Ab+0.090
Neg logit contributions
arter-0.087
 robber-0.080
 trigger-0.078
 pawn-0.071
 rook-0.068
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
So+0.105
Ab+0.103
+0.097
aw+0.093
Ph+0.091
Neg logit contributions
arter-0.200
 robber-0.182
 trigger-0.181
sing-0.177
 spine-0.171
Token She
Token ID1375
Feature activation-3.68e-03

Pos logit contributions
arter+0.045
 robber+0.042
 trigger+0.040
 pawn+0.039
 rook+0.038
Neg logit contributions
So-0.018
aw-0.018
-0.015
 together-0.015
's-0.015
Token sweeps
Token ID46778
Feature activation-3.01e-02

Pos logit contributions
So+0.005
aw+0.005
 about+0.005
+0.005
 together+0.004
Neg logit contributions
arter-0.008
 robber-0.008
 trigger-0.008
 pawn-0.007
 rook-0.007
Token the
Token ID262
Feature activation+1.41e-02

Pos logit contributions
So+0.024
aw+0.021
 about+0.017
+0.017
Ab+0.017
Neg logit contributions
arter-0.086
 trigger-0.081
 robber-0.081
 pawn-0.077
alks-0.076
Token cereal
Token ID33158
Feature activation-2.18e-02

Pos logit contributions
arter+0.023
 robber+0.021
 trigger+0.020
 pawn+0.019
 battlefield+0.018
Neg logit contributions
So-0.029
aw-0.028
 about-0.026
-0.026
 together-0.026
Token his
Token ID465
Feature activation-2.22e-02

Pos logit contributions
So+0.004
aw+0.004
+0.003
 about+0.003
 together+0.003
Neg logit contributions
arter-0.012
 robber-0.011
 trigger-0.011
 pawn-0.010
 rook-0.010
Token lucky
Token ID9670
Feature activation-1.77e-03

Pos logit contributions
So+0.033
aw+0.030
 about+0.030
+0.030
 together+0.029
Neg logit contributions
arter-0.050
 robber-0.046
 trigger-0.045
 pawn-0.042
 battlefield-0.042
Token stars
Token ID5788
Feature activation-1.29e-02

Pos logit contributions
 about+0.003
aw+0.003
So+0.003
 together+0.003
 by+0.003
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 battlefield-0.003
 pawn-0.003
Token he
Token ID339
Feature activation-2.58e-02

Pos logit contributions
So+0.013
aw+0.012
Ph+0.011
Ab+0.011
It+0.010
Neg logit contributions
arter-0.034
 robber-0.032
 trigger-0.030
 pawn-0.030
 rook-0.030
Token was
Token ID373
Feature activation-2.19e-02

Pos logit contributions
So+0.031
aw+0.029
Ab+0.026
 about+0.026
Ph+0.026
Neg logit contributions
arter-0.062
 robber-0.060
 trigger-0.056
 pawn-0.055
 robbers-0.054
Token able
Token ID1498
Feature activation-8.56e-02

Pos logit contributions
So+0.028
aw+0.025
Ph+0.022
Ab+0.021
Prom+0.020
Neg logit contributions
arter-0.054
 robber-0.049
 battlefield-0.046
 pawn-0.045
 robbers-0.045
Token to
Token ID284
Feature activation-2.37e-03

Pos logit contributions
aw+0.121
So+0.121
Ph+0.104
Alice+0.093
Ab+0.092
Neg logit contributions
arter-0.186
 robbers-0.174
 robber-0.172
 weapon-0.167
alks-0.165
Token observe
Token ID12414
Feature activation-6.70e-03

Pos logit contributions
So+0.004
+0.004
 about+0.004
 such+0.004
aw+0.004
Neg logit contributions
arter-0.005
 robber-0.005
 trigger-0.004
 pawn-0.004
 battlefield-0.004
Token it
Token ID340
Feature activation-2.09e-02

Pos logit contributions
So+0.006
Ph+0.005
aw+0.005
Ab+0.005
+0.005
Neg logit contributions
arter-0.018
 robber-0.017
 pawn-0.016
 trigger-0.016
 battlefield-0.016
Token.
Token ID13
Feature activation-3.85e-02

Pos logit contributions
So+0.018
aw+0.018
Ph+0.015
Ab+0.014
 about+0.013
Neg logit contributions
arter-0.057
 robber-0.053
 trigger-0.052
 pawn-0.051
 battlefield-0.050
Token<|endoftext|>
Token ID50256
Feature activation-1.22e-02

Pos logit contributions
aw+0.034
So+0.030
 about+0.027
Ab+0.026
 such+0.026
Neg logit contributions
arter-0.101
 robber-0.094
 pawn-0.092
alks-0.092
 rook-0.089
Token a
Token ID257
Feature activation-1.40e-02

Pos logit contributions
arter+0.042
 robber+0.040
 trigger+0.039
 pawn+0.037
 battlefield+0.037
Neg logit contributions
So-0.010
aw-0.009
 about-0.008
-0.008
 together-0.007
Token broom
Token ID47085
Feature activation-6.16e-02

Pos logit contributions
So+0.021
+0.020
 together+0.019
 about+0.019
's+0.019
Neg logit contributions
arter-0.032
 robber-0.027
 trigger-0.027
 battlefield-0.026
alks-0.025
Token and
Token ID290
Feature activation-4.09e-03

Pos logit contributions
So+0.050
aw+0.046
 about+0.041
+0.040
 together+0.039
Neg logit contributions
arter-0.178
 robber-0.168
 trigger-0.162
 pawn-0.157
 battlefield-0.154
Token a
Token ID257
Feature activation-2.31e-02

Pos logit contributions
So+0.004
aw+0.004
 about+0.004
Ab+0.003
 such+0.003
Neg logit contributions
arter-0.011
 robber-0.010
 trigger-0.010
 pawn-0.010
 robbers-0.009
Token dust
Token ID8977
Feature activation-4.99e-02

Pos logit contributions
So+0.041
+0.040
 together+0.038
's+0.038
aw+0.038
Neg logit contributions
arter-0.044
 robber-0.037
 trigger-0.036
 battlefield-0.034
 pawn-0.033
Tokenpan
Token ID6839
Feature activation-8.54e-02

Pos logit contributions
So+0.084
aw+0.081
 about+0.076
+0.076
 together+0.075
Neg logit contributions
arter-0.100
 robber-0.092
 trigger-0.087
 pawn-0.084
 rook-0.081
Token.
Token ID13
Feature activation+8.38e-05

Pos logit contributions
Ab+0.094
So+0.093
aw+0.085
+0.085
Ph+0.082
Neg logit contributions
arter-0.201
 robber-0.193
 trigger-0.191
sing-0.181
 pawn-0.179
Token She
Token ID1375
Feature activation-9.67e-03

Pos logit contributions
arter+0.000
 robber+0.000
 trigger+0.000
 pawn+0.000
 battlefield+0.000
Neg logit contributions
So-0.000
aw-0.000
 about-0.000
-0.000
 together-0.000
Token said
Token ID531
Feature activation-1.17e-02

Pos logit contributions
So+0.009
aw+0.009
 such+0.009
Ab+0.009
Ph+0.009
Neg logit contributions
 robber-0.023
arter-0.022
 pawn-0.022
 rook-0.021
 trigger-0.021
Token,
Token ID11
Feature activation-1.12e-02

Pos logit contributions
So+0.016
aw+0.014
Ab+0.013
+0.013
 such+0.013
Neg logit contributions
arter-0.027
 robber-0.026
 pawn-0.025
 trigger-0.024
 rook-0.024
Token "
Token ID366
Feature activation-1.60e-02

Pos logit contributions
So+0.013
aw+0.012
 such+0.010
+0.010
Ab+0.010
Neg logit contributions
arter-0.028
 robber-0.027
 trigger-0.026
 pawn-0.025
 rook-0.025
Tokenpron
Token ID31186
Feature activation-2.77e-02

Pos logit contributions
arter+0.012
 robber+0.010
 trigger+0.010
 pawn+0.010
 battlefield+0.009
Neg logit contributions
So-0.009
aw-0.009
 about-0.009
-0.009
 together-0.009
Token and
Token ID290
Feature activation+4.42e-03

Pos logit contributions
So+0.023
aw+0.021
+0.019
 about+0.018
 together+0.018
Neg logit contributions
arter-0.079
 robber-0.075
 trigger-0.072
 pawn-0.070
 rook-0.069
Token climbed
Token ID19952
Feature activation-2.20e-02

Pos logit contributions
arter+0.010
 robber+0.010
 trigger+0.009
 pawn+0.009
 rook+0.009
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
 such-0.005
Ph-0.005
Token on
Token ID319
Feature activation-4.08e-03

Pos logit contributions
So+0.030
aw+0.025
Ph+0.023
+0.022
 about+0.021
Neg logit contributions
arter-0.050
 robber-0.049
 trigger-0.048
alks-0.047
 pawn-0.047
Token a
Token ID257
Feature activation+5.07e-03

Pos logit contributions
So+0.004
aw+0.004
 about+0.003
+0.003
Ph+0.003
Neg logit contributions
arter-0.011
 robber-0.011
 trigger-0.010
 pawn-0.010
 rook-0.010
Token stool
Token ID38753
Feature activation-8.51e-02

Pos logit contributions
arter+0.009
 robber+0.008
 trigger+0.008
 pawn+0.007
 rook+0.007
Neg logit contributions
So-0.010
aw-0.009
 about-0.009
 such-0.009
 together-0.009
Token.
Token ID13
Feature activation+6.60e-04

Pos logit contributions
So+0.083
aw+0.073
Ab+0.072
Ph+0.068
 such+0.063
Neg logit contributions
arter-0.219
 robber-0.214
 trigger-0.208
 pawn-0.201
 battlefield-0.200
Token She
Token ID1375
Feature activation-7.62e-03

Pos logit contributions
arter+0.002
 robber+0.001
 trigger+0.001
 pawn+0.001
 battlefield+0.001
Neg logit contributions
So-0.001
aw-0.001
 such-0.001
Ab-0.001
 together-0.001
Token saw
Token ID2497
Feature activation+1.16e-02

Pos logit contributions
So+0.011
aw+0.010
 such+0.010
Ph+0.010
Ab+0.010
Neg logit contributions
 robber-0.015
arter-0.015
 pawn-0.015
 rook-0.014
 trigger-0.013
Token mom
Token ID1995
Feature activation-5.41e-03

Pos logit contributions
arter+0.033
 robber+0.031
 trigger+0.030
 pawn+0.030
 rook+0.029
Neg logit contributions
So-0.009
aw-0.008
-0.008
Ph-0.007
 about-0.007
Token take
Token ID1011
Feature activation+5.69e-03

Pos logit contributions
So+0.006
aw+0.006
Ph+0.006
Ab+0.006
Prom+0.005
Neg logit contributions
arter-0.012
 robber-0.011
 pawn-0.011
 trigger-0.011
 robbers-0.011
Token put
Token ID1234
Feature activation-3.41e-02

Pos logit contributions
arter+0.043
 trigger+0.039
 robber+0.039
 pawn+0.037
 battlefield+0.036
Neg logit contributions
So-0.033
 about-0.032
aw-0.032
-0.031
 together-0.030
Token flour
Token ID10601
Feature activation-7.48e-02

Pos logit contributions
So+0.035
aw+0.028
 about+0.026
+0.026
Ab+0.026
Neg logit contributions
arter-0.090
 robber-0.086
 trigger-0.085
 pawn-0.082
 rook-0.079
Token,
Token ID11
Feature activation+1.37e-02

Pos logit contributions
So+0.082
aw+0.071
Ab+0.067
Ph+0.064
 about+0.063
Neg logit contributions
arter-0.188
 robber-0.179
 trigger-0.178
 pawn-0.168
 rook-0.164
Token water
Token ID1660
Feature activation-3.92e-02

Pos logit contributions
arter+0.030
 robber+0.029
 trigger+0.028
 pawn+0.027
 robbers+0.026
Neg logit contributions
So-0.019
aw-0.017
 about-0.016
-0.015
Ph-0.015
Token,
Token ID11
Feature activation+9.15e-03

Pos logit contributions
So+0.036
aw+0.033
 about+0.029
+0.029
 such+0.028
Neg logit contributions
arter-0.108
 robber-0.102
 trigger-0.098
 pawn-0.095
 rook-0.093
Token yeast
Token ID20146
Feature activation-8.47e-02

Pos logit contributions
arter+0.022
 robber+0.021
 trigger+0.020
 pawn+0.020
 rook+0.019
Neg logit contributions
So-0.011
aw-0.010
 about-0.009
-0.009
 such-0.009
Token and
Token ID290
Feature activation+1.68e-02

Pos logit contributions
So+0.075
aw+0.068
 about+0.060
+0.059
 such+0.056
Neg logit contributions
arter-0.236
 robber-0.222
 trigger-0.215
 pawn-0.209
 rook-0.205
Token salt
Token ID8268
Feature activation-5.91e-02

Pos logit contributions
arter+0.036
 robber+0.034
 trigger+0.032
 pawn+0.031
 rook+0.031
Neg logit contributions
So-0.025
aw-0.024
 about-0.023
Ph-0.022
 such-0.021
Token in
Token ID287
Feature activation+1.33e-02

Pos logit contributions
So+0.055
aw+0.048
+0.042
Ab+0.042
 about+0.041
Neg logit contributions
arter-0.162
 robber-0.153
 trigger-0.149
 pawn-0.144
 rook-0.141
Token a
Token ID257
Feature activation-1.04e-02

Pos logit contributions
arter+0.038
 robber+0.036
 trigger+0.035
 pawn+0.034
 rook+0.033
Neg logit contributions
So-0.011
aw-0.010
 about-0.009
-0.008
Ph-0.008
Token big
Token ID1263
Feature activation-5.41e-03

Pos logit contributions
So+0.019
aw+0.018
 about+0.018
 such+0.017
Ph+0.017
Neg logit contributions
arter-0.019
 robber-0.018
 trigger-0.017
 pawn-0.016
 rook-0.016
Token.
Token ID13
Feature activation+1.76e-02

Pos logit contributions
arter+0.021
 robber+0.020
 trigger+0.019
 pawn+0.018
 rook+0.018
Neg logit contributions
So-0.007
aw-0.006
-0.005
 about-0.005
 such-0.005
Token He
Token ID679
Feature activation+2.17e-02

Pos logit contributions
arter+0.038
 robber+0.036
 pawn+0.034
 trigger+0.033
 rook+0.033
Neg logit contributions
aw-0.025
So-0.025
 such-0.023
 about-0.022
 together-0.022
Token stepped
Token ID10764
Feature activation-5.58e-03

Pos logit contributions
arter+0.049
 robber+0.048
 pawn+0.046
 trigger+0.044
 rook+0.044
Neg logit contributions
aw-0.025
 such-0.025
So-0.024
Ph-0.023
 about-0.022
Token onto
Token ID4291
Feature activation-2.91e-03

Pos logit contributions
So+0.007
aw+0.007
 about+0.006
 such+0.006
Ph+0.006
Neg logit contributions
arter-0.013
 robber-0.013
 trigger-0.012
 pawn-0.012
 rook-0.012
Token a
Token ID257
Feature activation+1.74e-03

Pos logit contributions
So+0.001
 such+0.001
aw+0.001
+0.001
 about+0.001
Neg logit contributions
arter-0.010
 robber-0.009
 trigger-0.009
 pawn-0.009
 battlefield-0.009
Token stool
Token ID38753
Feature activation-8.47e-02

Pos logit contributions
arter+0.003
 robber+0.003
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.003
aw-0.003
-0.003
 about-0.003
 together-0.003
Token and
Token ID290
Feature activation+4.30e-03

Pos logit contributions
So+0.089
aw+0.086
Ab+0.081
Ph+0.079
 such+0.074
Neg logit contributions
arter-0.210
 robber-0.203
 trigger-0.195
 pawn-0.190
 battlefield-0.188
Token held
Token ID2714
Feature activation-1.11e-03

Pos logit contributions
arter+0.008
 robber+0.008
 pawn+0.008
 trigger+0.008
 rook+0.008
Neg logit contributions
So-0.006
aw-0.006
Ph-0.006
 about-0.006
 such-0.006
Token the
Token ID262
Feature activation+1.52e-02

Pos logit contributions
So+0.001
aw+0.001
 about+0.001
+0.001
 such+0.001
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 pawn-0.003
 rook-0.003
Token spoon
Token ID24556
Feature activation-1.52e-02

Pos logit contributions
arter+0.028
 robber+0.026
 trigger+0.023
 pawn+0.023
 battlefield+0.022
Neg logit contributions
So-0.028
aw-0.027
-0.026
's-0.026
 about-0.026
Token while
Token ID981
Feature activation-1.00e-02

Pos logit contributions
aw+0.015
So+0.014
Ph+0.012
 such+0.012
Ab+0.012
Neg logit contributions
arter-0.040
 trigger-0.037
 robber-0.036
 pawn-0.036
 rook-0.035
Tokenice
Token ID501
Feature activation-1.71e-02

Pos logit contributions
So+0.015
aw+0.014
 about+0.014
 such+0.014
+0.014
Neg logit contributions
arter-0.017
 robber-0.016
 trigger-0.015
 pawn-0.014
alks-0.014
Token and
Token ID290
Feature activation-8.84e-05

Pos logit contributions
So+0.018
aw+0.016
 about+0.015
+0.014
 such+0.014
Neg logit contributions
arter-0.044
 robber-0.042
 trigger-0.040
 pawn-0.039
 rook-0.038
Token cl
Token ID537
Feature activation-1.75e-02

Pos logit contributions
So+0.000
aw+0.000
+0.000
 about+0.000
 together+0.000
Neg logit contributions
arter-0.000
 robber-0.000
 trigger-0.000
 pawn-0.000
 battlefield-0.000
Tokenove
Token ID659
Feature activation-1.56e-02

Pos logit contributions
So+0.025
aw+0.024
 about+0.022
+0.022
 together+0.022
Neg logit contributions
arter-0.040
 robber-0.037
 trigger-0.035
 pawn-0.034
 rook-0.033
Token and
Token ID290
Feature activation-1.85e-02

Pos logit contributions
So+0.018
aw+0.016
 about+0.015
+0.014
Ph+0.014
Neg logit contributions
arter-0.039
 robber-0.037
 trigger-0.036
 pawn-0.035
 rook-0.033
Token cinnamon
Token ID29181
Feature activation-8.43e-02

Pos logit contributions
So+0.028
aw+0.027
 about+0.025
+0.024
 such+0.024
Neg logit contributions
arter-0.040
 robber-0.037
 trigger-0.035
 pawn-0.034
 rook-0.033
Token and
Token ID290
Feature activation-1.96e-04

Pos logit contributions
So+0.080
aw+0.070
Ab+0.062
Ph+0.062
+0.061
Neg logit contributions
arter-0.224
 robber-0.214
 trigger-0.208
 pawn-0.203
 rook-0.198
Token cass
Token ID30606
Feature activation+3.64e-03

Pos logit contributions
So+0.000
aw+0.000
 about+0.000
+0.000
 together+0.000
Neg logit contributions
arter-0.000
 robber-0.000
 trigger-0.000
 pawn-0.000
 rook-0.000
Tokenia
Token ID544
Feature activation-5.60e-02

Pos logit contributions
arter+0.008
 robber+0.007
 trigger+0.007
 pawn+0.007
 battlefield+0.006
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
-0.005
 together-0.005
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
So+0.055
aw+0.051
Ab+0.045
Ph+0.045
 such+0.043
Neg logit contributions
arter-0.146
 robber-0.140
 trigger-0.132
 pawn-0.129
 rook-0.126
Token sa
Token ID473
Feature activation-3.10e-02

Pos logit contributions
So+0.013
aw+0.012
+0.012
 about+0.012
 together+0.012
Neg logit contributions
arter-0.027
 robber-0.025
 trigger-0.025
 pawn-0.023
 battlefield-0.023
Token small
Token ID1402
Feature activation+1.60e-02

Pos logit contributions
So+0.005
+0.005
 together+0.005
aw+0.004
 about+0.004
Neg logit contributions
arter-0.009
 trigger-0.008
 robber-0.008
 battlefield-0.007
alks-0.007
Token broom
Token ID47085
Feature activation-5.51e-02

Pos logit contributions
arter+0.034
 robber+0.030
 trigger+0.030
 battlefield+0.028
 pawn+0.027
Neg logit contributions
So-0.024
-0.024
 together-0.023
aw-0.023
 about-0.023
Token and
Token ID290
Feature activation-8.73e-04

Pos logit contributions
So+0.053
aw+0.050
 about+0.046
+0.045
 together+0.044
Neg logit contributions
arter-0.150
 robber-0.141
 trigger-0.136
 pawn-0.132
 rook-0.129
Token a
Token ID257
Feature activation-1.97e-02

Pos logit contributions
So+0.001
aw+0.001
 about+0.000
+0.000
 together+0.000
Neg logit contributions
arter-0.003
 robber-0.002
 trigger-0.002
 pawn-0.002
 battlefield-0.002
Token dust
Token ID8977
Feature activation-4.86e-02

Pos logit contributions
So+0.034
+0.032
aw+0.032
 together+0.031
 about+0.031
Neg logit contributions
arter-0.039
 robber-0.034
 trigger-0.033
 pawn-0.031
 battlefield-0.031
Tokenpan
Token ID6839
Feature activation-8.37e-02

Pos logit contributions
So+0.088
aw+0.085
+0.080
 about+0.080
 together+0.079
Neg logit contributions
arter-0.091
 robber-0.084
 trigger-0.080
 pawn-0.075
 rook-0.073
Token.
Token ID13
Feature activation+2.79e-03

Pos logit contributions
So+0.092
Ab+0.083
+0.081
aw+0.079
Ph+0.079
Neg logit contributions
arter-0.206
 robber-0.195
 trigger-0.183
sing-0.179
 tablet-0.179
Token She
Token ID1375
Feature activation-7.33e-03

Pos logit contributions
arter+0.006
 robber+0.005
 pawn+0.005
 tablet+0.005
 battlefield+0.005
Neg logit contributions
aw-0.004
So-0.004
Ph-0.004
Ab-0.004
 such-0.003
Token sweeps
Token ID46778
Feature activation-2.59e-02

Pos logit contributions
So+0.010
aw+0.010
 about+0.009
 such+0.009
 together+0.009
Neg logit contributions
arter-0.016
 robber-0.015
 trigger-0.014
 pawn-0.014
 rook-0.014
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
So+0.020
aw+0.018
+0.014
 about+0.014
Ab+0.014
Neg logit contributions
arter-0.074
 robber-0.071
 trigger-0.070
 pawn-0.067
alks-0.065
Token floor
Token ID4314
Feature activation-8.26e-03

Pos logit contributions
arter+0.022
 robber+0.020
 trigger+0.020
 pawn+0.018
 battlefield+0.017
Neg logit contributions
So-0.026
aw-0.026
 about-0.024
 such-0.024
-0.024
Token -
Token ID532
Feature activation+1.70e-02

Pos logit contributions
So+0.016
aw+0.015
 about+0.014
 together+0.013
's+0.013
Neg logit contributions
arter-0.061
 robber-0.058
 trigger-0.055
 pawn-0.054
 battlefield-0.053
Token it
Token ID340
Feature activation-8.38e-03

Pos logit contributions
arter+0.044
 robber+0.043
 trigger+0.041
 pawn+0.041
 rook+0.040
Neg logit contributions
So-0.017
aw-0.016
Ph-0.015
Ab-0.013
 together-0.013
Token was
Token ID373
Feature activation-3.05e-03

Pos logit contributions
So+0.004
aw+0.004
 about+0.003
 together+0.003
 such+0.003
Neg logit contributions
arter-0.026
 robber-0.025
 trigger-0.024
 pawn-0.024
 rook-0.023
Token bigger
Token ID5749
Feature activation-6.28e-02

Pos logit contributions
So+0.004
aw+0.003
+0.003
Ph+0.003
 together+0.003
Neg logit contributions
arter-0.008
 robber-0.007
 trigger-0.007
 pawn-0.007
 rook-0.007
Token and
Token ID290
Feature activation-1.23e-03

Pos logit contributions
So+0.088
aw+0.080
+0.076
Ph+0.075
Ab+0.075
Neg logit contributions
arter-0.144
 robber-0.135
 trigger-0.127
 pawn-0.125
 rook-0.122
Token ju
Token ID7544
Feature activation-8.35e-02

Pos logit contributions
So+0.002
aw+0.002
 about+0.002
Ph+0.002
Ab+0.002
Neg logit contributions
arter-0.002
 robber-0.002
 trigger-0.002
 pawn-0.002
 robbers-0.002
Tokenic
Token ID291
Feature activation+1.64e-03

Pos logit contributions
 about+0.130
+0.125
So+0.124
 together+0.119
 such+0.117
Neg logit contributions
arter-0.171
 trigger-0.149
 robber-0.148
 pawn-0.137
 rook-0.134
Tokenier
Token ID959
Feature activation-2.99e-02

Pos logit contributions
arter+0.004
 robber+0.004
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.002
aw-0.002
 about-0.002
-0.002
 together-0.002
Token than
Token ID621
Feature activation+1.27e-03

Pos logit contributions
So+0.035
aw+0.033
+0.030
 about+0.029
 together+0.029
Neg logit contributions
arter-0.076
 robber-0.071
 trigger-0.068
 pawn-0.066
 rook-0.064
Token any
Token ID597
Feature activation-2.18e-02

Pos logit contributions
arter+0.003
 robber+0.003
 trigger+0.003
 pawn+0.003
 battlefield+0.003
Neg logit contributions
aw-0.001
So-0.001
 about-0.001
 such-0.001
 together-0.001
Token he
Token ID339
Feature activation+7.57e-04

Pos logit contributions
So+0.031
aw+0.029
 about+0.027
+0.027
 together+0.027
Neg logit contributions
arter-0.050
 robber-0.046
 trigger-0.045
 pawn-0.043
 rook-0.041
Token a
Token ID257
Feature activation-8.29e-03

Pos logit contributions
So+0.017
aw+0.016
Ab+0.013
 about+0.012
Ph+0.012
Neg logit contributions
arter-0.032
 robber-0.031
 trigger-0.030
 pawn-0.029
 robbers-0.029
Token broom
Token ID47085
Feature activation-5.26e-02

Pos logit contributions
So+0.011
aw+0.011
+0.010
 about+0.010
 such+0.010
Neg logit contributions
arter-0.019
 robber-0.018
 trigger-0.017
 pawn-0.017
 rook-0.016
Token and
Token ID290
Feature activation-4.59e-03

Pos logit contributions
So+0.046
aw+0.043
 about+0.038
+0.038
 together+0.037
Neg logit contributions
arter-0.147
 robber-0.139
 trigger-0.134
 pawn-0.130
 rook-0.127
Token a
Token ID257
Feature activation-2.19e-02

Pos logit contributions
So+0.004
aw+0.004
+0.003
 about+0.003
 together+0.003
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.012
 pawn-0.011
 rook-0.011
Token dust
Token ID8977
Feature activation-4.54e-02

Pos logit contributions
So+0.041
aw+0.040
 about+0.037
+0.037
 such+0.037
Neg logit contributions
arter-0.040
 robber-0.037
 trigger-0.035
 pawn-0.033
 rook-0.032
Tokenpan
Token ID6839
Feature activation-8.34e-02

Pos logit contributions
So+0.090
aw+0.086
+0.083
 about+0.081
Ab+0.081
Neg logit contributions
arter-0.078
 robber-0.072
 trigger-0.069
 pawn-0.063
 rook-0.061
Token to
Token ID284
Feature activation-2.72e-03

Pos logit contributions
Ab+0.099
So+0.096
+0.092
aw+0.090
Ph+0.085
Neg logit contributions
arter-0.193
 robber-0.180
 trigger-0.178
sing-0.171
 spine-0.168
Token clean
Token ID3424
Feature activation-2.73e-02

Pos logit contributions
So+0.004
aw+0.004
 about+0.004
+0.004
 together+0.004
Neg logit contributions
arter-0.006
 robber-0.005
 trigger-0.005
 pawn-0.005
 rook-0.005
Token up
Token ID510
Feature activation-1.96e-02

Pos logit contributions
So+0.032
aw+0.027
Ab+0.026
Ph+0.024
+0.022
Neg logit contributions
arter-0.070
 trigger-0.067
 robber-0.064
 tablet-0.062
 battlefield-0.060
Token the
Token ID262
Feature activation+2.91e-04

Pos logit contributions
So+0.016
aw+0.015
Ab+0.012
+0.012
Ph+0.011
Neg logit contributions
arter-0.056
 robber-0.053
 trigger-0.051
 pawn-0.050
 battlefield-0.049
Token mess
Token ID2085
Feature activation+1.49e-02

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.000
 pawn+0.000
 battlefield+0.000
Neg logit contributions
So-0.001
aw-0.001
 about-0.000
-0.000
 together-0.000
Token you
Token ID345
Feature activation-1.06e-02

Pos logit contributions
So+0.004
aw+0.004
 together+0.004
 such+0.004
 about+0.004
Neg logit contributions
arter-0.016
 robber-0.015
 trigger-0.015
 pawn-0.014
 battlefield-0.014
Token."
Token ID526
Feature activation-1.78e-02

Pos logit contributions
So+0.009
aw+0.009
Ab+0.008
Ph+0.008
 such+0.007
Neg logit contributions
arter-0.029
 robber-0.027
 trigger-0.026
 pawn-0.026
 robbers-0.025
Token She
Token ID1375
Feature activation-6.68e-03

Pos logit contributions
aw+0.015
So+0.014
 such+0.013
 about+0.012
 enough+0.012
Neg logit contributions
arter-0.047
 robber-0.045
 pawn-0.042
 trigger-0.042
 robbers-0.042
Token got
Token ID1392
Feature activation-3.58e-03

Pos logit contributions
aw+0.008
 such+0.008
So+0.008
Ph+0.007
Ab+0.007
Neg logit contributions
 robber-0.015
 pawn-0.014
arter-0.014
 rook-0.013
 robbers-0.013
Token a
Token ID257
Feature activation-8.95e-03

Pos logit contributions
So+0.005
aw+0.004
Ph+0.004
Ab+0.003
Alice+0.003
Neg logit contributions
 robber-0.008
 trigger-0.008
 pawn-0.008
arter-0.008
 robbers-0.007
Token stool
Token ID38753
Feature activation-8.30e-02

Pos logit contributions
So+0.015
aw+0.014
 about+0.013
+0.013
 together+0.013
Neg logit contributions
arter-0.019
 robber-0.017
 trigger-0.016
 pawn-0.015
 battlefield-0.015
Token and
Token ID290
Feature activation+1.54e-03

Pos logit contributions
So+0.089
aw+0.086
Ab+0.079
Ph+0.074
 such+0.071
Neg logit contributions
arter-0.204
 robber-0.200
 trigger-0.192
 pawn-0.187
 rook-0.183
Token fixed
Token ID5969
Feature activation-2.38e-03

Pos logit contributions
 robber+0.003
arter+0.003
 pawn+0.003
 robbers+0.003
 trigger+0.003
Neg logit contributions
So-0.002
aw-0.002
Ph-0.002
 about-0.002
Ab-0.002
Token the
Token ID262
Feature activation+8.73e-03

Pos logit contributions
So+0.002
aw+0.002
 about+0.001
+0.001
Ph+0.001
Neg logit contributions
arter-0.007
 robber-0.007
 trigger-0.006
 pawn-0.006
 rook-0.006
Token cabinet
Token ID13447
Feature activation-6.24e-03

Pos logit contributions
arter+0.016
 robber+0.013
 trigger+0.012
 battlefield+0.012
 pawn+0.012
Neg logit contributions
So-0.016
-0.016
's-0.016
 by-0.016
 about-0.016
Token so
Token ID523
Feature activation+3.81e-03

Pos logit contributions
So+0.006
aw+0.006
Ph+0.005
Ab+0.005
 such+0.005
Neg logit contributions
arter-0.016
 robber-0.015
 pawn-0.015
 trigger-0.015
 rook-0.014
Token back
Token ID736
Feature activation-3.86e-02

Pos logit contributions
So+0.032
aw+0.030
 So+0.025
Prom+0.024
+0.023
Neg logit contributions
arter-0.052
 robber-0.048
 knight-0.042
 trigger-0.041
 robbers-0.041
Token and
Token ID290
Feature activation-1.57e-02

Pos logit contributions
So+0.040
aw+0.036
Ab+0.031
Ph+0.030
+0.028
Neg logit contributions
arter-0.103
 robber-0.095
 robbers-0.088
 pawn-0.088
 trigger-0.087
Token her
Token ID607
Feature activation-3.70e-02

Pos logit contributions
So+0.021
aw+0.020
Ab+0.017
Ph+0.016
Lu+0.015
Neg logit contributions
arter-0.036
 robber-0.032
 robbers-0.030
 pawn-0.030
 battlefield-0.030
Token family
Token ID1641
Feature activation+3.44e-04

Pos logit contributions
 about+0.045
 was+0.042
's+0.042
 together+0.041
 by+0.041
Neg logit contributions
arter-0.087
 trigger-0.086
 robber-0.084
 pawn-0.077
 battlefield-0.076
Token was
Token ID373
Feature activation-2.90e-02

Pos logit contributions
arter+0.001
 robber+0.001
 pawn+0.001
 soldier+0.001
 knight+0.001
Neg logit contributions
So-0.000
aw-0.000
Ab-0.000
Ph-0.000
Alice-0.000
Token able
Token ID1498
Feature activation-8.25e-02

Pos logit contributions
So+0.046
aw+0.044
 So+0.041
Prom+0.037
eat+0.035
Neg logit contributions
arter-0.054
 robber-0.047
sing-0.043
 knight-0.042
 alien-0.041
Token to
Token ID284
Feature activation-3.20e-03

Pos logit contributions
aw+0.130
So+0.128
Ph+0.101
 So+0.096
Ab+0.094
Neg logit contributions
arter-0.168
 robbers-0.156
 robber-0.154
 weapon-0.142
alks-0.142
Token enjoy
Token ID2883
Feature activation-1.97e-02

Pos logit contributions
So+0.005
+0.005
aw+0.005
 about+0.005
 such+0.005
Neg logit contributions
arter-0.007
 robber-0.006
 trigger-0.006
 pawn-0.006
 rook-0.005
Token it
Token ID340
Feature activation-6.62e-03

Pos logit contributions
So+0.018
aw+0.015
+0.013
Ph+0.013
Ab+0.012
Neg logit contributions
arter-0.056
 robber-0.053
 pawn-0.049
 trigger-0.049
 battlefield-0.049
Token.
Token ID13
Feature activation-3.72e-02

Pos logit contributions
aw+0.007
So+0.006
Ab+0.006
Ph+0.005
It+0.005
Neg logit contributions
arter-0.017
 robber-0.016
 pawn-0.015
 rook-0.015
 battlefield-0.015
Token The
Token ID383
Feature activation-1.66e-02

Pos logit contributions
aw+0.047
So+0.045
 enough+0.039
Ab+0.038
a+0.038
Neg logit contributions
arter-0.083
alks-0.073
 robber-0.072
 pawn-0.071
igsaw-0.070
Token self
Token ID2116
Feature activation-7.77e-03

Pos logit contributions
So+0.001
aw+0.001
+0.001
 about+0.001
 together+0.001
Neg logit contributions
arter-0.001
 robber-0.001
 trigger-0.001
 pawn-0.001
 battlefield-0.001
Token,
Token ID11
Feature activation-1.28e-02

Pos logit contributions
So+0.008
aw+0.007
Ab+0.007
Ph+0.006
 about+0.006
Neg logit contributions
arter-0.020
 robber-0.019
 trigger-0.018
 pawn-0.018
 rook-0.018
Token will
Token ID481
Feature activation-4.03e-02

Pos logit contributions
So+0.014
aw+0.014
Ph+0.011
Ab+0.011
 together+0.010
Neg logit contributions
arter-0.032
 robber-0.030
 pawn-0.028
 trigger-0.028
 robbers-0.027
Token she
Token ID673
Feature activation-3.79e-02

Pos logit contributions
So+0.052
aw+0.052
 about+0.045
 together+0.045
+0.044
Neg logit contributions
arter-0.095
 robber-0.089
 trigger-0.084
 pawn-0.081
 rook-0.079
Token be
Token ID307
Feature activation-3.51e-03

Pos logit contributions
So+0.056
aw+0.054
 about+0.049
 together+0.049
+0.049
Neg logit contributions
arter-0.083
 robber-0.077
 trigger-0.073
 pawn-0.070
 rook-0.068
Token able
Token ID1498
Feature activation-8.25e-02

Pos logit contributions
So+0.005
aw+0.004
Prom+0.004
 So+0.004
Ab+0.004
Neg logit contributions
arter-0.007
 robber-0.007
 knight-0.006
 alien-0.006
 robbers-0.006
Token to
Token ID284
Feature activation+1.74e-03

Pos logit contributions
aw+0.122
So+0.115
Ph+0.094
Ab+0.086
uct+0.084
Neg logit contributions
arter-0.177
 robber-0.168
 robbers-0.163
 weapon-0.151
 pawn-0.148
Token fly
Token ID6129
Feature activation-2.63e-02

Pos logit contributions
arter+0.004
 robber+0.003
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.003
aw-0.003
-0.003
 about-0.003
 together-0.003
Token as
Token ID355
Feature activation-2.03e-02

Pos logit contributions
So+0.025
aw+0.023
 about+0.020
+0.020
Ab+0.019
Neg logit contributions
arter-0.071
 robber-0.067
 trigger-0.064
 pawn-0.063
 battlefield-0.061
Token high
Token ID1029
Feature activation-1.09e-03

Pos logit contributions
So+0.020
aw+0.018
+0.015
's+0.015
Ph+0.014
Neg logit contributions
arter-0.055
 robber-0.052
 trigger-0.049
 pawn-0.049
 rook-0.048
Token as
Token ID355
Feature activation-9.50e-03

Pos logit contributions
So+0.001
aw+0.001
+0.001
 about+0.001
 together+0.001
Neg logit contributions
arter-0.003
 robber-0.002
 trigger-0.002
 pawn-0.002
 battlefield-0.002
Token a
Token ID257
Feature activation-1.12e-02

Pos logit contributions
arter+0.019
 robber+0.019
 pawn+0.018
 trigger+0.018
 robbers+0.017
Neg logit contributions
So-0.007
aw-0.006
Ph-0.006
 about-0.006
-0.006
Token broom
Token ID47085
Feature activation-5.73e-02

Pos logit contributions
So+0.019
aw+0.017
+0.017
 about+0.017
 together+0.017
Neg logit contributions
arter-0.023
 robber-0.020
 trigger-0.020
 battlefield-0.019
 pawn-0.018
Token and
Token ID290
Feature activation+2.85e-03

Pos logit contributions
So+0.049
aw+0.045
Ab+0.039
+0.038
 such+0.037
Neg logit contributions
arter-0.160
 robber-0.154
 trigger-0.150
 pawn-0.144
 rook-0.141
Token a
Token ID257
Feature activation-2.27e-02

Pos logit contributions
arter+0.008
 robber+0.008
 trigger+0.008
 pawn+0.007
 rook+0.007
Neg logit contributions
So-0.002
aw-0.002
 about-0.002
-0.002
 together-0.002
Token dust
Token ID8977
Feature activation-4.64e-02

Pos logit contributions
So+0.045
aw+0.043
+0.041
 about+0.041
 together+0.041
Neg logit contributions
arter-0.039
 robber-0.035
 trigger-0.033
 pawn-0.031
 battlefield-0.030
Tokenpan
Token ID6839
Feature activation-8.24e-02

Pos logit contributions
So+0.083
aw+0.077
+0.074
Ab+0.073
 about+0.072
Neg logit contributions
arter-0.089
 robber-0.083
 trigger-0.081
 pawn-0.075
 rook-0.073
Token.
Token ID13
Feature activation+2.63e-02

Pos logit contributions
So+0.096
Ab+0.094
+0.088
Ph+0.085
aw+0.085
Neg logit contributions
arter-0.195
 trigger-0.180
 robber-0.179
sing-0.172
 pawn-0.169
Token They
Token ID1119
Feature activation+1.28e-02

Pos logit contributions
arter+0.048
 robber+0.045
 trigger+0.041
 pawn+0.041
 rook+0.040
Neg logit contributions
So-0.048
aw-0.046
Ab-0.043
-0.043
 together-0.043
Token help
Token ID1037
Feature activation-5.34e-03

Pos logit contributions
arter+0.027
 robber+0.024
 trigger+0.023
 pawn+0.022
 battlefield+0.022
Neg logit contributions
So-0.021
-0.020
aw-0.019
 together-0.019
 about-0.019
Token him
Token ID683
Feature activation+1.12e-02

Pos logit contributions
So+0.005
aw+0.005
+0.005
 about+0.004
Ph+0.004
Neg logit contributions
arter-0.014
 robber-0.013
 trigger-0.013
 pawn-0.013
 robbers-0.012
Token sweep
Token ID16085
Feature activation-2.44e-02

Pos logit contributions
arter+0.024
 robber+0.022
 trigger+0.021
 pawn+0.021
 rook+0.020
Neg logit contributions
So-0.017
aw-0.017
 about-0.015
-0.015
 such-0.015
Token a
Token ID257
Feature activation-5.61e-03

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 pawn+0.001
 rook+0.001
Neg logit contributions
So-0.000
aw-0.000
 about-0.000
Ab-0.000
-0.000
Token broom
Token ID47085
Feature activation-4.90e-02

Pos logit contributions
So+0.010
aw+0.010
+0.010
 together+0.010
 about+0.009
Neg logit contributions
arter-0.010
 robber-0.009
 trigger-0.009
 pawn-0.008
 battlefield-0.008
Token and
Token ID290
Feature activation-1.12e-02

Pos logit contributions
So+0.038
aw+0.035
 about+0.031
+0.031
 together+0.030
Neg logit contributions
arter-0.143
 robber-0.134
 trigger-0.130
 pawn-0.127
 rook-0.124
Token a
Token ID257
Feature activation-2.17e-02

Pos logit contributions
So+0.013
aw+0.012
+0.012
 about+0.011
 together+0.011
Neg logit contributions
arter-0.028
 robber-0.026
 trigger-0.025
 pawn-0.024
 battlefield-0.024
Token dust
Token ID8977
Feature activation-4.64e-02

Pos logit contributions
So+0.039
+0.037
aw+0.037
 together+0.036
 about+0.036
Neg logit contributions
arter-0.040
 robber-0.036
 trigger-0.034
 pawn-0.032
 battlefield-0.032
Tokenpan
Token ID6839
Feature activation-8.22e-02

Pos logit contributions
So+0.076
aw+0.074
 about+0.070
+0.070
 together+0.069
Neg logit contributions
arter-0.094
 robber-0.086
 trigger-0.082
 pawn-0.079
 rook-0.076
Token from
Token ID422
Feature activation-1.67e-02

Pos logit contributions
So+0.081
aw+0.075
Ab+0.073
+0.066
Ph+0.066
Neg logit contributions
arter-0.214
 robber-0.202
 trigger-0.195
 pawn-0.184
 battlefield-0.182
Token the
Token ID262
Feature activation-2.38e-02

Pos logit contributions
So+0.007
 together+0.007
aw+0.007
 such+0.007
 about+0.006
Neg logit contributions
arter-0.053
 robber-0.051
 trigger-0.050
 pawn-0.048
 rook-0.047
Token closet
Token ID21615
Feature activation-2.36e-02

Pos logit contributions
So+0.044
aw+0.042
+0.041
 about+0.040
's+0.040
Neg logit contributions
arter-0.044
 robber-0.039
 trigger-0.037
 pawn-0.035
 battlefield-0.034
Token."
Token ID526
Feature activation-2.26e-02

Pos logit contributions
So+0.021
aw+0.019
Ab+0.017
+0.017
Ph+0.016
Neg logit contributions
arter-0.065
 robber-0.062
 trigger-0.060
 pawn-0.057
 battlefield-0.057
Token
Token ID198
Feature activation-7.76e-03

Pos logit contributions
aw+0.024
 such+0.023
uct+0.020
 about+0.020
 enough+0.020
Neg logit contributions
arter-0.049
 robber-0.047
alks-0.046
 pawn-0.045
 robbers-0.044
Token gave
Token ID2921
Feature activation-7.87e-03

Pos logit contributions
So+0.002
aw+0.002
 about+0.001
 such+0.001
Ab+0.001
Neg logit contributions
arter-0.004
 robber-0.004
 trigger-0.003
 pawn-0.003
 rook-0.003
Token the
Token ID262
Feature activation+2.18e-02

Pos logit contributions
So+0.006
aw+0.006
+0.005
 about+0.005
Ab+0.005
Neg logit contributions
arter-0.022
 robber-0.021
 trigger-0.021
 pawn-0.020
 rook-0.020
Token money
Token ID1637
Feature activation+1.03e-02

Pos logit contributions
arter+0.045
 robber+0.043
 trigger+0.040
 pawn+0.039
 rook+0.038
Neg logit contributions
So-0.035
aw-0.034
-0.032
 together-0.032
 about-0.031
Token to
Token ID284
Feature activation+1.10e-03

Pos logit contributions
arter+0.027
 robber+0.027
 trigger+0.026
 pawn+0.026
 rook+0.025
Neg logit contributions
So-0.009
aw-0.008
Ab-0.007
Ph-0.007
 about-0.006
Token the
Token ID262
Feature activation+4.52e-03

Pos logit contributions
arter+0.004
 robber+0.003
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.001
 about-0.000
 such-0.000
 together-0.000
aw-0.000
Token old
Token ID1468
Feature activation+4.36e-02

Pos logit contributions
arter+0.012
 robber+0.010
 trigger+0.010
 pawn+0.010
alks+0.010
Neg logit contributions
 about-0.005
aw-0.005
So-0.005
 by-0.005
's-0.005
Token man
Token ID582
Feature activation+2.45e-02

Pos logit contributions
arter+0.080
 robber+0.076
 trigger+0.070
 pawn+0.067
 battlefield+0.066
Neg logit contributions
So-0.081
aw-0.077
-0.074
 together-0.072
 such-0.072
Token and
Token ID290
Feature activation+3.34e-03

Pos logit contributions
arter+0.066
 robber+0.062
 pawn+0.059
 trigger+0.059
 rook+0.058
Neg logit contributions
So-0.023
aw-0.022
Ph-0.019
Ab-0.019
It-0.018
Token he
Token ID339
Feature activation-1.44e-02

Pos logit contributions
arter+0.009
 robber+0.009
 trigger+0.008
 pawn+0.008
 robbers+0.008
Neg logit contributions
So-0.003
aw-0.003
 about-0.003
-0.003
Ph-0.002
Token was
Token ID373
Feature activation-8.13e-03

Pos logit contributions
So+0.014
aw+0.013
Ab+0.012
 such+0.012
Ph+0.012
Neg logit contributions
arter-0.036
 robber-0.036
 pawn-0.034
 trigger-0.034
 rook-0.033
Token very
Token ID845
Feature activation-5.31e-04

Pos logit contributions
So+0.011
aw+0.010
Ab+0.009
Ph+0.009
Prom+0.009
Neg logit contributions
arter-0.018
 robber-0.017
 pawn-0.016
 battlefield-0.016
 rook-0.015
Token a
Token ID257
Feature activation+1.51e-02

Pos logit contributions
arter+0.075
 robber+0.071
 trigger+0.069
 pawn+0.067
 rook+0.066
Neg logit contributions
So-0.021
aw-0.019
-0.017
 about-0.017
 together-0.016
Token sweet
Token ID6029
Feature activation+1.12e-02

Pos logit contributions
arter+0.030
 robber+0.027
 trigger+0.026
alks+0.024
 pawn+0.024
Neg logit contributions
So-0.027
aw-0.025
-0.024
 together-0.024
's-0.024
Token tune
Token ID14009
Feature activation+2.17e-02

Pos logit contributions
arter+0.025
 robber+0.023
 trigger+0.022
 pawn+0.021
 battlefield+0.021
Neg logit contributions
So-0.016
aw-0.016
 about-0.015
-0.015
's-0.015
Token,
Token ID11
Feature activation+1.30e-02

Pos logit contributions
arter+0.058
 robber+0.055
 trigger+0.053
 pawn+0.052
 rook+0.050
Neg logit contributions
So-0.021
aw-0.019
-0.017
Ab-0.016
 such-0.016
Token a
Token ID257
Feature activation-1.79e-02

Pos logit contributions
arter+0.036
 robber+0.035
 trigger+0.033
 pawn+0.032
 rook+0.032
Neg logit contributions
So-0.012
aw-0.010
 about-0.008
-0.008
 together-0.008
Token mis
Token ID2984
Feature activation+4.09e-02

Pos logit contributions
So+0.028
aw+0.027
+0.025
 about+0.025
 together+0.024
Neg logit contributions
arter-0.039
 robber-0.035
 trigger-0.034
 pawn-0.032
 battlefield-0.031
Tokenchie
Token ID3043
Feature activation+3.04e-02

Pos logit contributions
arter+0.056
 robber+0.050
 trigger+0.046
 pawn+0.043
 rook+0.041
Neg logit contributions
So-0.094
aw-0.091
 about-0.089
 together-0.087
-0.087
Tokenvous
Token ID31222
Feature activation-2.61e-02

Pos logit contributions
arter+0.037
 robber+0.033
 trigger+0.029
 battlefield+0.027
 pawn+0.027
Neg logit contributions
So-0.070
aw-0.066
 such-0.066
 together-0.066
 about-0.066
Token fox
Token ID21831
Feature activation-5.26e-03

Pos logit contributions
aw+0.046
So+0.045
 about+0.044
+0.043
's+0.042
Neg logit contributions
arter-0.050
 robber-0.043
 trigger-0.042
 pawn-0.040
 battlefield-0.040
Token appeared
Token ID4120
Feature activation-2.02e-02

Pos logit contributions
So+0.007
aw+0.007
 about+0.006
+0.006
 together+0.006
Neg logit contributions
arter-0.012
 robber-0.012
 trigger-0.011
 pawn-0.011
 rook-0.010
Token.
Token ID13
Feature activation+2.53e-03

Pos logit contributions
So+0.018
aw+0.016
Ph+0.014
Ab+0.014
 about+0.013
Neg logit contributions
arter-0.055
 robber-0.052
 trigger-0.050
 pawn-0.049
 rook-0.047
Token knows
Token ID4206
Feature activation+1.12e-02

Pos logit contributions
So+0.001
aw+0.001
 about+0.001
+0.001
 together+0.001
Neg logit contributions
arter-0.002
 robber-0.002
 trigger-0.002
 pawn-0.002
 rook-0.002
Token to
Token ID284
Feature activation+1.63e-02

Pos logit contributions
arter+0.029
 robber+0.028
 pawn+0.026
 robbers+0.026
 trigger+0.026
Neg logit contributions
So-0.011
aw-0.010
Ph-0.009
Ab-0.009
-0.008
Token avoid
Token ID3368
Feature activation-1.05e-02

Pos logit contributions
arter+0.039
 robber+0.037
 trigger+0.035
 pawn+0.034
 battlefield+0.033
Neg logit contributions
So-0.021
aw-0.020
-0.019
 about-0.019
 such-0.018
Token big
Token ID1263
Feature activation-5.85e-03

Pos logit contributions
So+0.012
aw+0.011
 about+0.010
+0.010
 together+0.010
Neg logit contributions
arter-0.027
 robber-0.025
 trigger-0.024
 pawn-0.023
 battlefield-0.023
Token p
Token ID279
Feature activation+1.75e-02

Pos logit contributions
aw+0.007
So+0.007
 about+0.006
+0.006
 together+0.006
Neg logit contributions
arter-0.014
 robber-0.013
 trigger-0.013
 pawn-0.012
 battlefield-0.012
Tokenudd
Token ID4185
Feature activation+4.43e-02

Pos logit contributions
arter+0.041
 robber+0.039
 trigger+0.037
 pawn+0.036
 rook+0.035
Neg logit contributions
aw-0.024
So-0.023
 together-0.021
 about-0.021
-0.021
Tokenles
Token ID829
Feature activation+9.90e-03

Pos logit contributions
arter+0.085
 robber+0.077
 pawn+0.071
 trigger+0.071
 rook+0.070
Neg logit contributions
aw-0.080
So-0.079
 about-0.074
-0.072
 together-0.072
Token of
Token ID286
Feature activation-1.44e-02

Pos logit contributions
arter+0.028
 robber+0.027
 trigger+0.026
 pawn+0.025
 rook+0.024
Neg logit contributions
So-0.008
aw-0.008
 about-0.007
-0.007
 together-0.007
Token oil
Token ID3056
Feature activation-6.10e-03

Pos logit contributions
So+0.018
aw+0.017
 about+0.017
 such+0.016
+0.016
Neg logit contributions
arter-0.035
 robber-0.032
 trigger-0.031
 pawn-0.030
 battlefield-0.029
Token and
Token ID290
Feature activation+5.43e-03

Pos logit contributions
So+0.005
aw+0.005
 about+0.005
+0.004
 together+0.004
Neg logit contributions
arter-0.017
 robber-0.016
 trigger-0.015
 pawn-0.015
 rook-0.015
Token go
Token ID467
Feature activation-3.02e-02

Pos logit contributions
arter+0.013
 robber+0.012
 trigger+0.012
 pawn+0.011
 battlefield+0.011
Neg logit contributions
So-0.007
aw-0.007
 about-0.006
-0.006
 together-0.006
Token He
Token ID679
Feature activation+2.04e-02

Pos logit contributions
So+0.002
aw+0.002
 together+0.002
+0.002
 such+0.002
Neg logit contributions
arter-0.006
 robber-0.006
 trigger-0.006
 pawn-0.006
 battlefield-0.006
Token did
Token ID750
Feature activation+1.52e-02

Pos logit contributions
arter+0.055
 robber+0.051
 trigger+0.049
 pawn+0.047
 rook+0.047
Neg logit contributions
So-0.021
aw-0.020
 about-0.018
-0.018
 together-0.018
Token not
Token ID407
Feature activation+1.18e-02

Pos logit contributions
arter+0.036
 robber+0.034
 trigger+0.032
 pawn+0.031
 battlefield+0.030
Neg logit contributions
So-0.020
aw-0.019
-0.017
Ab-0.017
 together-0.017
Token know
Token ID760
Feature activation+3.14e-02

Pos logit contributions
arter+0.030
 trigger+0.027
alks+0.027
 pawn+0.026
 battlefield+0.026
Neg logit contributions
 about-0.014
So-0.014
-0.013
's-0.013
 by-0.012
Token where
Token ID810
Feature activation+2.76e-03

Pos logit contributions
arter+0.082
 robber+0.077
 trigger+0.073
 pawn+0.071
 robbers+0.070
Neg logit contributions
So-0.034
aw-0.031
-0.028
Ab-0.026
Ph-0.026
Token to
Token ID284
Feature activation+4.18e-02

Pos logit contributions
arter+0.007
 robber+0.007
 trigger+0.006
 pawn+0.006
 rook+0.006
Neg logit contributions
So-0.003
aw-0.003
-0.003
 about-0.003
 together-0.003
Token go
Token ID467
Feature activation+7.30e-03

Pos logit contributions
arter+0.087
 robber+0.080
 trigger+0.076
 pawn+0.073
 rook+0.071
Neg logit contributions
So-0.067
aw-0.065
 about-0.061
-0.060
 together-0.060
Token.
Token ID13
Feature activation-1.73e-03

Pos logit contributions
arter+0.020
 robber+0.019
 trigger+0.018
 pawn+0.018
 robbers+0.018
Neg logit contributions
So-0.007
aw-0.006
 about-0.005
Ab-0.005
-0.005
Token
Token ID198
Feature activation+6.92e-04

Pos logit contributions
So+0.001
aw+0.001
 such+0.001
+0.001
Ab+0.001
Neg logit contributions
arter-0.005
 robber-0.005
 trigger-0.004
 pawn-0.004
 robbers-0.004
Token
Token ID198
Feature activation+1.62e-02

Pos logit contributions
arter+0.002
 robber+0.002
rex+0.001
 trigger+0.001
 battlefield+0.001
Neg logit contributions
aw-0.001
 such-0.001
 enough-0.001
So-0.001
-0.001
TokenTom
Token ID13787
Feature activation+1.78e-02

Pos logit contributions
arter+0.043
 robber+0.043
 trigger+0.040
 pawn+0.039
 robbers+0.038
Neg logit contributions
So-0.013
aw-0.013
 such-0.013
 together-0.013
 about-0.012
Token seen
Token ID1775
Feature activation+8.37e-03

Pos logit contributions
arter+0.014
 robber+0.014
 trigger+0.013
 pawn+0.012
 robbers+0.012
Neg logit contributions
So-0.009
aw-0.008
-0.007
 together-0.007
Ph-0.007
Token it
Token ID340
Feature activation-4.56e-03

Pos logit contributions
arter+0.022
 robber+0.021
 trigger+0.020
 pawn+0.019
 rook+0.019
Neg logit contributions
So-0.009
aw-0.007
-0.006
 together-0.006
Ph-0.006
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
So+0.004
aw+0.003
 about+0.003
+0.003
 together+0.003
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.012
 pawn-0.012
 rook-0.012
Token
Token ID198
Feature activation-9.23e-03

Pos logit contributions
So+0.014
aw+0.014
 about+0.013
+0.013
 such+0.013
Neg logit contributions
arter-0.022
 robber-0.021
 trigger-0.021
 pawn-0.020
alks-0.019
Token
Token ID198
Feature activation+5.66e-03

Pos logit contributions
aw+0.008
 such+0.008
 enough+0.007
 about+0.007
So+0.006
Neg logit contributions
arter-0.022
 robber-0.022
alks-0.021
 trigger-0.021
 pawn-0.021
TokenG
Token ID38
Feature activation+4.42e-02

Pos logit contributions
arter+0.013
 robber+0.013
 trigger+0.012
 pawn+0.012
 battlefield+0.011
Neg logit contributions
 about-0.006
aw-0.006
 such-0.006
 together-0.006
So-0.006
Tokenret
Token ID1186
Feature activation+2.33e-02

Pos logit contributions
arter+0.082
 robber+0.075
 trigger+0.071
 pawn+0.068
 rook+0.066
Neg logit contributions
So-0.080
aw-0.078
 about-0.074
-0.073
 together-0.073
Tokena
Token ID64
Feature activation-8.37e-03

Pos logit contributions
arter+0.064
 robber+0.061
 trigger+0.059
 pawn+0.058
 rook+0.057
Neg logit contributions
So-0.019
aw-0.017
 together-0.016
 about-0.016
 such-0.016
Token decided
Token ID3066
Feature activation-2.08e-02

Pos logit contributions
So+0.008
 such+0.007
aw+0.007
 about+0.007
Ab+0.007
Neg logit contributions
arter-0.021
 robber-0.020
 pawn-0.019
 trigger-0.019
 rook-0.019
Token to
Token ID284
Feature activation-6.47e-03

Pos logit contributions
aw+0.026
So+0.025
Ab+0.020
Ph+0.020
Lu+0.020
Neg logit contributions
 robber-0.046
 robbers-0.043
arter-0.041
 weapon-0.040
 trigger-0.040
Token try
Token ID1949
Feature activation-1.01e-02

Pos logit contributions
So+0.010
+0.009
 about+0.009
's+0.009
 such+0.009
Neg logit contributions
arter-0.014
 robber-0.013
 trigger-0.013
 pawn-0.012
 battlefield-0.012
Token things
Token ID1243
Feature activation-1.37e-03

Pos logit contributions
So+0.015
aw+0.014
+0.013
 about+0.013
 together+0.013
Neg logit contributions
arter-0.022
 robber-0.021
 trigger-0.020
 pawn-0.019
 rook-0.018
Token are
Token ID389
Feature activation+1.32e-03

Pos logit contributions
So+0.002
aw+0.002
Ab+0.002
+0.001
 about+0.001
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 pawn-0.003
 battlefield-0.003
Token not
Token ID407
Feature activation+3.16e-03

Pos logit contributions
arter+0.003
 robber+0.003
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.001
aw-0.001
 about-0.001
-0.001
 together-0.001
Token toys
Token ID14958
Feature activation+6.42e-03

Pos logit contributions
arter+0.008
 robber+0.007
 trigger+0.007
 pawn+0.007
 robbers+0.007
Neg logit contributions
So-0.004
aw-0.004
-0.003
Ab-0.003
Ph-0.003
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
arter+0.018
 robber+0.017
 trigger+0.016
 pawn+0.016
 rook+0.015
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
-0.005
 together-0.005
Token They
Token ID1119
Feature activation+1.96e-02

Pos logit contributions
arter+0.029
 robber+0.027
 trigger+0.026
 pawn+0.025
 rook+0.025
Neg logit contributions
So-0.012
aw-0.012
 about-0.011
-0.011
 such-0.010
Token learn
Token ID2193
Feature activation+1.33e-02

Pos logit contributions
arter+0.048
 robber+0.044
 trigger+0.042
 pawn+0.040
 battlefield+0.040
Neg logit contributions
So-0.026
aw-0.024
-0.023
 about-0.023
 together-0.022
Token that
Token ID326
Feature activation+1.51e-02

Pos logit contributions
arter+0.035
 robber+0.033
 pawn+0.032
 trigger+0.032
 tablet+0.032
Neg logit contributions
So-0.012
aw-0.011
Ab-0.011
Ph-0.011
Alice-0.010
Token playing
Token ID2712
Feature activation+4.66e-02

Pos logit contributions
arter+0.038
 robber+0.035
 trigger+0.033
 pawn+0.033
 robbers+0.032
Neg logit contributions
So-0.018
aw-0.018
Ab-0.015
Ph-0.015
-0.014
Token with
Token ID351
Feature activation+2.81e-02

Pos logit contributions
arter+0.141
 robber+0.129
 trigger+0.127
alks+0.121
 pawn+0.120
Neg logit contributions
So-0.035
 together-0.032
aw-0.031
 about-0.030
-0.029
Token lasers
Token ID34628
Feature activation+2.09e-02

Pos logit contributions
arter+0.075
 robber+0.070
 trigger+0.068
 pawn+0.065
 battlefield+0.064
Neg logit contributions
So-0.028
aw-0.027
 about-0.026
 together-0.026
 such-0.025
Token build
Token ID1382
Feature activation+1.07e-03

Pos logit contributions
So+0.013
 together+0.012
+0.012
 about+0.012
's+0.012
Neg logit contributions
arter-0.013
 robber-0.011
 trigger-0.011
 battlefield-0.010
 pawn-0.010
Token a
Token ID257
Feature activation-2.51e-03

Pos logit contributions
arter+0.003
 robber+0.002
 trigger+0.002
 pawn+0.002
 rook+0.002
Neg logit contributions
So-0.001
aw-0.001
Ab-0.001
-0.001
Ph-0.001
Token huge
Token ID3236
Feature activation+1.14e-04

Pos logit contributions
So+0.005
 together+0.004
aw+0.004
+0.004
's+0.004
Neg logit contributions
arter-0.005
 robber-0.004
 trigger-0.004
 pawn-0.004
alks-0.004
Token tower
Token ID10580
Feature activation-2.10e-02

Pos logit contributions
arter+0.000
 robber+0.000
 trigger+0.000
alks+0.000
 pawn+0.000
Neg logit contributions
 together-0.000
aw-0.000
So-0.000
 about-0.000
's-0.000
Token.
Token ID13
Feature activation+5.67e-04

Pos logit contributions
So+0.016
aw+0.014
Ab+0.012
 such+0.011
Ph+0.011
Neg logit contributions
arter-0.061
 robber-0.058
 trigger-0.056
 pawn-0.055
 rook-0.054
Token They
Token ID1119
Feature activation+3.74e-03

Pos logit contributions
arter+0.001
 robber+0.001
 trigger+0.001
 pawn+0.001
alks+0.001
Neg logit contributions
So-0.001
aw-0.001
 such-0.001
-0.001
 about-0.001
Token use
Token ID779
Feature activation+5.80e-03

Pos logit contributions
arter+0.008
 robber+0.007
 trigger+0.007
 battlefield+0.007
alks+0.007
Neg logit contributions
So-0.006
-0.006
's-0.005
 together-0.005
aw-0.005
Token all
Token ID477
Feature activation+1.92e-02

Pos logit contributions
arter+0.016
 robber+0.015
 trigger+0.015
 pawn+0.014
 rook+0.014
Neg logit contributions
So-0.005
aw-0.005
-0.004
 about-0.004
 together-0.004
Token the
Token ID262
Feature activation+9.16e-03

Pos logit contributions
arter+0.039
alks+0.037
 pawn+0.037
igsaw+0.035
 rook+0.035
Neg logit contributions
So-0.025
Ph-0.024
aw-0.024
Ab-0.023
Deb-0.023
Token blocks
Token ID7021
Feature activation-1.86e-02

Pos logit contributions
arter+0.016
 robber+0.014
 trigger+0.013
 pawn+0.012
 battlefield+0.012
Neg logit contributions
So-0.018
aw-0.018
 about-0.017
-0.017
 together-0.017
Token they
Token ID484
Feature activation-1.31e-02

Pos logit contributions
So+0.013
aw+0.012
+0.010
Ab+0.010
 about+0.010
Neg logit contributions
arter-0.055
 robber-0.052
 trigger-0.050
 pawn-0.049
 rook-0.048
Token his
Token ID465
Feature activation+1.40e-02

Pos logit contributions
So+0.004
aw+0.004
 about+0.004
+0.003
 together+0.003
Neg logit contributions
arter-0.011
 robber-0.010
 trigger-0.010
 pawn-0.010
 rook-0.010
Token broken
Token ID5445
Feature activation+3.36e-02

Pos logit contributions
arter+0.029
 robber+0.027
 trigger+0.025
 pawn+0.025
 battlefield+0.024
Neg logit contributions
So-0.023
aw-0.021
-0.021
 about-0.020
's-0.020
Token zipper
Token ID48992
Feature activation+2.03e-02

Pos logit contributions
arter+0.056
 robber+0.052
 trigger+0.050
 pawn+0.046
 rook+0.044
Neg logit contributions
So-0.067
aw-0.065
 about-0.061
-0.061
 together-0.061
Token.
Token ID13
Feature activation+3.90e-03

Pos logit contributions
arter+0.060
 robber+0.057
 trigger+0.055
 pawn+0.054
 battlefield+0.052
Neg logit contributions
So-0.014
aw-0.013
-0.011
Ab-0.011
 about-0.011
Token They
Token ID1119
Feature activation+2.64e-03

Pos logit contributions
arter+0.009
 robber+0.009
 trigger+0.008
 pawn+0.008
 rook+0.008
Neg logit contributions
So-0.005
aw-0.005
 about-0.005
 together-0.005
's-0.005
Token tried
Token ID3088
Feature activation+1.03e-02

Pos logit contributions
arter+0.007
 robber+0.006
 trigger+0.006
 pawn+0.006
 rook+0.006
Neg logit contributions
So-0.003
aw-0.003
 about-0.002
-0.002
 such-0.002
Token to
Token ID284
Feature activation+2.53e-02

Pos logit contributions
arter+0.032
 robber+0.031
 trigger+0.029
 pawn+0.029
 rook+0.028
Neg logit contributions
So-0.006
aw-0.006
-0.004
 about-0.004
Ab-0.004
Token help
Token ID1037
Feature activation+7.60e-03

Pos logit contributions
arter+0.059
 robber+0.051
alks+0.050
 trigger+0.050
 battlefield+0.049
Neg logit contributions
So-0.039
-0.035
 together-0.033
's-0.033
 by-0.033
Token him
Token ID683
Feature activation+2.94e-02

Pos logit contributions
arter+0.021
 robber+0.019
 trigger+0.018
 pawn+0.018
 rook+0.018
Neg logit contributions
So-0.008
 about-0.007
 together-0.007
's-0.007
aw-0.007
Token,
Token ID11
Feature activation+6.94e-04

Pos logit contributions
arter+0.081
 robber+0.076
 trigger+0.073
 pawn+0.070
 battlefield+0.070
Neg logit contributions
So-0.029
 about-0.026
-0.026
 together-0.026
's-0.026
Token but
Token ID475
Feature activation-3.20e-03

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.001
 pawn+0.001
 rook+0.001
Neg logit contributions
So-0.001
aw-0.001
-0.001
 about-0.001
 together-0.001
Token dug
Token ID18735
Feature activation-1.24e-02

Pos logit contributions
So+0.019
+0.018
 was+0.017
's+0.017
 together+0.017
Neg logit contributions
arter-0.068
 robber-0.060
 trigger-0.058
igsaw-0.057
alks-0.056
Token.
Token ID13
Feature activation-1.34e-02

Pos logit contributions
So+0.014
aw+0.012
Ph+0.012
Ab+0.012
Prom+0.012
Neg logit contributions
arter-0.029
 trigger-0.028
 robber-0.028
 pawn-0.027
 battlefield-0.026
Token It
Token ID632
Feature activation+1.12e-02

Pos logit contributions
So+0.019
aw+0.018
 about+0.017
+0.017
 together+0.017
Neg logit contributions
arter-0.030
 robber-0.028
 trigger-0.027
 pawn-0.026
 rook-0.025
Token was
Token ID373
Feature activation+5.51e-03

Pos logit contributions
arter+0.036
 robber+0.034
 trigger+0.033
 pawn+0.032
 rook+0.032
Neg logit contributions
So-0.005
aw-0.005
 about-0.004
-0.003
 such-0.003
Token an
Token ID281
Feature activation-2.99e-02

Pos logit contributions
arter+0.016
 robber+0.015
 trigger+0.014
 pawn+0.014
 rook+0.013
Neg logit contributions
So-0.005
aw-0.005
-0.004
 about-0.004
 together-0.004
Token old
Token ID1468
Feature activation+6.08e-03

Pos logit contributions
So+0.044
 about+0.043
aw+0.043
+0.042
 such+0.039
Neg logit contributions
arter-0.065
 robber-0.060
 trigger-0.059
 pawn-0.058
 rook-0.056
Token toy
Token ID13373
Feature activation+1.67e-03

Pos logit contributions
arter+0.011
 robber+0.010
 trigger+0.009
 pawn+0.009
 battlefield+0.009
Neg logit contributions
So-0.011
aw-0.011
 about-0.011
-0.010
 together-0.010
Token that
Token ID326
Feature activation+6.75e-04

Pos logit contributions
arter+0.005
 robber+0.004
 trigger+0.004
 pawn+0.004
 battlefield+0.004
Neg logit contributions
So-0.002
aw-0.001
-0.001
 together-0.001
 about-0.001
Token Jack
Token ID3619
Feature activation+4.68e-03

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.002
 pawn+0.002
 rook+0.002
Neg logit contributions
So-0.001
aw-0.001
 about-0.001
-0.001
 together-0.000
Token used
Token ID973
Feature activation-5.50e-03

Pos logit contributions
arter+0.013
 robber+0.012
 trigger+0.012
 pawn+0.012
 rook+0.011
Neg logit contributions
So-0.004
aw-0.004
 about-0.004
-0.003
 together-0.003
Token to
Token ID284
Feature activation+2.35e-03

Pos logit contributions
So+0.004
aw+0.004
Ab+0.003
+0.003
Ph+0.003
Neg logit contributions
arter-0.016
 robber-0.015
 trigger-0.015
 pawn-0.014
 rook-0.014
Token down
Token ID866
Feature activation+9.42e-03

Pos logit contributions
arter+0.004
 robber+0.004
 trigger+0.004
 pawn+0.004
 rook+0.003
Neg logit contributions
So-0.002
aw-0.001
 about-0.001
-0.001
 together-0.001
Token.
Token ID13
Feature activation+3.19e-02

Pos logit contributions
arter+0.027
 robber+0.026
 trigger+0.025
 pawn+0.024
 rook+0.024
Neg logit contributions
So-0.007
aw-0.007
-0.005
 about-0.005
Ab-0.005
Token It
Token ID632
Feature activation+2.37e-02

Pos logit contributions
arter+0.075
 robber+0.070
 trigger+0.067
 pawn+0.065
 rook+0.064
Neg logit contributions
So-0.043
aw-0.040
Ab-0.038
-0.037
 together-0.036
Token makes
Token ID1838
Feature activation+1.85e-02

Pos logit contributions
arter+0.052
 robber+0.048
 trigger+0.046
 pawn+0.044
 rook+0.043
Neg logit contributions
So-0.036
aw-0.034
 about-0.032
-0.032
 together-0.031
Token a
Token ID257
Feature activation+8.16e-04

Pos logit contributions
arter+0.051
 robber+0.048
 trigger+0.048
 pawn+0.045
 battlefield+0.045
Neg logit contributions
So-0.017
aw-0.014
Ab-0.013
-0.013
 about-0.012
Token loud
Token ID7812
Feature activation+1.01e-02

Pos logit contributions
arter+0.002
 robber+0.002
 pawn+0.001
 trigger+0.001
 robbers+0.001
Neg logit contributions
So-0.001
aw-0.001
-0.001
's-0.001
It-0.001
Token noise
Token ID7838
Feature activation+2.96e-02

Pos logit contributions
arter+0.021
 robber+0.019
 trigger+0.018
 pawn+0.018
 rook+0.017
Neg logit contributions
So-0.016
aw-0.016
 about-0.015
-0.015
's-0.015
Token.
Token ID13
Feature activation+2.32e-02

Pos logit contributions
arter+0.098
 robber+0.094
 trigger+0.091
 pawn+0.089
 rook+0.088
Neg logit contributions
aw-0.011
So-0.011
 about-0.010
 together-0.008
-0.008
Token It
Token ID632
Feature activation+1.77e-02

Pos logit contributions
arter+0.055
 robber+0.052
 trigger+0.049
 pawn+0.049
 rook+0.047
Neg logit contributions
So-0.029
aw-0.028
Ab-0.026
-0.025
Ph-0.024
Token breaks
Token ID9457
Feature activation-4.92e-04

Pos logit contributions
arter+0.041
 robber+0.038
 trigger+0.036
 pawn+0.035
 rook+0.034
Neg logit contributions
So-0.024
aw-0.024
-0.022
 about-0.022
's-0.022
Token into
Token ID656
Feature activation-5.92e-03

Pos logit contributions
So+0.001
aw+0.001
+0.000
 about+0.000
 such+0.000
Neg logit contributions
arter-0.001
 robber-0.001
 trigger-0.001
 pawn-0.001
 rook-0.001
Token a
Token ID257
Feature activation-5.22e-05

Pos logit contributions
arter+0.006
 robber+0.006
 trigger+0.006
 pawn+0.006
 rook+0.006
Neg logit contributions
So-0.002
aw-0.002
-0.002
Ab-0.002
Ph-0.002
Token new
Token ID649
Feature activation+3.37e-03

Pos logit contributions
So+0.000
aw+0.000
+0.000
 together+0.000
 about+0.000
Neg logit contributions
arter-0.000
 robber-0.000
 trigger-0.000
 pawn-0.000
 battlefield-0.000
Token friend
Token ID1545
Feature activation+4.72e-03

Pos logit contributions
arter+0.008
 robber+0.007
 trigger+0.007
 pawn+0.006
 rook+0.006
Neg logit contributions
So-0.005
aw-0.005
 about-0.004
-0.004
 together-0.004
Token and
Token ID290
Feature activation+1.08e-03

Pos logit contributions
arter+0.013
 robber+0.012
 pawn+0.012
 trigger+0.012
 rook+0.011
Neg logit contributions
So-0.004
aw-0.004
Ab-0.003
Ph-0.003
-0.003
Token was
Token ID373
Feature activation-1.39e-02

Pos logit contributions
arter+0.003
 robber+0.003
 trigger+0.003
 pawn+0.003
 rook+0.003
Neg logit contributions
So-0.001
aw-0.001
-0.001
 about-0.001
 together-0.001
Token never
Token ID1239
Feature activation-2.06e-02

Pos logit contributions
So+0.020
aw+0.017
Ph+0.015
 So+0.015
Ab+0.015
Neg logit contributions
arter-0.030
 robber-0.028
 knight-0.025
 pawn-0.025
 rook-0.024
Token frustrated
Token ID14718
Feature activation+1.68e-02

Pos logit contributions
So+0.035
aw+0.034
 about+0.033
+0.032
 such+0.032
Neg logit contributions
arter-0.040
 robber-0.037
 trigger-0.035
 pawn-0.034
 rook-0.032
Token again
Token ID757
Feature activation-1.55e-02

Pos logit contributions
arter+0.043
 robber+0.041
 trigger+0.038
 pawn+0.038
 rook+0.037
Neg logit contributions
So-0.019
aw-0.017
-0.015
Ab-0.015
Ph-0.015
Token.
Token ID13
Feature activation-8.45e-03

Pos logit contributions
So+0.010
aw+0.009
 about+0.008
+0.008
 together+0.007
Neg logit contributions
arter-0.047
 robber-0.044
 trigger-0.043
 pawn-0.042
 battlefield-0.041
Token<|endoftext|>
Token ID50256
Feature activation+4.24e-03

Pos logit contributions
So+0.005
aw+0.004
 about+0.003
 together+0.003
+0.003
Neg logit contributions
arter-0.026
 robber-0.025
 trigger-0.024
 pawn-0.024
 rook-0.023
TokenOnce
Token ID7454
Feature activation+6.67e-03

Pos logit contributions
arter+0.010
 robber+0.010
 pawn+0.009
 trigger+0.009
 battlefield+0.009
Neg logit contributions
So-0.004
aw-0.004
Ab-0.004
 enough-0.003
Ph-0.003
Token bear
Token ID6842
Feature activation+3.23e-02

Pos logit contributions
arter+0.085
alks+0.074
 battlefield+0.067
 robber+0.065
igsaw+0.065
Neg logit contributions
's-0.100
 by-0.098
 was-0.096
 such-0.095
 together-0.095
Token?
Token ID30
Feature activation+1.55e-02

Pos logit contributions
arter+0.083
 trigger+0.078
 robber+0.076
 pawn+0.073
alks+0.072
Neg logit contributions
So-0.034
 about-0.034
aw-0.034
 together-0.034
-0.033
Token It
Token ID632
Feature activation+1.73e-02

Pos logit contributions
arter+0.039
 robber+0.037
 trigger+0.035
 pawn+0.034
 battlefield+0.034
Neg logit contributions
So-0.018
aw-0.017
-0.016
 about-0.016
 together-0.015
Token's
Token ID338
Feature activation-2.69e-02

Pos logit contributions
arter+0.053
 robber+0.051
 trigger+0.049
 pawn+0.048
 rook+0.047
Neg logit contributions
So-0.010
aw-0.009
-0.009
's-0.008
 about-0.008
Token just
Token ID655
Feature activation-1.22e-02

Pos logit contributions
So+0.029
 about+0.029
aw+0.028
 such+0.027
+0.027
Neg logit contributions
arter-0.069
 robber-0.064
 trigger-0.063
 pawn-0.060
 rook-0.059
Token a
Token ID257
Feature activation-2.57e-02

Pos logit contributions
aw+0.010
So+0.010
 about+0.009
 such+0.009
+0.009
Neg logit contributions
arter-0.034
 robber-0.032
 trigger-0.032
 pawn-0.030
 battlefield-0.030
Token toy
Token ID13373
Feature activation+7.57e-03

Pos logit contributions
+0.035
So+0.034
's+0.033
 was+0.032
 more+0.032
Neg logit contributions
arter-0.059
alks-0.051
 trigger-0.050
 robber-0.049
 battlefield-0.049
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
arter+0.022
 robber+0.020
 trigger+0.020
 pawn+0.019
alks+0.019
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
-0.005
's-0.005
Token You
Token ID921
Feature activation-5.30e-03

Pos logit contributions
arter+0.030
 robber+0.028
 trigger+0.027
 pawn+0.026
 battlefield+0.025
Neg logit contributions
So-0.013
aw-0.012
-0.011
 about-0.011
 together-0.011
Token should
Token ID815
Feature activation+1.28e-02

Pos logit contributions
+0.005
's+0.005
So+0.005
 about+0.005
aw+0.005
Neg logit contributions
arter-0.015
 trigger-0.013
 robber-0.013
alks-0.013
 battlefield-0.012
Token share
Token ID2648
Feature activation-7.57e-03

Pos logit contributions
arter+0.032
 robber+0.029
 trigger+0.029
 pawn+0.028
 battlefield+0.028
Neg logit contributions
So-0.015
 about-0.014
-0.014
aw-0.013
's-0.013
Token to
Token ID284
Feature activation+1.03e-02

Pos logit contributions
aw+0.008
So+0.007
Ph+0.006
uct+0.006
Ab+0.006
Neg logit contributions
arter-0.017
 robber-0.017
 pawn-0.016
 robbers-0.016
 battlefield-0.016
Token lock
Token ID5793
Feature activation-1.18e-02

Pos logit contributions
arter+0.021
 robber+0.020
 trigger+0.019
 pawn+0.018
 rook+0.017
Neg logit contributions
So-0.017
aw-0.016
-0.016
 about-0.015
 together-0.015
Token the
Token ID262
Feature activation+6.70e-03

Pos logit contributions
So+0.010
aw+0.009
Ab+0.008
+0.007
Ph+0.007
Neg logit contributions
arter-0.033
 robber-0.032
 trigger-0.031
 pawn-0.030
 battlefield-0.029
Token door
Token ID3420
Feature activation-5.50e-03

Pos logit contributions
arter+0.013
 robber+0.012
 trigger+0.011
 pawn+0.011
alks+0.011
Neg logit contributions
So-0.012
 about-0.011
aw-0.011
's-0.011
-0.011
Token so
Token ID523
Feature activation-2.07e-03

Pos logit contributions
So+0.006
aw+0.006
Ab+0.005
Ph+0.005
 such+0.004
Neg logit contributions
arter-0.014
 robber-0.013
 trigger-0.012
 pawn-0.012
 battlefield-0.012
Token no
Token ID645
Feature activation-5.99e-02

Pos logit contributions
So+0.002
aw+0.002
Ab+0.002
Ph+0.002
 such+0.002
Neg logit contributions
arter-0.005
 trigger-0.005
 robber-0.005
 pawn-0.004
 battlefield-0.004
Token monsters
Token ID10963
Feature activation-2.71e-02

Pos logit contributions
So+0.074
aw+0.070
 about+0.066
+0.065
 together+0.064
Neg logit contributions
arter-0.147
 robber-0.137
 trigger-0.132
 pawn-0.128
 rook-0.125
Token can
Token ID460
Feature activation+1.13e-02

Pos logit contributions
So+0.036
aw+0.034
Ab+0.030
 such+0.030
 about+0.030
Neg logit contributions
arter-0.064
 robber-0.060
 trigger-0.058
 pawn-0.055
 battlefield-0.054
Token come
Token ID1282
Feature activation-6.73e-03

Pos logit contributions
arter+0.024
 robber+0.022
 trigger+0.021
 pawn+0.021
 rook+0.020
Neg logit contributions
So-0.018
-0.017
 about-0.016
's-0.016
aw-0.016
Token in
Token ID287
Feature activation+3.76e-03

Pos logit contributions
So+0.006
 together+0.006
 about+0.006
+0.006
's+0.006
Neg logit contributions
arter-0.019
 robber-0.018
 trigger-0.017
 pawn-0.017
 rook-0.016
Token,"
Token ID553
Feature activation-2.00e-02

Pos logit contributions
arter+0.010
 robber+0.009
 trigger+0.009
 pawn+0.008
 battlefield+0.008
Neg logit contributions
aw-0.004
So-0.004
Ab-0.003
Ph-0.003
 about-0.003
Token walked
Token ID6807
Feature activation-8.94e-03

Pos logit contributions
 robber+0.000
arter+0.000
 robbers+0.000
 pawn+0.000
 trigger+0.000
Neg logit contributions
So-0.000
aw-0.000
 about-0.000
Ab-0.000
 such-0.000
Token back
Token ID736
Feature activation-2.44e-02

Pos logit contributions
So+0.016
aw+0.015
+0.013
Prom+0.013
Ab+0.013
Neg logit contributions
 robber-0.015
arter-0.015
 trigger-0.014
 robbers-0.014
 pawn-0.014
Token to
Token ID284
Feature activation-2.30e-02

Pos logit contributions
So+0.037
aw+0.036
+0.030
Ph+0.030
It+0.029
Neg logit contributions
arter-0.053
 robber-0.048
 robbers-0.046
 pawn-0.046
alks-0.044
Token their
Token ID511
Feature activation-1.93e-02

Pos logit contributions
So+0.027
aw+0.026
+0.021
 about+0.020
Ab+0.020
Neg logit contributions
arter-0.060
 robber-0.056
 trigger-0.052
 robbers-0.052
 pawn-0.051
Token small
Token ID1402
Feature activation-1.79e-03

Pos logit contributions
So+0.030
aw+0.029
 about+0.027
+0.027
 such+0.027
Neg logit contributions
arter-0.041
 robber-0.038
 trigger-0.036
 pawn-0.035
 rook-0.034
Token house
Token ID2156
Feature activation-2.16e-02

Pos logit contributions
So+0.003
aw+0.003
 about+0.003
+0.003
 together+0.003
Neg logit contributions
arter-0.003
 robber-0.003
 trigger-0.003
 pawn-0.003
 rook-0.003
Token.
Token ID13
Feature activation-1.76e-02

Pos logit contributions
So+0.025
aw+0.024
Ab+0.020
It+0.020
+0.020
Neg logit contributions
arter-0.054
 robber-0.051
 pawn-0.048
 trigger-0.047
sing-0.047
Token
Token ID198
Feature activation-1.73e-02

Pos logit contributions
aw+0.022
So+0.020
 such+0.016
 enough+0.016
+0.016
Neg logit contributions
arter-0.043
 robber-0.041
 robbers-0.038
 battlefield-0.037
 trigger-0.037
Token
Token ID198
Feature activation-2.52e-03

Pos logit contributions
aw+0.015
So+0.013
 enough+0.012
 such+0.012
+0.010
Neg logit contributions
arter-0.046
 robber-0.043
 tablet-0.041
 battlefield-0.040
 trigger-0.040
TokenAs
Token ID1722
Feature activation-4.01e-03

Pos logit contributions
aw+0.003
 enough+0.003
 about+0.003
 such+0.002
's+0.002
Neg logit contributions
 robber-0.006
arter-0.006
 robbers-0.005
 trigger-0.005
 battlefield-0.005
Token they
Token ID484
Feature activation+6.90e-03

Pos logit contributions
aw+0.006
So+0.006
uct+0.004
+0.004
's+0.004
Neg logit contributions
arter-0.009
 robber-0.009
 robbers-0.008
 pawn-0.007
 trigger-0.007
Token,
Token ID11
Feature activation-6.83e-03

Pos logit contributions
arter+0.027
 robber+0.026
 trigger+0.025
 pawn+0.024
 rook+0.023
Neg logit contributions
So-0.011
aw-0.010
-0.009
Ab-0.009
 such-0.009
Token and
Token ID290
Feature activation-1.03e-03

Pos logit contributions
So+0.008
aw+0.007
Ab+0.006
 about+0.006
+0.006
Neg logit contributions
arter-0.016
 robber-0.016
 pawn-0.015
 trigger-0.015
 robbers-0.015
Token the
Token ID262
Feature activation-1.33e-02

Pos logit contributions
So+0.001
aw+0.001
 about+0.001
Ab+0.001
+0.001
Neg logit contributions
arter-0.002
 robber-0.002
 trigger-0.002
 robbers-0.002
 pawn-0.002
Token boys
Token ID6510
Feature activation+1.04e-02

Pos logit contributions
So+0.014
aw+0.014
 right+0.013
's+0.013
+0.013
Neg logit contributions
arter-0.037
 trigger-0.031
alks-0.031
 robber-0.031
 pawn-0.030
Token included
Token ID3017
Feature activation-1.95e-02

Pos logit contributions
arter+0.024
 robber+0.024
 trigger+0.022
 pawn+0.022
 robbers+0.022
Neg logit contributions
So-0.012
aw-0.011
 such-0.010
Ab-0.010
 about-0.010
Token everything
Token ID2279
Feature activation-3.34e-02

Pos logit contributions
So+0.022
aw+0.019
+0.017
Ab+0.017
 about+0.017
Neg logit contributions
arter-0.048
 robber-0.047
 trigger-0.044
 pawn-0.044
 robbers-0.043
Token that
Token ID326
Feature activation-4.93e-03

Pos logit contributions
So+0.039
aw+0.036
Ph+0.030
Alice+0.029
Ab+0.029
Neg logit contributions
arter-0.080
 pawn-0.073
 robber-0.073
 rook-0.070
 mineral-0.070
Token could
Token ID714
Feature activation-2.27e-03

Pos logit contributions
So+0.005
aw+0.005
+0.004
 about+0.004
 together+0.004
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.012
 pawn-0.011
 battlefield-0.011
Token make
Token ID787
Feature activation+2.64e-03

Pos logit contributions
So+0.003
+0.003
 about+0.003
aw+0.003
 such+0.003
Neg logit contributions
arter-0.005
 robber-0.005
 trigger-0.005
 pawn-0.004
 rook-0.004
Token their
Token ID511
Feature activation-7.10e-04

Pos logit contributions
arter+0.006
 robber+0.006
 trigger+0.006
 pawn+0.006
 battlefield+0.006
Neg logit contributions
So-0.003
aw-0.002
Ab-0.002
Prom-0.002
Ph-0.002
Token day
Token ID1110
Feature activation+1.78e-02

Pos logit contributions
So+0.001
aw+0.001
+0.001
 about+0.001
 together+0.001
Neg logit contributions
arter-0.002
 robber-0.001
 trigger-0.001
 pawn-0.001
 rook-0.001
Tokenpron
Token ID31186
Feature activation-2.77e-02

Pos logit contributions
arter+0.012
 robber+0.010
 trigger+0.010
 pawn+0.010
 battlefield+0.009
Neg logit contributions
So-0.009
aw-0.009
 about-0.009
-0.009
 together-0.009
Token and
Token ID290
Feature activation+4.42e-03

Pos logit contributions
So+0.023
aw+0.021
+0.019
 about+0.018
 together+0.018
Neg logit contributions
arter-0.079
 robber-0.075
 trigger-0.072
 pawn-0.070
 rook-0.069
Token climbed
Token ID19952
Feature activation-2.20e-02

Pos logit contributions
arter+0.010
 robber+0.010
 trigger+0.009
 pawn+0.009
 rook+0.009
Neg logit contributions
So-0.006
aw-0.005
 about-0.005
 such-0.005
Ph-0.005
Token on
Token ID319
Feature activation-4.08e-03

Pos logit contributions
So+0.030
aw+0.025
Ph+0.023
+0.022
 about+0.021
Neg logit contributions
arter-0.050
 robber-0.049
 trigger-0.048
alks-0.047
 pawn-0.047
Token a
Token ID257
Feature activation+5.07e-03

Pos logit contributions
So+0.004
aw+0.004
 about+0.003
+0.003
Ph+0.003
Neg logit contributions
arter-0.011
 robber-0.011
 trigger-0.010
 pawn-0.010
 rook-0.010
Token stool
Token ID38753
Feature activation-8.51e-02

Pos logit contributions
arter+0.009
 robber+0.008
 trigger+0.008
 pawn+0.007
 rook+0.007
Neg logit contributions
So-0.010
aw-0.009
 about-0.009
 such-0.009
 together-0.009
Token.
Token ID13
Feature activation+6.60e-04

Pos logit contributions
So+0.083
aw+0.073
Ab+0.072
Ph+0.068
 such+0.063
Neg logit contributions
arter-0.219
 robber-0.214
 trigger-0.208
 pawn-0.201
 battlefield-0.200
Token She
Token ID1375
Feature activation-7.62e-03

Pos logit contributions
arter+0.002
 robber+0.001
 trigger+0.001
 pawn+0.001
 battlefield+0.001
Neg logit contributions
So-0.001
aw-0.001
 such-0.001
Ab-0.001
 together-0.001
Token saw
Token ID2497
Feature activation+1.16e-02

Pos logit contributions
So+0.011
aw+0.010
 such+0.010
Ph+0.010
Ab+0.010
Neg logit contributions
 robber-0.015
arter-0.015
 pawn-0.015
 rook-0.014
 trigger-0.013
Token mom
Token ID1995
Feature activation-5.41e-03

Pos logit contributions
arter+0.033
 robber+0.031
 trigger+0.030
 pawn+0.030
 rook+0.029
Neg logit contributions
So-0.009
aw-0.008
-0.008
Ph-0.007
 about-0.007
Token take
Token ID1011
Feature activation+5.69e-03

Pos logit contributions
So+0.006
aw+0.006
Ph+0.006
Ab+0.006
Prom+0.005
Neg logit contributions
arter-0.012
 robber-0.011
 pawn-0.011
 trigger-0.011
 robbers-0.011
Token and
Token ID290
Feature activation-5.59e-03

Pos logit contributions
arter+0.018
 robber+0.017
 trigger+0.016
 pawn+0.016
 battlefield+0.016
Neg logit contributions
So-0.007
aw-0.007
Ab-0.006
Ph-0.006
 such-0.005
Token determination
Token ID12123
Feature activation-1.76e-02

Pos logit contributions
So+0.007
aw+0.007
Ab+0.006
Ph+0.006
 about+0.006
Neg logit contributions
arter-0.013
 robber-0.012
 trigger-0.011
 pawn-0.011
 robbers-0.011
Token,
Token ID11
Feature activation-1.26e-02

Pos logit contributions
So+0.017
aw+0.017
Ab+0.016
Ph+0.015
Alice+0.013
Neg logit contributions
arter-0.045
 robber-0.043
 trigger-0.041
 pawn-0.041
 robbers-0.039
Token anything
Token ID1997
Feature activation-5.40e-02

Pos logit contributions
So+0.014
aw+0.013
Ab+0.011
 about+0.011
Ph+0.011
Neg logit contributions
arter-0.032
 robber-0.030
 trigger-0.028
 pawn-0.028
 rook-0.027
Token is
Token ID318
Feature activation-2.61e-02

Pos logit contributions
aw+0.065
So+0.065
Ab+0.062
Alice+0.059
Ph+0.058
Neg logit contributions
arter-0.119
 robber-0.114
 pawn-0.108
 trigger-0.105
 robbers-0.102
Token possible
Token ID1744
Feature activation-8.11e-02

Pos logit contributions
So+0.036
aw+0.036
Ab+0.031
Ph+0.031
's+0.030
Neg logit contributions
arter-0.058
 robber-0.056
 trigger-0.051
 pawn-0.050
 robbers-0.049
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
aw+0.085
So+0.081
Ph+0.079
Ab+0.074
Alice+0.065
Neg logit contributions
arter-0.197
 robber-0.191
 pawn-0.179
 robbers-0.176
 trigger-0.175
Token The
Token ID383
Feature activation-9.62e-03

Pos logit contributions
aw+0.021
So+0.020
 about+0.018
 together+0.018
Ab+0.017
Neg logit contributions
arter-0.053
 robber-0.051
 pawn-0.048
alks-0.047
 trigger-0.047
Token two
Token ID734
Feature activation+2.96e-03

Pos logit contributions
So+0.012
+0.010
aw+0.010
 about+0.010
 together+0.010
Neg logit contributions
arter-0.025
 robber-0.022
 trigger-0.022
 pawn-0.021
 battlefield-0.021
Token friends
Token ID2460
Feature activation+1.19e-02

Pos logit contributions
arter+0.007
 robber+0.006
 trigger+0.006
 pawn+0.006
 robbers+0.006
Neg logit contributions
So-0.004
aw-0.004
 about-0.003
 such-0.003
-0.003
Token smiled
Token ID13541
Feature activation-2.14e-02

Pos logit contributions
arter+0.027
 robber+0.027
 trigger+0.025
 pawn+0.025
 battlefield+0.024
Neg logit contributions
So-0.013
aw-0.013
Ab-0.012
Ph-0.012
 such-0.012
Token were
Token ID547
Feature activation-2.36e-02

Pos logit contributions
arter+0.033
 pawn+0.032
 robber+0.031
 rook+0.030
 ship+0.029
Neg logit contributions
So-0.021
aw-0.021
Ph-0.020
Ab-0.020
Alice-0.018
Token very
Token ID845
Feature activation-6.95e-03

Pos logit contributions
So+0.035
aw+0.035
Prom+0.031
Ab+0.031
Ph+0.030
Neg logit contributions
arter-0.041
 robber-0.037
sing-0.035
alks-0.034
 alien-0.034
Token thankful
Token ID25535
Feature activation-6.86e-03

Pos logit contributions
aw+0.011
So+0.010
 about+0.009
 such+0.009
Ph+0.008
Neg logit contributions
arter-0.015
 robber-0.013
 pawn-0.013
 rook-0.012
alks-0.012
Token they
Token ID484
Feature activation-3.47e-02

Pos logit contributions
aw+0.010
Ab+0.009
Ph+0.009
So+0.009
Alice+0.008
Neg logit contributions
arter-0.014
 robber-0.013
sing-0.012
 spine-0.012
alks-0.012
Token were
Token ID547
Feature activation-2.65e-02

Pos logit contributions
So+0.042
aw+0.042
Ab+0.038
 about+0.036
Ph+0.035
Neg logit contributions
arter-0.079
 robber-0.079
 trigger-0.072
 pawn-0.071
 robbers-0.070
Token able
Token ID1498
Feature activation-8.14e-02

Pos logit contributions
So+0.044
aw+0.043
Ab+0.037
 So+0.037
Ph+0.037
Neg logit contributions
arter-0.049
 robber-0.044
 alien-0.040
alks-0.040
 robbers-0.039
Token to
Token ID284
Feature activation-3.22e-03

Pos logit contributions
aw+0.128
So+0.122
Ph+0.105
Alice+0.100
Deb+0.099
Neg logit contributions
arter-0.161
 robbers-0.149
alks-0.148
 robber-0.139
 pawn-0.135
Token replace
Token ID6330
Feature activation-3.68e-02

Pos logit contributions
So+0.005
+0.005
 together+0.005
 such+0.005
 about+0.005
Neg logit contributions
arter-0.006
 robber-0.006
 trigger-0.006
 pawn-0.005
 robbers-0.005
Token the
Token ID262
Feature activation+6.46e-03

Pos logit contributions
So+0.039
aw+0.034
Ph+0.033
Ab+0.031
+0.030
Neg logit contributions
arter-0.091
 robber-0.084
 trigger-0.083
 pawn-0.082
 tablet-0.081
Token old
Token ID1468
Feature activation+5.26e-02

Pos logit contributions
arter+0.014
 robber+0.012
 trigger+0.012
 pawn+0.011
 rook+0.011
Neg logit contributions
So-0.010
aw-0.010
 about-0.009
-0.009
 together-0.009
Token rug
Token ID14477
Feature activation-7.36e-03

Pos logit contributions
arter+0.083
 robber+0.075
 trigger+0.070
 pawn+0.066
 battlefield+0.063
Neg logit contributions
So-0.111
aw-0.109
-0.102
 about-0.101
 such-0.100
Token,
Token ID11
Feature activation-1.61e-02

Pos logit contributions
So+0.014
aw+0.012
Ab+0.011
Ph+0.011
uct+0.010
Neg logit contributions
 robber-0.024
arter-0.024
 robbers-0.023
 pawn-0.023
 rook-0.022
Token she
Token ID673
Feature activation-3.82e-02

Pos logit contributions
So+0.015
aw+0.014
Ph+0.012
Ab+0.012
 about+0.011
Neg logit contributions
arter-0.043
 robber-0.041
 pawn-0.039
 trigger-0.038
 robbers-0.038
Token would
Token ID561
Feature activation-1.54e-02

Pos logit contributions
So+0.037
aw+0.035
 about+0.031
+0.031
 together+0.030
Neg logit contributions
arter-0.104
 robber-0.098
 trigger-0.094
 pawn-0.091
 rook-0.089
Token bring
Token ID2222
Feature activation-1.65e-02

Pos logit contributions
So+0.020
+0.018
 about+0.018
aw+0.018
 together+0.018
Neg logit contributions
arter-0.037
 robber-0.034
 trigger-0.033
 pawn-0.032
 rook-0.031
Token a
Token ID257
Feature activation-1.38e-02

Pos logit contributions
So+0.015
aw+0.014
+0.012
Ab+0.012
 about+0.011
Neg logit contributions
arter-0.044
 robber-0.043
 trigger-0.040
 pawn-0.040
 rook-0.039
Token stool
Token ID38753
Feature activation-9.70e-02

Pos logit contributions
So+0.018
aw+0.017
+0.016
 about+0.016
 together+0.016
Neg logit contributions
arter-0.033
 robber-0.030
 trigger-0.029
 pawn-0.028
 battlefield-0.027
Token so
Token ID523
Feature activation+1.07e-04

Pos logit contributions
So+0.078
aw+0.072
Ab+0.062
Ph+0.058
+0.056
Neg logit contributions
arter-0.273
 robber-0.264
 trigger-0.250
 pawn-0.248
 rook-0.243
Token she
Token ID673
Feature activation-4.58e-02

Pos logit contributions
arter+0.000
 robber+0.000
 trigger+0.000
alks+0.000
 pawn+0.000
Neg logit contributions
So-0.000
aw-0.000
 such-0.000
Ph-0.000
's-0.000
Token could
Token ID714
Feature activation-1.05e-02

Pos logit contributions
So+0.051
aw+0.048
 about+0.043
Ab+0.042
 such+0.042
Neg logit contributions
arter-0.115
 robber-0.110
 trigger-0.105
 pawn-0.103
 rook-0.100
Token see
Token ID766
Feature activation+2.67e-03

Pos logit contributions
So+0.017
aw+0.016
+0.016
 about+0.016
 together+0.015
Neg logit contributions
arter-0.022
 robber-0.020
 trigger-0.019
 pawn-0.018
 battlefield-0.018
Token on
Token ID319
Feature activation-1.87e-02

Pos logit contributions
arter+0.006
 robber+0.006
 pawn+0.006
 trigger+0.006
 robbers+0.005
Neg logit contributions
So-0.003
Ph-0.002
Ab-0.002
aw-0.002
-0.002
Token,
Token ID11
Feature activation+9.69e-04

Pos logit contributions
arter+0.041
 robber+0.040
 trigger+0.037
 pawn+0.036
 robbers+0.036
Neg logit contributions
aw-0.029
So-0.027
Ph-0.026
Ab-0.025
It-0.023
Token Amy
Token ID14235
Feature activation-4.25e-02

Pos logit contributions
arter+0.002
 robber+0.002
 trigger+0.002
 pawn+0.002
 robbers+0.002
Neg logit contributions
aw-0.001
So-0.001
Ph-0.001
Ab-0.001
-0.001
Token got
Token ID1392
Feature activation-9.31e-03

Pos logit contributions
 such+0.053
So+0.051
Ph+0.051
aw+0.050
Ab+0.050
Neg logit contributions
 robber-0.086
arter-0.083
 pawn-0.081
 robbers-0.078
 trigger-0.078
Token a
Token ID257
Feature activation-1.54e-02

Pos logit contributions
So+0.012
aw+0.012
Ph+0.010
Alice+0.010
 about+0.010
Neg logit contributions
 robber-0.020
arter-0.020
 trigger-0.019
 robbers-0.019
 pawn-0.018
Token little
Token ID1310
Feature activation+1.66e-02

Pos logit contributions
So+0.027
aw+0.025
+0.025
 about+0.025
 together+0.024
Neg logit contributions
arter-0.030
 robber-0.027
 trigger-0.026
 pawn-0.024
 battlefield-0.024
Token stool
Token ID38753
Feature activation-8.85e-02

Pos logit contributions
arter+0.031
 robber+0.031
 trigger+0.029
 pawn+0.028
 robbers+0.027
Neg logit contributions
aw-0.027
So-0.027
Ab-0.025
 such-0.025
Ph-0.025
Token from
Token ID422
Feature activation-2.10e-02

Pos logit contributions
So+0.097
Ab+0.095
aw+0.095
Ph+0.089
 such+0.081
Neg logit contributions
arter-0.209
 robber-0.207
 trigger-0.197
 pawn-0.191
 rook-0.187
Token her
Token ID607
Feature activation-3.01e-02

Pos logit contributions
So+0.016
aw+0.015
+0.013
 about+0.012
 together+0.012
Neg logit contributions
arter-0.061
 robber-0.058
 trigger-0.056
 pawn-0.054
 battlefield-0.053
Token house
Token ID2156
Feature activation-2.56e-02

Pos logit contributions
So+0.054
aw+0.053
 about+0.049
+0.049
 together+0.049
Neg logit contributions
arter-0.057
 robber-0.052
 trigger-0.049
 pawn-0.047
 rook-0.046
Token and
Token ID290
Feature activation-8.37e-03

Pos logit contributions
So+0.025
aw+0.024
Ab+0.023
Ph+0.022
+0.020
Neg logit contributions
arter-0.066
 robber-0.063
 trigger-0.060
 pawn-0.059
 battlefield-0.058
Token put
Token ID1234
Feature activation-2.10e-02

Pos logit contributions
aw+0.013
So+0.013
Ph+0.012
Ab+0.011
 such+0.011
Neg logit contributions
 robber-0.015
 robbers-0.015
 pawn-0.015
arter-0.015
 trigger-0.014