TOP ACTIVATIONS
MAX = 0.107

sees aw , the merry - go - round . They
coaster , and the merry - go - round . He
's like a big merry - go - round !"
and play on the merry - go - round . The
and fast . The merry - go - round spins .
forgot about the broken merry - go - round .
the sandbox and the merry - go - round . They
can make our own merry - go - round ."
big fountain and the merry - go - round . Maybe
He would ride the merry - go - round and eat
and ran to the merry - go - round . They
. Lily saw a merry - go - round and asked
swing , and a merry - go - round . Lily
wanted to ride the merry - go - round . She
they got to the merry - go - round , they
" It 's a merry - go - round . It
they got on the merry - go - round and spun
followed them to the merry - go - round and the
ran back to the merry - go - round to show
and went on the merry - go - round . She

MIN ACTIVATIONS
MIN = -0.078

some cheese , tomato and lettuce inside . When the sandwich
ery and mixed it with lettuce and tomatoes .
. S ara spat out the grape and dropped
saw five fish and seven seaw eed . They were happy
her to fill it with lettuce . Lucy grabbed the lettuce
it in a bowl with lettuce , tomatoes , cheese and
. The bee asked the rad ish , " Will you
had meat and cheese and lettuce . He liked burger .
They went past rocks and seaw eed . They saw other
off in search of b unn ies . They found a
with cheese , tomatoes and lettuce . She put it inside
buckets and shovel s and seaw eed . Then we can
shore , collecting shells and seaw eed . Jimmy took time
and cheese and ham and lettuce at home . She says
. It has carrots and lettuce and tomatoes ."
had cheese and ham and lettuce . She did not like
has cheese and ham and lettuce . Tom is hungry .
ate it with shells and seaw eed . They find a
some shells and rocks and seaw eed . He picked them
she would buy carrots and lettuce to eat .

INTERVAL 0.061 - 0.107
CONTAINS 0.022%

a little girl named L yl a who was always looking
of the merry - go - round . He thought it
She loved to play hide - and - seek with her
the store with the ice - cream . He sat on
. It is the door bell . Mom my is home

INTERVAL 0.015 - 0.061
CONTAINS 10.597%

very excited because he had never been to a movie theater
but she could not get the tape off the roll .
sorry . He turns the truck around . He goes away
tried to get the doll back . They ran into the
at them . " Hello !" Anna says .

INTERVAL -0.032 - 0.015
CONTAINS 88.461%

house and loved it there . Every day , she would
tang y sensation in their mouths . They made funny faces
? Do you know how dangerous this is ? You could
looked like it was going to fall out of the sky
. He tried to rock the big rock . But the

INTERVAL -0.078 - -0.032
CONTAINS 0.920%

took a long time to cook the pizza . Finally ,
?" Lily said , " I 'm helping my mom my
She picked up the other oy ster and did the same
of hot water . She drank some of the water and
Jack , asked L izz ie to give him her stick
Token sees
Token ID7224
Feature activation+3.83e-02

Pos logit contributions
 ever+0.007
years+0.006
ad+0.006
rest+0.006
bridge+0.006
Neg logit contributions
-0.007
Charl-0.007
 stret-0.006
 ask-0.006
 fuss-0.006
Tokenaw
Token ID707
Feature activation+2.02e-02

Pos logit contributions
years+0.074
 ever+0.072
rest+0.068
ad+0.066
year+0.065
Neg logit contributions
-0.049
 insists-0.041
ealing-0.040
 ask-0.039
 swap-0.039
Token,
Token ID11
Feature activation+2.60e-05

Pos logit contributions
 ever+0.036
years+0.033
ad+0.032
bridge+0.032
rest+0.031
Neg logit contributions
-0.030
Charl-0.028
 ask-0.027
 stret-0.027
 insists-0.026
Token the
Token ID262
Feature activation+6.11e-03

Pos logit contributions
years+0.000
 ever+0.000
rest+0.000
year+0.000
lo+0.000
Neg logit contributions
 rinse-0.000
 ask-0.000
 swap-0.000
 fuss-0.000
-0.000
Token merry
Token ID44570
Feature activation+3.78e-02

Pos logit contributions
 ever+0.010
years+0.009
ad+0.009
rest+0.009
bridge+0.008
Neg logit contributions
-0.010
Charl-0.010
 stret-0.009
 ask-0.009
 insists-0.009
Token-
Token ID12
Feature activation+1.03e-01

Pos logit contributions
years+0.067
 ever+0.066
year+0.061
bridge+0.060
rest+0.059
Neg logit contributions
-0.058
 fuss-0.052
 stret-0.051
 ask-0.051
 difference-0.049
Tokengo
Token ID2188
Feature activation+5.38e-02

Pos logit contributions
years+0.171
ad+0.151
aces+0.141
 weeks+0.140
 days+0.139
Neg logit contributions
-0.150
 stret-0.147
arl-0.133
ealing-0.128
oodle-0.127
Token-
Token ID12
Feature activation+8.33e-02

Pos logit contributions
years+0.110
year+0.095
bridge+0.088
aces+0.087
rest+0.085
Neg logit contributions
-0.075
by-0.064
ealing-0.062
 fuss-0.062
 ask-0.061
Tokenround
Token ID744
Feature activation+8.61e-03

Pos logit contributions
years+0.196
 ever+0.178
ad+0.176
aces+0.173
bridge+0.172
Neg logit contributions
-0.078
 stret-0.066
 ask-0.053
Charl-0.051
 agree-0.050
Token.
Token ID13
Feature activation-2.16e-03

Pos logit contributions
years+0.017
 ever+0.016
year+0.015
bridge+0.015
rest+0.015
Neg logit contributions
-0.011
 ask-0.010
 swap-0.010
 rinse-0.010
 stret-0.009
Token They
Token ID1119
Feature activation-1.16e-02

Pos logit contributions
Charl+0.004
 stret+0.003
+0.003
heit+0.003
 fuss+0.003
Neg logit contributions
 ever-0.003
bridge-0.003
aces-0.003
 days-0.003
ad-0.003
Token coaster
Token ID42450
Feature activation+1.86e-02

Pos logit contributions
years+0.092
year+0.087
 ever+0.087
ions+0.078
rest+0.077
Neg logit contributions
-0.068
 stret-0.062
Charl-0.057
 ask-0.053
 insists-0.052
Token,
Token ID11
Feature activation+7.79e-03

Pos logit contributions
years+0.036
 ever+0.033
ad+0.033
bridge+0.032
year+0.032
Neg logit contributions
-0.023
 ask-0.021
Charl-0.021
 stret-0.021
 Benjamin-0.020
Token and
Token ID290
Feature activation+4.66e-03

Pos logit contributions
 ever+0.014
ad+0.014
years+0.014
bridge+0.013
rest+0.013
Neg logit contributions
-0.010
 ask-0.010
Charl-0.010
 stret-0.009
 insists-0.009
Token the
Token ID262
Feature activation+5.42e-04

Pos logit contributions
ad+0.007
 ever+0.007
years+0.007
aces+0.007
bridge+0.007
Neg logit contributions
-0.007
 ask-0.007
 Benjamin-0.007
Charl-0.007
 insists-0.007
Token merry
Token ID44570
Feature activation+4.18e-02

Pos logit contributions
 ever+0.001
ad+0.001
years+0.001
aces+0.001
bridge+0.001
Neg logit contributions
-0.001
Charl-0.001
 ask-0.001
 stret-0.001
 insists-0.001
Token-
Token ID12
Feature activation+1.01e-01

Pos logit contributions
years+0.066
 ever+0.064
year+0.060
ions+0.060
ad+0.058
Neg logit contributions
-0.071
 stret-0.064
 habit-0.064
 fuss-0.062
 ask-0.061
Tokengo
Token ID2188
Feature activation+5.76e-02

Pos logit contributions
lights+0.137
ad+0.136
years+0.136
 ever+0.136
 days+0.131
Neg logit contributions
-0.161
 stret-0.155
arl-0.142
ealing-0.142
 swap-0.141
Token-
Token ID12
Feature activation+8.36e-02

Pos logit contributions
years+0.107
year+0.093
lights+0.091
 crystals+0.091
ions+0.090
Neg logit contributions
-0.078
ealing-0.064
 stret-0.064
 swap-0.063
by-0.061
Tokenround
Token ID744
Feature activation+1.13e-02

Pos logit contributions
 ever+0.154
years+0.154
bridge+0.147
ad+0.146
lights+0.145
Neg logit contributions
-0.105
 stret-0.094
Charl-0.092
 ask-0.084
 swap-0.081
Token.
Token ID13
Feature activation+1.06e-03

Pos logit contributions
years+0.021
ad+0.019
year+0.019
 ever+0.019
bridge+0.019
Neg logit contributions
-0.015
 ask-0.013
 stret-0.013
 swap-0.013
 insists-0.012
Token He
Token ID679
Feature activation+2.44e-03

Pos logit contributions
 ever+0.002
ad+0.001
aces+0.001
bridge+0.001
 days+0.001
Neg logit contributions
Charl-0.002
-0.002
 stret-0.002
 fuss-0.002
 rinse-0.002
Token's
Token ID338
Feature activation-2.89e-03

Pos logit contributions
+0.003
Charl+0.003
 ask+0.003
 insists+0.003
 rinse+0.002
Neg logit contributions
 ever-0.005
years-0.005
ad-0.005
bridge-0.004
aces-0.004
Token like
Token ID588
Feature activation+2.83e-03

Pos logit contributions
+0.005
Charl+0.005
 stret+0.005
 ask+0.005
 insists+0.005
Neg logit contributions
 ever-0.004
ad-0.004
bridge-0.004
years-0.004
aces-0.004
Token a
Token ID257
Feature activation-1.43e-02

Pos logit contributions
ad+0.005
years+0.005
bridge+0.005
aces+0.005
 ever+0.005
Neg logit contributions
Charl-0.004
-0.004
 ask-0.004
 Midnight-0.004
 rinse-0.004
Token big
Token ID1263
Feature activation+2.93e-03

Pos logit contributions
ucker+0.025
Charl+0.024
ealing+0.024
uf+0.024
 Sonny+0.024
Neg logit contributions
 ever-0.024
 days-0.019
bridge-0.018
 next-0.017
te-0.016
Token merry
Token ID44570
Feature activation+4.64e-02

Pos logit contributions
 ever+0.005
 days+0.004
ad+0.004
bridge+0.004
aces+0.003
Neg logit contributions
Charl-0.005
ucker-0.005
 Sonny-0.005
itch-0.005
 Benjamin-0.005
Token-
Token ID12
Feature activation+9.95e-02

Pos logit contributions
 ever+0.064
years+0.057
ad+0.056
bridge+0.055
aces+0.054
Neg logit contributions
-0.088
Charl-0.085
 stret-0.081
 ask-0.080
 insists-0.079
Tokengo
Token ID2188
Feature activation+6.46e-02

Pos logit contributions
years+0.146
ad+0.134
aces+0.128
 ever+0.124
lights+0.115
Neg logit contributions
-0.178
 stret-0.155
Charl-0.152
 massage-0.144
 ask-0.138
Token-
Token ID12
Feature activation+8.29e-02

Pos logit contributions
years+0.132
aces+0.115
year+0.113
bridge+0.109
ad+0.107
Neg logit contributions
-0.098
 stret-0.072
 massage-0.070
!'"-0.069
 ask-0.068
Tokenround
Token ID744
Feature activation+1.57e-02

Pos logit contributions
years+0.169
 ever+0.164
ad+0.160
bridge+0.158
aces+0.157
Neg logit contributions
-0.100
Charl-0.089
 stret-0.082
 ask-0.072
 massage-0.070
Token!"
Token ID2474
Feature activation-1.85e-02

Pos logit contributions
years+0.031
ad+0.029
bridge+0.028
year+0.028
 ever+0.028
Neg logit contributions
-0.022
 ask-0.018
 insists-0.016
Charl-0.016
 stret-0.016
Token
Token ID220
Feature activation-7.18e-03

Pos logit contributions
Charl+0.025
die+0.024
 Sonny+0.024
Stan+0.024
 stret+0.023
Neg logit contributions
 ever-0.033
 days-0.031
aces-0.030
ad-0.029
bridge-0.028
Token and
Token ID290
Feature activation-2.75e-03

Pos logit contributions
years+0.015
 ever+0.014
year+0.014
rest+0.014
ad+0.013
Neg logit contributions
-0.009
Charl-0.008
 Midnight-0.008
 ask-0.007
 Woo-0.007
Token play
Token ID711
Feature activation+7.82e-03

Pos logit contributions
+0.003
 ask+0.003
Charl+0.003
 rinse+0.003
 stret+0.003
Neg logit contributions
 ever-0.006
years-0.005
bridge-0.005
ad-0.005
rest-0.005
Token on
Token ID319
Feature activation+2.40e-02

Pos logit contributions
 ever+0.012
years+0.011
ad+0.011
rest+0.010
bridge+0.010
Neg logit contributions
-0.014
Charl-0.013
 ask-0.013
 stret-0.013
 Midnight-0.012
Token the
Token ID262
Feature activation+1.86e-02

Pos logit contributions
years+0.046
year+0.044
 ever+0.044
bridge+0.043
rest+0.042
Neg logit contributions
-0.033
Charl-0.030
 ask-0.029
 massage-0.028
 Midnight-0.027
Token merry
Token ID44570
Feature activation+5.76e-02

Pos logit contributions
 ever+0.033
years+0.030
ad+0.030
bridge+0.030
aces+0.029
Neg logit contributions
-0.028
Charl-0.026
 stret-0.025
 ask-0.025
 insists-0.025
Token-
Token ID12
Feature activation+9.87e-02

Pos logit contributions
years+0.092
 ever+0.090
year+0.083
bridge+0.081
ad+0.081
Neg logit contributions
-0.099
 habit-0.089
 stret-0.087
 ask-0.087
 fuss-0.085
Tokengo
Token ID2188
Feature activation+6.20e-02

Pos logit contributions
years+0.146
 ever+0.133
ad+0.133
lights+0.128
ions+0.125
Neg logit contributions
-0.159
 stret-0.145
Charl-0.136
oodle-0.132
 ask-0.132
Token-
Token ID12
Feature activation+8.56e-02

Pos logit contributions
years+0.125
year+0.109
bridge+0.108
aces+0.103
ad+0.101
Neg logit contributions
-0.082
 ask-0.063
oodle-0.061
 lot-0.060
by-0.060
Tokenround
Token ID744
Feature activation+1.22e-02

Pos logit contributions
years+0.179
 ever+0.178
bridge+0.171
ad+0.169
aces+0.166
Neg logit contributions
-0.091
Charl-0.078
 stret-0.076
 ask-0.068
 agree-0.063
Token.
Token ID13
Feature activation-6.65e-03

Pos logit contributions
years+0.024
bridge+0.023
ad+0.023
 ever+0.022
year+0.022
Neg logit contributions
-0.016
 ask-0.013
 swap-0.012
 agree-0.012
 insists-0.012
Token The
Token ID383
Feature activation-4.91e-03

Pos logit contributions
 stret+0.010
Charl+0.009
 fuss+0.009
heit+0.009
 rinse+0.009
Neg logit contributions
 ever-0.012
 days-0.011
ad-0.011
aces-0.010
years-0.010
Token and
Token ID290
Feature activation+2.12e-02

Pos logit contributions
years+0.052
 ever+0.048
year+0.047
rest+0.046
ad+0.046
Neg logit contributions
-0.025
 stret-0.023
 insists-0.023
 ask-0.022
 fuss-0.022
Token fast
Token ID3049
Feature activation+1.54e-02

Pos logit contributions
 ever+0.039
ad+0.038
years+0.037
bridge+0.036
aces+0.036
Neg logit contributions
-0.029
 ask-0.027
 rinse-0.027
 fuss-0.026
 insists-0.026
Token.
Token ID13
Feature activation-9.23e-03

Pos logit contributions
 ever+0.025
years+0.023
ad+0.023
bridge+0.022
rest+0.022
Neg logit contributions
-0.025
Charl-0.024
 ask-0.023
 insists-0.023
 stret-0.023
Token The
Token ID383
Feature activation-1.69e-03

Pos logit contributions
+0.012
 ask+0.011
 Benjamin+0.011
Charl+0.011
 rinse+0.011
Neg logit contributions
 ever-0.018
rest-0.017
years-0.017
ad-0.016
bridge-0.016
Token merry
Token ID44570
Feature activation+3.82e-02

Pos logit contributions
Charl+0.003
+0.003
die+0.003
ucker+0.003
 ask+0.003
Neg logit contributions
 ever-0.003
ad-0.002
bridge-0.002
 days-0.002
years-0.002
Token-
Token ID12
Feature activation+9.87e-02

Pos logit contributions
 ever+0.062
years+0.060
year+0.055
bridge+0.055
ad+0.054
Neg logit contributions
-0.064
 ask-0.058
 stret-0.058
 fuss-0.057
 insists-0.056
Tokengo
Token ID2188
Feature activation+5.33e-02

Pos logit contributions
years+0.139
ad+0.138
 ever+0.129
 days+0.129
aces+0.129
Neg logit contributions
-0.165
 stret-0.160
ealing-0.142
arl-0.141
oodle-0.139
Token-
Token ID12
Feature activation+8.01e-02

Pos logit contributions
years+0.092
 ever+0.083
bridge+0.079
aces+0.078
year+0.078
Neg logit contributions
-0.088
 ask-0.075
 stret-0.073
 swap-0.072
 insists-0.072
Tokenround
Token ID744
Feature activation+1.27e-02

Pos logit contributions
years+0.171
 ever+0.165
ad+0.161
bridge+0.160
aces+0.158
Neg logit contributions
-0.087
 stret-0.077
Charl-0.073
 ask-0.064
arl-0.060
Token spins
Token ID37621
Feature activation+7.47e-03

Pos logit contributions
 ever+0.025
years+0.025
bridge+0.023
ad+0.023
year+0.023
Neg logit contributions
-0.016
 ask-0.015
 insists-0.014
 rinse-0.014
 swap-0.014
Token.
Token ID13
Feature activation-7.02e-03

Pos logit contributions
years+0.014
 ever+0.013
ad+0.013
bridge+0.013
rest+0.013
Neg logit contributions
-0.010
Charl-0.009
 stret-0.008
 Benjamin-0.008
 Woo-0.008
Token forgot
Token ID16453
Feature activation+1.86e-03

Pos logit contributions
+0.008
Charl+0.008
 ask+0.007
 rinse+0.007
 insists+0.007
Neg logit contributions
 ever-0.007
bridge-0.006
years-0.006
ad-0.006
aces-0.006
Token about
Token ID546
Feature activation-9.82e-04

Pos logit contributions
 ever+0.003
ad+0.003
bridge+0.003
years+0.002
aces+0.002
Neg logit contributions
-0.003
Charl-0.003
 stret-0.003
 ask-0.003
 insists-0.003
Token the
Token ID262
Feature activation+8.40e-03

Pos logit contributions
Charl+0.002
+0.002
 ask+0.002
 fuss+0.002
 Benjamin+0.002
Neg logit contributions
 ever-0.002
bridge-0.001
aces-0.001
years-0.001
ad-0.001
Token broken
Token ID5445
Feature activation+1.97e-02

Pos logit contributions
 ever+0.015
years+0.013
ad+0.013
bridge+0.013
aces+0.013
Neg logit contributions
-0.013
Charl-0.012
 stret-0.012
 ask-0.011
 insists-0.011
Token merry
Token ID44570
Feature activation+5.15e-02

Pos logit contributions
 ever+0.034
years+0.030
ad+0.030
bridge+0.030
aces+0.029
Neg logit contributions
-0.031
Charl-0.030
 stret-0.028
 ask-0.028
 insists-0.028
Token-
Token ID12
Feature activation+9.84e-02

Pos logit contributions
years+0.080
 ever+0.078
year+0.073
bridge+0.072
ad+0.070
Neg logit contributions
-0.090
 stret-0.084
Charl-0.081
 fuss-0.081
 ask-0.079
Tokengo
Token ID2188
Feature activation+6.21e-02

Pos logit contributions
years+0.155
ad+0.140
aces+0.139
 ever+0.138
 days+0.134
Neg logit contributions
 stret-0.154
-0.153
Charl-0.142
 ask-0.127
oodle-0.126
Token-
Token ID12
Feature activation+8.62e-02

Pos logit contributions
years+0.113
year+0.101
bridge+0.100
aces+0.097
 ever+0.097
Neg logit contributions
-0.092
 stret-0.085
 ask-0.076
 fuss-0.074
 swap-0.074
Tokenround
Token ID744
Feature activation+1.34e-02

Pos logit contributions
years+0.182
 ever+0.181
bridge+0.176
ad+0.172
aces+0.171
Neg logit contributions
-0.092
 stret-0.085
Charl-0.084
 ask-0.070
 Coc-0.067
Token.
Token ID13
Feature activation-7.91e-03

Pos logit contributions
years+0.027
bridge+0.025
ad+0.025
year+0.025
 ever+0.024
Neg logit contributions
-0.015
 stret-0.014
 ask-0.014
 agree-0.013
 swap-0.013
Token
Token ID198
Feature activation+1.46e-03

Pos logit contributions
 stret+0.012
Charl+0.012
+0.012
aman+0.011
 fuss+0.011
Neg logit contributions
 ever-0.014
ad-0.012
 days-0.012
aces-0.012
bridge-0.012
Token the
Token ID262
Feature activation+7.86e-03

Pos logit contributions
 ever+0.006
years+0.006
ad+0.006
rest+0.006
bridge+0.006
Neg logit contributions
-0.005
 ask-0.005
 stret-0.005
 rinse-0.005
Charl-0.005
Token sandbox
Token ID35204
Feature activation-1.23e-02

Pos logit contributions
 ever+0.014
ad+0.013
years+0.013
rest+0.013
bridge+0.013
Neg logit contributions
-0.011
Charl-0.011
 stret-0.010
 ask-0.010
 insists-0.010
Token and
Token ID290
Feature activation+5.15e-03

Pos logit contributions
+0.013
 ask+0.013
 insists+0.012
 rinse+0.012
 fuss+0.012
Neg logit contributions
years-0.026
rest-0.024
 ever-0.024
year-0.024
ad-0.023
Token the
Token ID262
Feature activation+7.92e-03

Pos logit contributions
 ever+0.008
years+0.007
ad+0.007
bridge+0.007
rest+0.007
Neg logit contributions
-0.009
 ask-0.008
Charl-0.008
 stret-0.008
 insists-0.008
Token merry
Token ID44570
Feature activation+3.72e-02

Pos logit contributions
 ever+0.014
ad+0.013
years+0.013
bridge+0.013
rest+0.013
Neg logit contributions
-0.011
Charl-0.011
 stret-0.010
 ask-0.010
 insists-0.010
Token-
Token ID12
Feature activation+9.81e-02

Pos logit contributions
years+0.059
 ever+0.058
ad+0.052
year+0.052
bridge+0.052
Neg logit contributions
-0.064
 fuss-0.058
 stret-0.057
 ask-0.056
 habit-0.055
Tokengo
Token ID2188
Feature activation+5.06e-02

Pos logit contributions
years+0.144
ad+0.144
 ever+0.136
 days+0.133
aces+0.132
Neg logit contributions
-0.151
 stret-0.149
arl-0.140
 swap-0.133
ealing-0.131
Token-
Token ID12
Feature activation+7.65e-02

Pos logit contributions
years+0.097
aces+0.083
bridge+0.083
year+0.082
ad+0.079
Neg logit contributions
-0.073
 stret-0.060
by-0.060
 ask-0.059
 fuss-0.059
Tokenround
Token ID744
Feature activation+4.91e-03

Pos logit contributions
years+0.166
 ever+0.162
ad+0.157
bridge+0.155
aces+0.154
Neg logit contributions
-0.080
 stret-0.067
Charl-0.062
 ask-0.058
arl-0.055
Token.
Token ID13
Feature activation-5.75e-04

Pos logit contributions
years+0.010
 ever+0.009
ad+0.009
bridge+0.009
year+0.009
Neg logit contributions
-0.006
 ask-0.006
 stret-0.006
 insists-0.005
 swap-0.005
Token They
Token ID1119
Feature activation-9.36e-03

Pos logit contributions
Charl+0.001
+0.001
die+0.001
 stret+0.001
ucker+0.001
Neg logit contributions
 ever-0.001
 days-0.001
bridge-0.001
aces-0.001
ad-0.001
Token can
Token ID460
Feature activation+1.08e-02

Pos logit contributions
Charl+0.030
+0.029
 stret+0.027
die+0.027
 Benjamin+0.027
Neg logit contributions
 ever-0.060
ad-0.052
bridge-0.051
aces-0.051
years-0.051
Token make
Token ID787
Feature activation+1.35e-02

Pos logit contributions
 ever+0.020
ad+0.018
bridge+0.017
aces+0.016
rest+0.016
Neg logit contributions
Charl-0.016
-0.015
 stret-0.014
die-0.014
 insists-0.014
Token our
Token ID674
Feature activation+8.21e-03

Pos logit contributions
 ever+0.020
ad+0.018
bridge+0.017
years+0.017
aces+0.017
Neg logit contributions
Charl-0.024
-0.024
 stret-0.022
 ask-0.021
 insists-0.021
Token own
Token ID898
Feature activation+2.37e-02

Pos logit contributions
 ever+0.015
bridge+0.014
years+0.014
ad+0.014
year+0.014
Neg logit contributions
-0.012
Charl-0.011
 fuss-0.011
 difference-0.010
 ask-0.010
Token merry
Token ID44570
Feature activation+5.00e-02

Pos logit contributions
 ever+0.042
ad+0.037
years+0.037
bridge+0.037
aces+0.036
Neg logit contributions
-0.036
Charl-0.035
 stret-0.033
 ask-0.032
 insists-0.032
Token-
Token ID12
Feature activation+9.78e-02

Pos logit contributions
 ever+0.076
years+0.072
ad+0.068
bridge+0.066
year+0.065
Neg logit contributions
-0.091
Charl-0.082
 stret-0.081
 ask-0.080
 fuss-0.079
Tokengo
Token ID2188
Feature activation+5.82e-02

Pos logit contributions
years+0.137
 ever+0.129
 days+0.125
aces+0.125
ad+0.122
Neg logit contributions
-0.171
 stret-0.159
Charl-0.145
 ask-0.139
oodle-0.137
Token-
Token ID12
Feature activation+8.57e-02

Pos logit contributions
years+0.098
year+0.089
 ever+0.087
bridge+0.086
ad+0.086
Neg logit contributions
-0.099
 stret-0.083
 ask-0.080
 fuss-0.076
 swap-0.075
Tokenround
Token ID744
Feature activation+8.77e-03

Pos logit contributions
years+0.171
 ever+0.170
aces+0.161
bridge+0.160
ad+0.160
Neg logit contributions
-0.103
 stret-0.089
Charl-0.084
 ask-0.078
arl-0.072
Token."
Token ID526
Feature activation-1.88e-02

Pos logit contributions
years+0.017
year+0.016
ad+0.016
 ever+0.016
bridge+0.015
Neg logit contributions
-0.012
 ask-0.010
 stret-0.010
 swap-0.009
 agree-0.009
Token
Token ID198
Feature activation-1.87e-03

Pos logit contributions
 stret+0.031
Charl+0.030
heit+0.029
die+0.028
uable+0.028
Neg logit contributions
 ever-0.031
ad-0.028
 days-0.026
aces-0.026
years-0.024
Token big
Token ID1263
Feature activation+1.08e-02

Pos logit contributions
 ever+0.033
years+0.030
ad+0.030
aces+0.030
bridge+0.029
Neg logit contributions
-0.028
Charl-0.026
 stret-0.025
 difference-0.025
 ask-0.025
Token fountain
Token ID29420
Feature activation+6.57e-03

Pos logit contributions
 ever+0.019
years+0.017
ad+0.017
bridge+0.017
aces+0.017
Neg logit contributions
-0.017
Charl-0.016
 ask-0.015
 stret-0.015
 fuss-0.015
Token and
Token ID290
Feature activation+9.37e-03

Pos logit contributions
years+0.012
ad+0.012
 ever+0.011
aces+0.011
bridge+0.011
Neg logit contributions
-0.010
 ask-0.008
 insists-0.008
 difference-0.008
 rinse-0.008
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
 ever+0.015
ad+0.014
aces+0.014
years+0.014
bridge+0.014
Neg logit contributions
-0.015
 ask-0.015
 rinse-0.014
Charl-0.014
 insists-0.013
Token merry
Token ID44570
Feature activation+3.96e-02

Pos logit contributions
 ever+0.022
ad+0.020
years+0.019
bridge+0.019
aces+0.019
Neg logit contributions
-0.020
Charl-0.019
 stret-0.018
 ask-0.018
 insists-0.018
Token-
Token ID12
Feature activation+9.67e-02

Pos logit contributions
years+0.064
 ever+0.063
ad+0.058
year+0.056
bridge+0.056
Neg logit contributions
-0.068
 fuss-0.060
 stret-0.059
 ask-0.059
 habit-0.057
Tokengo
Token ID2188
Feature activation+4.87e-02

Pos logit contributions
ad+0.142
aces+0.140
 days+0.135
years+0.135
 ever+0.129
Neg logit contributions
-0.155
 stret-0.144
arl-0.138
 Enjoy-0.129
oodle-0.129
Token-
Token ID12
Feature activation+7.57e-02

Pos logit contributions
years+0.085
aces+0.078
bridge+0.077
ad+0.075
 ever+0.073
Neg logit contributions
-0.081
 ask-0.065
ara-0.061
 fuss-0.061
 stret-0.061
Tokenround
Token ID744
Feature activation+5.98e-03

Pos logit contributions
 ever+0.166
years+0.164
aces+0.160
ad+0.159
bridge+0.157
Neg logit contributions
-0.078
 stret-0.063
Charl-0.060
 ask-0.057
arl-0.054
Token.
Token ID13
Feature activation-8.35e-03

Pos logit contributions
years+0.011
 ever+0.011
ad+0.011
bridge+0.011
aces+0.010
Neg logit contributions
-0.008
 ask-0.007
 insists-0.007
Charl-0.006
 stret-0.006
Token Maybe
Token ID6674
Feature activation-6.45e-04

Pos logit contributions
Charl+0.013
+0.012
 fuss+0.012
 stret+0.012
ucker+0.012
Neg logit contributions
 ever-0.014
bridge-0.013
ad-0.012
aces-0.012
years-0.012
Token He
Token ID679
Feature activation+9.04e-04

Pos logit contributions
 ever+0.007
ad+0.007
 days+0.006
bridge+0.006
aces+0.006
Neg logit contributions
Charl-0.010
-0.009
 stret-0.009
 rinse-0.009
heit-0.009
Token would
Token ID561
Feature activation+9.84e-03

Pos logit contributions
 ever+0.002
bridge+0.002
ad+0.002
aces+0.001
years+0.001
Neg logit contributions
-0.001
Charl-0.001
 ask-0.001
 insists-0.001
die-0.001
Token ride
Token ID6594
Feature activation+6.84e-03

Pos logit contributions
 ever+0.020
years+0.019
bridge+0.019
aces+0.019
rest+0.019
Neg logit contributions
-0.011
 ask-0.011
Charl-0.011
 rinse-0.010
 stret-0.010
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
bridge+0.011
 ever+0.011
aces+0.011
years+0.011
ad+0.011
Neg logit contributions
-0.011
 Benjamin-0.009
 ask-0.009
Charl-0.009
 Coc-0.009
Token merry
Token ID44570
Feature activation+5.34e-02

Pos logit contributions
 ever+0.045
ad+0.042
years+0.042
bridge+0.041
aces+0.040
Neg logit contributions
-0.038
Charl-0.036
 stret-0.033
 ask-0.033
 insists-0.033
Token-
Token ID12
Feature activation+9.65e-02

Pos logit contributions
years+0.094
year+0.087
 ever+0.085
ad+0.080
bridge+0.079
Neg logit contributions
-0.089
 habit-0.077
 stret-0.074
 fuss-0.074
 ask-0.073
Tokengo
Token ID2188
Feature activation+5.73e-02

Pos logit contributions
years+0.142
 ever+0.135
ad+0.135
 crystals+0.134
 days+0.132
Neg logit contributions
-0.146
 stret-0.136
 swap-0.124
ealing-0.120
arl-0.120
Token-
Token ID12
Feature activation+8.04e-02

Pos logit contributions
years+0.104
year+0.096
bridge+0.095
 ever+0.089
ad+0.089
Neg logit contributions
-0.084
 swap-0.067
 ask-0.066
by-0.064
ealing-0.064
Tokenround
Token ID744
Feature activation+1.22e-02

Pos logit contributions
 ever+0.176
years+0.174
bridge+0.170
ad+0.166
aces+0.165
Neg logit contributions
-0.078
Charl-0.066
 stret-0.063
 swap-0.055
 ask-0.054
Token and
Token ID290
Feature activation+1.09e-03

Pos logit contributions
years+0.022
 ever+0.022
bridge+0.022
ad+0.021
rest+0.021
Neg logit contributions
-0.017
 ask-0.015
Charl-0.014
 swap-0.014
 Benjamin-0.014
Token eat
Token ID4483
Feature activation-2.24e-02

Pos logit contributions
 ever+0.002
years+0.002
bridge+0.002
ad+0.002
aces+0.002
Neg logit contributions
-0.001
Charl-0.001
 ask-0.001
 Benjamin-0.001
 stret-0.001
Token and
Token ID290
Feature activation-1.73e-03

Pos logit contributions
+0.016
Charl+0.014
 Midnight+0.013
 stret+0.013
 ask+0.013
Neg logit contributions
 ever-0.022
years-0.021
bridge-0.021
ad-0.021
rest-0.020
Token ran
Token ID4966
Feature activation-1.99e-03

Pos logit contributions
+0.002
Charl+0.002
 ask+0.002
 stret+0.002
 rinse+0.002
Neg logit contributions
 ever-0.003
ad-0.003
years-0.003
bridge-0.003
rest-0.003
Token to
Token ID284
Feature activation-1.08e-02

Pos logit contributions
+0.004
Charl+0.003
 insists+0.003
 ask+0.003
 stret+0.003
Neg logit contributions
 ever-0.003
ad-0.003
bridge-0.003
years-0.003
aces-0.003
Token the
Token ID262
Feature activation+7.60e-03

Pos logit contributions
Charl+0.026
ucker+0.026
ealing+0.026
+0.026
die+0.025
Neg logit contributions
 ever-0.008
ad-0.006
 days-0.005
lo-0.005
years-0.004
Token merry
Token ID44570
Feature activation+4.70e-02

Pos logit contributions
 ever+0.012
 days+0.011
bridge+0.011
ad+0.011
 next+0.011
Neg logit contributions
ucker-0.012
-0.011
ealing-0.011
Charl-0.011
 insists-0.011
Token-
Token ID12
Feature activation+9.61e-02

Pos logit contributions
 ever+0.068
years+0.063
bridge+0.060
ad+0.059
year+0.057
Neg logit contributions
-0.087
Charl-0.082
 stret-0.082
 ask-0.079
 fuss-0.077
Tokengo
Token ID2188
Feature activation+5.25e-02

Pos logit contributions
 ever+0.149
ad+0.142
years+0.139
aces+0.131
 days+0.131
Neg logit contributions
 stret-0.156
-0.152
Charl-0.146
arl-0.141
 Midnight-0.131
Token-
Token ID12
Feature activation+7.99e-02

Pos logit contributions
years+0.087
 ever+0.084
bridge+0.081
aces+0.077
year+0.077
Neg logit contributions
-0.085
 stret-0.079
Charl-0.073
 ask-0.072
 swap-0.072
Tokenround
Token ID744
Feature activation+3.91e-03

Pos logit contributions
 ever+0.164
years+0.152
ad+0.150
bridge+0.150
aces+0.147
Neg logit contributions
-0.097
Charl-0.095
 stret-0.090
 ask-0.079
arl-0.077
Token.
Token ID13
Feature activation-2.33e-03

Pos logit contributions
 ever+0.007
years+0.007
bridge+0.007
ad+0.007
rest+0.006
Neg logit contributions
-0.005
 stret-0.005
 ask-0.005
Charl-0.005
 swap-0.005
Token They
Token ID1119
Feature activation-4.97e-03

Pos logit contributions
Charl+0.004
+0.004
 stret+0.004
 fuss+0.004
 difference+0.004
Neg logit contributions
 ever-0.004
ad-0.003
 days-0.003
bridge-0.003
aces-0.003
Token.
Token ID13
Feature activation-5.96e-04

Pos logit contributions
years+0.019
 ever+0.019
bridge+0.018
ad+0.018
rest+0.017
Neg logit contributions
-0.015
 ask-0.013
Charl-0.013
 stret-0.012
 Midnight-0.012
Token Lily
Token ID20037
Feature activation-8.49e-03

Pos logit contributions
Charl+0.001
heit+0.001
itch+0.001
 difference+0.001
 fuss+0.001
Neg logit contributions
 ever-0.001
 days-0.001
aces-0.001
bridge-0.001
 of-0.001
Token saw
Token ID2497
Feature activation+1.80e-02

Pos logit contributions
Charl+0.014
+0.014
arl+0.014
 stret+0.013
 difference+0.013
Neg logit contributions
 ever-0.013
years-0.011
ad-0.011
 days-0.011
aces-0.011
Token a
Token ID257
Feature activation-9.36e-03

Pos logit contributions
 ever+0.028
bridge+0.024
aces+0.024
ad+0.024
rest+0.023
Neg logit contributions
Charl-0.031
 Midnight-0.030
-0.029
 Woo-0.029
 Benjamin-0.028
Token merry
Token ID44570
Feature activation+4.97e-02

Pos logit contributions
 Deal+0.018
Charl+0.018
 insists+0.017
severe+0.017
itch+0.017
Neg logit contributions
 ever-0.012
bridge-0.009
 days-0.009
ad-0.008
lf-0.008
Token-
Token ID12
Feature activation+9.61e-02

Pos logit contributions
 ever+0.061
ad+0.052
bridge+0.051
 days+0.049
years+0.049
Neg logit contributions
Charl-0.101
-0.100
 insists-0.094
 Sonny-0.093
 Benjamin-0.093
Tokengo
Token ID2188
Feature activation+5.95e-02

Pos logit contributions
aces+0.126
 ever+0.122
 days+0.121
lights+0.119
years+0.118
Neg logit contributions
 stret-0.161
-0.157
Charl-0.152
 swap-0.142
 ask-0.140
Token-
Token ID12
Feature activation+8.06e-02

Pos logit contributions
aces+0.115
years+0.114
bridge+0.110
 ever+0.102
year+0.100
Neg logit contributions
-0.076
 stret-0.065
aa-0.060
oodle-0.060
 ask-0.060
Tokenround
Token ID744
Feature activation+1.58e-02

Pos logit contributions
 ever+0.164
years+0.158
aces+0.157
bridge+0.155
 days+0.154
Neg logit contributions
-0.090
Charl-0.086
 stret-0.082
 ask-0.072
 swap-0.069
Token and
Token ID290
Feature activation+2.85e-03

Pos logit contributions
years+0.030
 ever+0.030
bridge+0.029
year+0.028
rest+0.027
Neg logit contributions
-0.021
 ask-0.018
 stret-0.017
aman-0.017
 insists-0.017
Token asked
Token ID1965
Feature activation-7.55e-03

Pos logit contributions
 ever+0.004
ad+0.004
bridge+0.004
years+0.004
aces+0.004
Neg logit contributions
-0.005
Charl-0.005
 ask-0.004
 stret-0.004
 insists-0.004
Token swing
Token ID9628
Feature activation+3.37e-02

Pos logit contributions
Charl+0.009
uable+0.009
uf+0.009
itch+0.009
ucker+0.009
Neg logit contributions
 ever-0.007
bridge-0.007
 days-0.006
ad-0.006
 next-0.006
Token,
Token ID11
Feature activation+1.10e-02

Pos logit contributions
years+0.072
 ever+0.067
rest+0.065
year+0.064
ad+0.063
Neg logit contributions
-0.043
 ask-0.036
 insists-0.035
 swap-0.034
 stret-0.032
Token and
Token ID290
Feature activation+4.50e-03

Pos logit contributions
 ever+0.021
years+0.021
ad+0.020
rest+0.020
lo+0.020
Neg logit contributions
-0.014
 ask-0.014
 insists-0.013
 stret-0.013
Charl-0.012
Token a
Token ID257
Feature activation-9.11e-03

Pos logit contributions
ad+0.008
 ever+0.007
lo+0.007
rest+0.007
aces+0.007
Neg logit contributions
 ask-0.007
-0.006
 Benjamin-0.006
Charl-0.006
 Woo-0.006
Token merry
Token ID44570
Feature activation+4.21e-02

Pos logit contributions
Charl+0.015
uable+0.014
uf+0.014
 Benjamin+0.014
ucker+0.014
Neg logit contributions
 ever-0.014
bridge-0.013
 days-0.012
ad-0.011
iest-0.011
Token-
Token ID12
Feature activation+9.58e-02

Pos logit contributions
 ever+0.054
ad+0.046
bridge+0.046
 days+0.044
aces+0.044
Neg logit contributions
Charl-0.083
-0.082
 Sonny-0.077
 Benjamin-0.077
 insists-0.077
Tokengo
Token ID2188
Feature activation+5.17e-02

Pos logit contributions
years+0.133
ad+0.131
 ever+0.128
lights+0.124
 days+0.123
Neg logit contributions
-0.155
 stret-0.150
arl-0.137
 swap-0.135
 ask-0.134
Token-
Token ID12
Feature activation+7.61e-02

Pos logit contributions
years+0.100
bridge+0.090
aces+0.088
year+0.085
ad+0.084
Neg logit contributions
-0.075
 ask-0.060
oodle-0.058
 agree-0.057
ealing-0.056
Tokenround
Token ID744
Feature activation+7.59e-03

Pos logit contributions
years+0.154
 ever+0.153
ad+0.146
bridge+0.146
aces+0.145
Neg logit contributions
-0.087
 stret-0.074
Charl-0.070
 ask-0.069
 agree-0.064
Token.
Token ID13
Feature activation-5.76e-03

Pos logit contributions
years+0.015
 ever+0.014
bridge+0.014
ad+0.014
year+0.014
Neg logit contributions
-0.010
 ask-0.009
 insists-0.008
 stret-0.008
 swap-0.008
Token Lily
Token ID20037
Feature activation-6.24e-03

Pos logit contributions
Charl+0.011
heit+0.011
 stret+0.011
itch+0.011
uable+0.010
Neg logit contributions
 ever-0.006
 days-0.006
bridge-0.006
aces-0.005
lights-0.005
Token wanted
Token ID2227
Feature activation+4.29e-03

Pos logit contributions
Charl+0.011
+0.011
arl+0.011
 stret+0.011
 difference+0.011
Neg logit contributions
 ever-0.009
ad-0.008
aces-0.007
years-0.007
 days-0.007
Token to
Token ID284
Feature activation+4.59e-04

Pos logit contributions
bridge+0.008
years+0.008
 ever+0.008
aces+0.007
ad+0.007
Neg logit contributions
 ask-0.006
-0.005
Charl-0.005
 Woo-0.005
 Sonny-0.005
Token ride
Token ID6594
Feature activation+3.56e-03

Pos logit contributions
 ever+0.001
ad+0.001
bridge+0.001
years+0.001
aces+0.001
Neg logit contributions
-0.001
Charl-0.001
 ask-0.000
 stret-0.000
 insists-0.000
Token the
Token ID262
Feature activation+1.89e-02

Pos logit contributions
bridge+0.006
 ever+0.006
years+0.006
ad+0.005
year+0.005
Neg logit contributions
-0.006
 ask-0.005
Charl-0.005
 Woo-0.005
 Coc-0.005
Token merry
Token ID44570
Feature activation+5.39e-02

Pos logit contributions
 ever+0.035
ad+0.032
bridge+0.031
years+0.031
aces+0.030
Neg logit contributions
-0.027
Charl-0.026
 stret-0.024
 ask-0.024
 insists-0.024
Token-
Token ID12
Feature activation+9.56e-02

Pos logit contributions
years+0.093
year+0.084
 ever+0.084
bridge+0.080
ad+0.078
Neg logit contributions
-0.092
 stret-0.079
 ask-0.078
 habit-0.078
 fuss-0.078
Tokengo
Token ID2188
Feature activation+5.56e-02

Pos logit contributions
years+0.149
ad+0.136
lights+0.133
 ever+0.133
 days+0.132
Neg logit contributions
-0.146
 stret-0.131
oodle-0.129
arl-0.121
 ask-0.120
Token-
Token ID12
Feature activation+7.96e-02

Pos logit contributions
years+0.108
bridge+0.098
year+0.098
lights+0.089
ad+0.089
Neg logit contributions
-0.077
oodle-0.063
 ask-0.061
 swap-0.057
ealing-0.057
Tokenround
Token ID744
Feature activation+9.08e-03

Pos logit contributions
years+0.175
 ever+0.171
bridge+0.168
ad+0.164
 days+0.163
Neg logit contributions
-0.078
 stret-0.062
Charl-0.061
 ask-0.057
oodle-0.055
Token.
Token ID13
Feature activation-7.30e-03

Pos logit contributions
years+0.018
bridge+0.017
ad+0.017
year+0.017
 ever+0.017
Neg logit contributions
-0.012
 ask-0.010
 insists-0.010
 Benjamin-0.009
 swap-0.009
Token She
Token ID1375
Feature activation-2.95e-03

Pos logit contributions
 stret+0.015
Charl+0.013
 difference+0.013
heit+0.012
severe+0.012
Neg logit contributions
 ever-0.009
ad-0.008
 days-0.008
 next-0.008
aces-0.007
Token they
Token ID484
Feature activation+1.36e-02

Pos logit contributions
+0.024
Charl+0.023
 ask+0.022
 Benjamin+0.022
 Sonny+0.022
Neg logit contributions
 ever-0.027
ad-0.025
bridge-0.025
years-0.025
aces-0.024
Token got
Token ID1392
Feature activation+2.31e-03

Pos logit contributions
 ever+0.022
ad+0.019
years+0.019
bridge+0.018
rest+0.018
Neg logit contributions
Charl-0.023
-0.023
 stret-0.022
die-0.021
 difference-0.021
Token to
Token ID284
Feature activation+4.55e-03

Pos logit contributions
bridge+0.004
aces+0.004
ad+0.003
rest+0.003
 ever+0.003
Neg logit contributions
-0.004
 ask-0.004
Charl-0.004
 Benjamin-0.003
 Sonny-0.003
Token the
Token ID262
Feature activation+7.92e-03

Pos logit contributions
 ever+0.005
ad+0.004
 days+0.004
bridge+0.003
rest+0.003
Neg logit contributions
Charl-0.010
-0.010
ucker-0.010
arl-0.009
die-0.009
Token merry
Token ID44570
Feature activation+4.67e-02

Pos logit contributions
 ever+0.013
bridge+0.012
 days+0.011
ad+0.011
 next+0.011
Neg logit contributions
Charl-0.013
ucker-0.013
-0.012
ccoli-0.012
die-0.012
Token-
Token ID12
Feature activation+9.56e-02

Pos logit contributions
years+0.078
 ever+0.077
bridge+0.073
year+0.073
aces+0.069
Neg logit contributions
-0.075
 ask-0.069
 stret-0.067
 fuss-0.067
 habit-0.066
Tokengo
Token ID2188
Feature activation+5.63e-02

Pos logit contributions
years+0.132
 ever+0.129
aces+0.125
 days+0.123
ad+0.120
Neg logit contributions
-0.159
 stret-0.155
Charl-0.144
 ask-0.141
ealing-0.139
Token-
Token ID12
Feature activation+8.00e-02

Pos logit contributions
years+0.109
bridge+0.101
year+0.097
aces+0.097
 ever+0.096
Neg logit contributions
-0.075
 ask-0.064
ealing-0.061
 swap-0.059
by-0.059
Tokenround
Token ID744
Feature activation+1.36e-02

Pos logit contributions
 ever+0.169
years+0.167
bridge+0.162
aces+0.159
 days+0.157
Neg logit contributions
-0.085
Charl-0.076
 stret-0.075
 ask-0.069
oodle-0.062
Token,
Token ID11
Feature activation-1.52e-02

Pos logit contributions
 ever+0.028
years+0.027
bridge+0.026
ad+0.026
rest+0.026
Neg logit contributions
-0.017
 ask-0.015
 Benjamin-0.014
Charl-0.014
 insists-0.014
Token they
Token ID484
Feature activation-1.13e-03

Pos logit contributions
+0.019
 Benjamin+0.019
 ask+0.018
 Sonny+0.018
 rinse+0.017
Neg logit contributions
ad-0.029
 ever-0.029
years-0.028
bridge-0.028
aces-0.028
Token "
Token ID366
Feature activation+3.79e-03

Pos logit contributions
+0.008
Charl+0.008
 stret+0.007
 insists+0.007
 rinse+0.007
Neg logit contributions
 ever-0.015
ad-0.014
years-0.014
bridge-0.014
aces-0.013
TokenIt
Token ID1026
Feature activation-3.75e-03

Pos logit contributions
 ever+0.008
aces+0.008
 days+0.008
ad+0.008
bridge+0.007
Neg logit contributions
Charl-0.004
-0.004
 Sonny-0.003
 Benjamin-0.003
die-0.003
Token's
Token ID338
Feature activation-1.37e-02

Pos logit contributions
+0.005
Charl+0.005
 stret+0.005
 ask+0.005
 insists+0.005
Neg logit contributions
 ever-0.007
ad-0.006
bridge-0.006
years-0.006
aces-0.006
Token a
Token ID257
Feature activation-9.82e-03

Pos logit contributions
+0.027
Charl+0.027
 ask+0.025
 stret+0.025
 insists+0.025
Neg logit contributions
 ever-0.018
ad-0.015
bridge-0.015
years-0.015
aces-0.014
Token merry
Token ID44570
Feature activation+4.22e-02

Pos logit contributions
ucker+0.017
Charl+0.016
+0.016
arl+0.016
 insists+0.016
Neg logit contributions
 ever-0.016
 days-0.013
ad-0.013
bridge-0.012
years-0.012
Token-
Token ID12
Feature activation+9.46e-02

Pos logit contributions
 ever+0.065
years+0.058
ad+0.057
bridge+0.057
aces+0.056
Neg logit contributions
-0.073
Charl-0.070
 stret-0.067
 ask-0.066
 insists-0.065
Tokengo
Token ID2188
Feature activation+5.51e-02

Pos logit contributions
lights+0.140
years+0.132
 days+0.131
aces+0.130
ad+0.128
Neg logit contributions
-0.147
 ask-0.131
 stret-0.129
ealing-0.129
Charl-0.127
Token-
Token ID12
Feature activation+7.96e-02

Pos logit contributions
years+0.099
aces+0.088
bridge+0.085
year+0.084
lights+0.083
Neg logit contributions
-0.086
 ask-0.072
 promise-0.069
 stret-0.068
ealing-0.068
Tokenround
Token ID744
Feature activation+1.22e-02

Pos logit contributions
years+0.140
 ever+0.138
bridge+0.138
lights+0.134
aces+0.133
Neg logit contributions
-0.110
Charl-0.097
 stret-0.092
 ask-0.091
 swap-0.084
Token.
Token ID13
Feature activation-6.58e-03

Pos logit contributions
years+0.022
 ever+0.021
ad+0.021
bridge+0.021
 days+0.020
Neg logit contributions
-0.017
 ask-0.015
 insists-0.014
 Benjamin-0.014
 swap-0.014
Token It
Token ID632
Feature activation-1.46e-04

Pos logit contributions
+0.009
Charl+0.009
 ask+0.008
 stret+0.008
 insists+0.008
Neg logit contributions
 ever-0.012
ad-0.011
bridge-0.011
years-0.011
aces-0.011
Token they
Token ID484
Feature activation+3.16e-03

Pos logit contributions
 ever+0.002
ad+0.001
 days+0.001
years+0.001
bridge+0.001
Neg logit contributions
Charl-0.002
-0.001
 stret-0.001
 insists-0.001
die-0.001
Token got
Token ID1392
Feature activation-2.52e-03

Pos logit contributions
 ever+0.005
bridge+0.005
ad+0.005
years+0.005
rest+0.005
Neg logit contributions
-0.005
Charl-0.005
 ask-0.005
 rinse-0.005
 insists-0.004
Token on
Token ID319
Feature activation+1.87e-02

Pos logit contributions
+0.004
Charl+0.004
 ask+0.004
 rinse+0.004
 Benjamin+0.003
Neg logit contributions
 ever-0.004
bridge-0.004
ad-0.004
aces-0.004
years-0.004
Token the
Token ID262
Feature activation+2.02e-02

Pos logit contributions
 ever+0.031
bridge+0.029
aces+0.028
years+0.028
rest+0.028
Neg logit contributions
-0.030
Charl-0.030
 stret-0.028
 ask-0.027
 Benjamin-0.027
Token merry
Token ID44570
Feature activation+5.52e-02

Pos logit contributions
 ever+0.034
ad+0.031
years+0.030
bridge+0.030
aces+0.029
Neg logit contributions
-0.032
Charl-0.031
 stret-0.029
 ask-0.029
 insists-0.029
Token-
Token ID12
Feature activation+9.44e-02

Pos logit contributions
years+0.091
 ever+0.088
year+0.084
bridge+0.082
ad+0.076
Neg logit contributions
-0.092
 stret-0.086
 habit-0.083
 ask-0.082
 fuss-0.081
Tokengo
Token ID2188
Feature activation+6.00e-02

Pos logit contributions
years+0.141
 ever+0.127
aces+0.127
ad+0.126
 crystals+0.124
Neg logit contributions
-0.149
 stret-0.145
Charl-0.132
aa-0.125
 ask-0.124
Token-
Token ID12
Feature activation+8.15e-02

Pos logit contributions
years+0.115
year+0.106
bridge+0.103
aces+0.099
 ever+0.097
Neg logit contributions
-0.084
 stret-0.074
 ask-0.069
 agree-0.068
aa-0.065
Tokenround
Token ID744
Feature activation+6.95e-03

Pos logit contributions
years+0.176
 ever+0.174
bridge+0.171
aces+0.166
ad+0.164
Neg logit contributions
-0.082
 stret-0.073
Charl-0.071
 ask-0.060
 agree-0.055
Token and
Token ID290
Feature activation+3.89e-03

Pos logit contributions
years+0.013
bridge+0.013
 ever+0.013
rest+0.012
year+0.012
Neg logit contributions
-0.009
 ask-0.008
 stret-0.008
 agree-0.008
 insists-0.008
Token spun
Token ID26843
Feature activation+3.45e-03

Pos logit contributions
 ever+0.006
ad+0.006
years+0.006
bridge+0.006
aces+0.006
Neg logit contributions
-0.006
Charl-0.006
 ask-0.006
 rinse-0.005
 Benjamin-0.005
Token followed
Token ID3940
Feature activation+8.97e-03

Pos logit contributions
 ever+0.004
bridge+0.004
ad+0.004
years+0.004
aces+0.004
Neg logit contributions
-0.003
Charl-0.003
 ask-0.003
 insists-0.003
 stret-0.003
Token them
Token ID606
Feature activation+1.35e-02

Pos logit contributions
bridge+0.019
aces+0.019
 ever+0.018
rest+0.018
years+0.017
Neg logit contributions
 ask-0.010
 Midnight-0.009
 Benjamin-0.009
-0.009
 Lucky-0.009
Token to
Token ID284
Feature activation-1.55e-02

Pos logit contributions
 ever+0.022
bridge+0.020
ad+0.020
years+0.020
aces+0.019
Neg logit contributions
-0.022
Charl-0.021
 ask-0.020
 stret-0.020
 insists-0.020
Token the
Token ID262
Feature activation-2.72e-03

Pos logit contributions
+0.028
Charl+0.027
 ask+0.027
 stret+0.026
 Benjamin+0.026
Neg logit contributions
 ever-0.023
bridge-0.020
aces-0.020
years-0.020
ad-0.019
Token merry
Token ID44570
Feature activation+4.66e-02

Pos logit contributions
Charl+0.004
+0.004
die+0.004
ucker+0.004
ccoli+0.004
Neg logit contributions
 ever-0.005
 days-0.004
bridge-0.004
ad-0.004
rest-0.004
Token-
Token ID12
Feature activation+9.35e-02

Pos logit contributions
 ever+0.069
years+0.068
bridge+0.065
year+0.062
ad+0.062
Neg logit contributions
-0.083
 stret-0.075
 ask-0.075
Charl-0.074
 fuss-0.074
Tokengo
Token ID2188
Feature activation+5.57e-02

Pos logit contributions
years+0.135
aces+0.128
ad+0.126
 ever+0.125
bridge+0.125
Neg logit contributions
-0.153
 stret-0.142
Charl-0.132
 ask-0.132
arl-0.131
Token-
Token ID12
Feature activation+8.29e-02

Pos logit contributions
years+0.104
bridge+0.097
year+0.092
aces+0.091
ad+0.087
Neg logit contributions
-0.080
 ask-0.067
 stret-0.066
 swap-0.064
 agree-0.064
Tokenround
Token ID744
Feature activation+1.17e-02

Pos logit contributions
 ever+0.173
years+0.172
bridge+0.170
aces+0.166
ad+0.164
Neg logit contributions
-0.090
Charl-0.078
 stret-0.076
 ask-0.071
 swap-0.066
Token and
Token ID290
Feature activation+2.93e-03

Pos logit contributions
years+0.022
 ever+0.021
bridge+0.021
ad+0.021
rest+0.020
Neg logit contributions
-0.015
 ask-0.014
 agree-0.013
 stret-0.013
 swap-0.013
Token the
Token ID262
Feature activation+7.48e-03

Pos logit contributions
 ever+0.005
ad+0.005
bridge+0.005
years+0.005
aces+0.005
Neg logit contributions
-0.004
Charl-0.004
 ask-0.004
 stret-0.004
 insists-0.004
Token ran
Token ID4966
Feature activation-2.57e-03

Pos logit contributions
 ever+0.032
ad+0.028
bridge+0.028
years+0.028
aces+0.027
Neg logit contributions
-0.028
Charl-0.027
 ask-0.026
 stret-0.025
 insists-0.025
Token back
Token ID736
Feature activation+6.24e-03

Pos logit contributions
+0.004
Charl+0.004
 ask+0.004
 stret+0.004
 Benjamin+0.004
Neg logit contributions
 ever-0.004
ad-0.004
bridge-0.004
years-0.004
aces-0.004
Token to
Token ID284
Feature activation-1.79e-02

Pos logit contributions
 ever+0.011
bridge+0.011
ad+0.010
years+0.010
aces+0.010
Neg logit contributions
-0.009
Charl-0.009
 ask-0.008
 stret-0.008
 insists-0.008
Token the
Token ID262
Feature activation+2.56e-05

Pos logit contributions
Charl+0.041
+0.040
ucker+0.040
die+0.039
ealing+0.039
Neg logit contributions
 ever-0.019
ad-0.016
 days-0.013
years-0.013
rest-0.012
Token merry
Token ID44570
Feature activation+4.28e-02

Pos logit contributions
 ever+0.000
 days+0.000
bridge+0.000
ad+0.000
 next+0.000
Neg logit contributions
Charl-0.000
-0.000
ucker-0.000
ccoli-0.000
die-0.000
Token-
Token ID12
Feature activation+9.34e-02

Pos logit contributions
 ever+0.063
years+0.059
bridge+0.056
ad+0.055
aces+0.055
Neg logit contributions
-0.078
Charl-0.072
 stret-0.072
 ask-0.070
 fuss-0.069
Tokengo
Token ID2188
Feature activation+5.24e-02

Pos logit contributions
lights+0.124
aces+0.123
 days+0.122
 ever+0.121
ad+0.118
Neg logit contributions
-0.157
 swap-0.141
 stret-0.140
 Enjoy-0.138
Sure-0.136
Token-
Token ID12
Feature activation+7.68e-02

Pos logit contributions
years+0.094
aces+0.087
bridge+0.087
 ever+0.085
year+0.083
Neg logit contributions
-0.076
 swap-0.065
 stret-0.062
oodle-0.062
ara-0.061
Tokenround
Token ID744
Feature activation+1.93e-03

Pos logit contributions
 ever+0.160
bridge+0.152
years+0.152
aces+0.151
 days+0.148
Neg logit contributions
-0.087
Charl-0.079
 stret-0.072
 ask-0.068
 swap-0.066
Token to
Token ID284
Feature activation-2.29e-03

Pos logit contributions
 ever+0.003
years+0.003
bridge+0.003
ad+0.003
rest+0.003
Neg logit contributions
-0.003
Charl-0.002
 ask-0.002
 stret-0.002
 Benjamin-0.002
Token show
Token ID905
Feature activation-4.11e-03

Pos logit contributions
Charl+0.003
+0.003
die+0.003
 stret+0.003
ucker+0.003
Neg logit contributions
 ever-0.005
ad-0.004
bridge-0.004
years-0.004
rest-0.004
Token and
Token ID290
Feature activation+3.17e-03

Pos logit contributions
bridge+0.009
lo+0.009
rest+0.009
years+0.009
aces+0.008
Neg logit contributions
 ask-0.006
 agree-0.005
-0.005
 swap-0.005
 habit-0.005
Token went
Token ID1816
Feature activation-2.72e-03

Pos logit contributions
 ever+0.006
ad+0.005
years+0.005
bridge+0.005
aces+0.005
Neg logit contributions
-0.005
Charl-0.005
 stret-0.004
 insists-0.004
die-0.004
Token on
Token ID319
Feature activation+1.67e-02

Pos logit contributions
+0.005
Charl+0.005
 stret+0.005
 insists+0.005
 Sonny+0.005
Neg logit contributions
 ever-0.004
ad-0.003
bridge-0.003
years-0.003
aces-0.003
Token the
Token ID262
Feature activation+1.31e-02

Pos logit contributions
bridge+0.027
 ever+0.025
aces+0.025
rest+0.025
years+0.024
Neg logit contributions
Charl-0.028
-0.028
 Benjamin-0.025
 ask-0.025
 Woo-0.025
Token merry
Token ID44570
Feature activation+5.45e-02

Pos logit contributions
 ever+0.025
years+0.023
ad+0.023
bridge+0.023
aces+0.023
Neg logit contributions
-0.018
Charl-0.017
 stret-0.016
 ask-0.016
 insists-0.015
Token-
Token ID12
Feature activation+9.29e-02

Pos logit contributions
years+0.087
 ever+0.086
year+0.080
bridge+0.080
ad+0.077
Neg logit contributions
-0.092
 stret-0.082
 habit-0.082
 ask-0.082
 fuss-0.081
Tokengo
Token ID2188
Feature activation+5.65e-02

Pos logit contributions
aces+0.126
years+0.123
 ever+0.121
lights+0.119
 days+0.118
Neg logit contributions
-0.146
 stret-0.137
 swap-0.134
Charl-0.134
oodle-0.128
Token-
Token ID12
Feature activation+8.11e-02

Pos logit contributions
years+0.106
bridge+0.102
aces+0.101
year+0.095
 ever+0.093
Neg logit contributions
-0.071
 swap-0.064
 ask-0.062
oodle-0.061
ara-0.060
Tokenround
Token ID744
Feature activation+8.22e-03

Pos logit contributions
 ever+0.167
bridge+0.163
years+0.162
aces+0.162
 days+0.157
Neg logit contributions
-0.085
Charl-0.078
 stret-0.074
 ask-0.069
 swap-0.069
Token.
Token ID13
Feature activation-2.56e-03

Pos logit contributions
years+0.015
 ever+0.015
bridge+0.015
ad+0.015
rest+0.014
Neg logit contributions
-0.011
 ask-0.010
 stret-0.009
 swap-0.009
 agree-0.009
Token She
Token ID1375
Feature activation-5.36e-03

Pos logit contributions
Charl+0.005
+0.004
die+0.004
 stret+0.004
ucker+0.004
Neg logit contributions
 ever-0.004
aces-0.003
ad-0.003
years-0.003
bridge-0.003
Token some
Token ID617
Feature activation+1.12e-02

Pos logit contributions
+0.031
Charl+0.029
 Benjamin+0.029
 Midnight+0.029
 Sonny+0.028
Neg logit contributions
 ever-0.028
ad-0.024
years-0.024
bridge-0.024
rest-0.023
Token cheese
Token ID9891
Feature activation-2.56e-02

Pos logit contributions
 ever+0.021
years+0.020
ad+0.019
bridge+0.019
rest+0.019
Neg logit contributions
-0.015
Charl-0.014
 rinse-0.014
 ask-0.013
 stret-0.013
Token,
Token ID11
Feature activation-1.51e-02

Pos logit contributions
+0.043
Charl+0.040
 Midnight+0.040
die+0.039
 rinse+0.039
Neg logit contributions
years-0.037
 ever-0.036
ad-0.035
rest-0.034
bridge-0.033
Token tomato
Token ID24240
Feature activation-3.26e-02

Pos logit contributions
+0.018
 ask+0.017
 rinse+0.017
 Midnight+0.016
 Benjamin+0.016
Neg logit contributions
 ever-0.031
lo-0.029
ad-0.029
rest-0.029
years-0.029
Token and
Token ID290
Feature activation-4.64e-03

Pos logit contributions
+0.045
Charl+0.042
 Midnight+0.041
 ask+0.040
die+0.040
Neg logit contributions
 ever-0.058
years-0.056
ad-0.055
rest-0.054
bridge-0.053
Token lettuce
Token ID39406
Feature activation-6.91e-02

Pos logit contributions
+0.007
 ask+0.006
Charl+0.006
 rinse+0.006
 Benjamin+0.006
Neg logit contributions
 ever-0.008
ad-0.008
rest-0.008
years-0.008
lo-0.008
Token inside
Token ID2641
Feature activation-2.70e-02

Pos logit contributions
+0.099
Charl+0.092
 ask+0.090
 rinse+0.087
 Sonny+0.087
Neg logit contributions
 ever-0.120
years-0.116
ad-0.114
bridge-0.112
rest-0.109
Token.
Token ID13
Feature activation-1.65e-03

Pos logit contributions
+0.038
 ask+0.035
 rinse+0.032
 difference+0.032
 Benjamin+0.032
Neg logit contributions
years-0.047
 ever-0.047
aces-0.046
bridge-0.046
rest-0.045
Token When
Token ID1649
Feature activation-9.28e-03

Pos logit contributions
+0.003
Charl+0.003
 stret+0.003
 fuss+0.002
 difference+0.002
Neg logit contributions
 ever-0.003
ad-0.002
aces-0.002
years-0.002
bridge-0.002
Token the
Token ID262
Feature activation-6.39e-03

Pos logit contributions
+0.014
Charl+0.013
 Benjamin+0.013
 Midnight+0.013
 ask+0.013
Neg logit contributions
aces-0.016
 ever-0.016
years-0.015
bridge-0.015
rest-0.015
Token sandwich
Token ID20433
Feature activation-2.34e-02

Pos logit contributions
+0.007
 ask+0.006
Charl+0.006
 Benjamin+0.006
die+0.006
Neg logit contributions
 ever-0.014
years-0.013
ad-0.013
rest-0.013
aces-0.013
Tokenery
Token ID1924
Feature activation-4.55e-02

Pos logit contributions
+0.032
Charl+0.032
 stret+0.030
 ask+0.029
 insists+0.029
Neg logit contributions
 ever-0.028
ad-0.025
bridge-0.025
years-0.024
aces-0.024
Token and
Token ID290
Feature activation-4.57e-03

Pos logit contributions
+0.074
Charl+0.070
 ask+0.067
 rinse+0.066
 insists+0.065
Neg logit contributions
 ever-0.073
years-0.068
ad-0.068
bridge-0.067
rest-0.065
Token mixed
Token ID7668
Feature activation-1.73e-02

Pos logit contributions
+0.007
 ask+0.007
Charl+0.007
 rinse+0.006
 Sonny+0.006
Neg logit contributions
 ever-0.008
ad-0.007
years-0.007
bridge-0.007
aces-0.007
Token it
Token ID340
Feature activation-1.18e-02

Pos logit contributions
Charl+0.033
+0.031
 stret+0.030
 insists+0.029
 ask+0.029
Neg logit contributions
 ever-0.025
ad-0.022
 days-0.021
bridge-0.021
aces-0.020
Token with
Token ID351
Feature activation-7.07e-03

Pos logit contributions
+0.019
 rinse+0.017
 ask+0.017
Charl+0.017
die+0.016
Neg logit contributions
years-0.019
bridge-0.018
ad-0.018
 ever-0.018
rest-0.017
Token lettuce
Token ID39406
Feature activation-6.84e-02

Pos logit contributions
+0.011
Charl+0.011
 ask+0.010
 rinse+0.010
 stret+0.010
Neg logit contributions
 ever-0.012
ad-0.011
bridge-0.011
years-0.011
aces-0.010
Token and
Token ID290
Feature activation-3.89e-03

Pos logit contributions
Charl+0.126
+0.124
 stret+0.117
 insists+0.114
 Benjamin+0.113
Neg logit contributions
 ever-0.102
aces-0.085
ad-0.084
bridge-0.083
 days-0.082
Token tomatoes
Token ID23972
Feature activation-3.62e-02

Pos logit contributions
+0.005
Charl+0.005
 ask+0.005
 stret+0.004
 insists+0.004
Neg logit contributions
 ever-0.008
ad-0.007
bridge-0.007
years-0.007
aces-0.007
Token.
Token ID13
Feature activation-6.66e-03

Pos logit contributions
+0.058
Charl+0.056
 ask+0.053
 rinse+0.053
 stret+0.052
Neg logit contributions
 ever-0.057
years-0.054
ad-0.053
bridge-0.052
rest-0.051
Token
Token ID198
Feature activation-2.00e-03

Pos logit contributions
Charl+0.012
 stret+0.012
heit+0.011
itch+0.011
uf+0.011
Neg logit contributions
 ever-0.008
 days-0.008
 of-0.007
 next-0.007
we-0.007
Token
Token ID198
Feature activation+2.76e-03

Pos logit contributions
Charl+0.003
 stret+0.003
ccoli+0.003
 insists+0.003
ealing+0.003
Neg logit contributions
 ever-0.003
 of-0.003
ad-0.003
 days-0.003
lo-0.003
Token.
Token ID13
Feature activation+4.55e-03

Pos logit contributions
 ever+0.010
years+0.010
bridge+0.010
ad+0.010
rest+0.009
Neg logit contributions
-0.008
Charl-0.008
 stret-0.008
 ask-0.007
 rinse-0.007
Token
Token ID198
Feature activation+3.77e-03

Pos logit contributions
 ever+0.007
ad+0.006
aces+0.005
 days+0.005
bridge+0.005
Neg logit contributions
 difference-0.008
Charl-0.008
-0.008
heit-0.008
 promise-0.008
Token
Token ID198
Feature activation-7.97e-04

Pos logit contributions
 ever+0.005
ad+0.005
 of+0.004
lo+0.004
 himself+0.004
Neg logit contributions
Charl-0.007
 habit-0.007
 difference-0.007
 stret-0.007
aman-0.007
TokenS
Token ID50
Feature activation-2.73e-03

Pos logit contributions
 difference+0.001
Charl+0.001
+0.001
 habit+0.001
uable+0.001
Neg logit contributions
 ever-0.001
ad-0.001
bridge-0.001
 days-0.001
 next-0.001
Tokenara
Token ID3301
Feature activation+1.48e-02

Pos logit contributions
Charl+0.002
 stret+0.002
+0.002
die+0.001
 Sonny+0.001
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.006
aces-0.006
 days-0.006
Token spat
Token ID15246
Feature activation-6.84e-02

Pos logit contributions
 ever+0.023
ad+0.020
bridge+0.019
years+0.019
aces+0.019
Neg logit contributions
Charl-0.026
-0.026
 stret-0.024
 ask-0.024
 Sonny-0.024
Token out
Token ID503
Feature activation-1.31e-02

Pos logit contributions
Charl+0.129
 difference+0.129
die+0.124
 compromise+0.119
ucker+0.117
Neg logit contributions
 ever-0.101
ad-0.082
 himself-0.077
aces-0.074
ily-0.074
Token the
Token ID262
Feature activation+1.39e-03

Pos logit contributions
+0.028
Charl+0.027
 stret+0.025
 insists+0.025
ucker+0.025
Neg logit contributions
 ever-0.016
ad-0.014
years-0.013
bridge-0.012
 days-0.012
Token grape
Token ID30777
Feature activation-1.70e-02

Pos logit contributions
 ever+0.002
ad+0.002
aces+0.002
bridge+0.002
rest+0.002
Neg logit contributions
Charl-0.002
-0.002
 stret-0.002
 Sonny-0.002
die-0.002
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
+0.029
Charl+0.029
 stret+0.027
 ask+0.027
 insists+0.027
Neg logit contributions
 ever-0.026
ad-0.023
bridge-0.022
years-0.022
aces-0.022
Token dropped
Token ID5710
Feature activation-3.13e-02

Pos logit contributions
Charl+0.026
arl+0.026
ench+0.025
 difference+0.025
+0.025
Neg logit contributions
 ever-0.021
ad-0.018
bridge-0.016
 days-0.016
aces-0.016
Token saw
Token ID2497
Feature activation+3.58e-03

Pos logit contributions
+0.015
 ask+0.014
 agree+0.013
 rinse+0.013
 insists+0.013
Neg logit contributions
 ever-0.014
years-0.014
 days-0.014
ad-0.014
rest-0.013
Token five
Token ID1936
Feature activation+2.89e-02

Pos logit contributions
 ever+0.006
years+0.005
ad+0.005
bridge+0.005
aces+0.005
Neg logit contributions
-0.006
 ask-0.005
Charl-0.005
 insists-0.005
 Benjamin-0.005
Token fish
Token ID5916
Feature activation-2.88e-02

Pos logit contributions
years+0.048
 ever+0.047
rest+0.047
year+0.046
ad+0.045
Neg logit contributions
-0.042
 fuss-0.039
 difference-0.038
 ask-0.037
 insists-0.037
Token and
Token ID290
Feature activation-4.15e-03

Pos logit contributions
+0.041
 ask+0.039
 insists+0.037
Charl+0.037
 rinse+0.037
Neg logit contributions
years-0.047
 ever-0.047
bridge-0.045
ad-0.045
aces-0.045
Token seven
Token ID3598
Feature activation+3.49e-02

Pos logit contributions
 ask+0.006
+0.006
 rinse+0.005
 Benjamin+0.005
 swap+0.005
Neg logit contributions
rest-0.007
 ever-0.007
lo-0.007
years-0.007
aces-0.007
Token seaw
Token ID32085
Feature activation-6.79e-02

Pos logit contributions
rest+0.062
 ever+0.060
year+0.059
bridge+0.059
years+0.058
Neg logit contributions
-0.050
 ask-0.045
 insists-0.044
ealing-0.043
 fuss-0.043
Tokeneed
Token ID2308
Feature activation-3.41e-02

Pos logit contributions
Charl+0.112
 Midnight+0.107
+0.103
 Cathy+0.102
 ask+0.097
Neg logit contributions
 ever-0.114
ad-0.114
aces-0.113
bridge-0.108
ers-0.099
Token.
Token ID13
Feature activation-4.73e-03

Pos logit contributions
+0.047
 ask+0.044
 insists+0.044
ucker+0.043
 Benjamin+0.043
Neg logit contributions
 ever-0.058
years-0.058
bridge-0.054
ad-0.053
rest-0.053
Token They
Token ID1119
Feature activation-1.04e-02

Pos logit contributions
Charl+0.008
+0.007
 stret+0.007
die+0.007
 fuss+0.007
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.007
aces-0.007
years-0.006
Token were
Token ID547
Feature activation-4.34e-03

Pos logit contributions
+0.018
Charl+0.017
 ask+0.016
 insists+0.016
 rinse+0.016
Neg logit contributions
 ever-0.016
ad-0.014
bridge-0.014
years-0.014
aces-0.014
Token happy
Token ID3772
Feature activation+2.29e-03

Pos logit contributions
+0.006
Charl+0.006
 ask+0.006
 Benjamin+0.006
die+0.006
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.007
years-0.007
aces-0.007
Token her
Token ID607
Feature activation-2.58e-02

Pos logit contributions
+0.017
Charl+0.017
 stret+0.016
 ask+0.016
 insists+0.016
Neg logit contributions
 ever-0.014
ad-0.012
bridge-0.012
years-0.012
aces-0.011
Token to
Token ID284
Feature activation-9.43e-03

Pos logit contributions
+0.040
Charl+0.038
 ask+0.038
 Midnight+0.036
 insists+0.036
Neg logit contributions
 ever-0.042
ad-0.040
years-0.040
bridge-0.039
aces-0.038
Token fill
Token ID6070
Feature activation-4.94e-03

Pos logit contributions
+0.012
Charl+0.012
 ask+0.011
 stret+0.011
 insists+0.011
Neg logit contributions
 ever-0.018
ad-0.017
bridge-0.017
years-0.017
aces-0.016
Token it
Token ID340
Feature activation-9.41e-03

Pos logit contributions
+0.009
Charl+0.008
 ask+0.008
 Benjamin+0.008
 stret+0.008
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.007
years-0.006
aces-0.006
Token with
Token ID351
Feature activation-4.14e-03

Pos logit contributions
+0.014
 rinse+0.013
 ask+0.013
 Midnight+0.012
ench+0.012
Neg logit contributions
years-0.016
ad-0.016
bridge-0.016
 ever-0.016
anes-0.015
Token lettuce
Token ID39406
Feature activation-6.73e-02

Pos logit contributions
+0.006
Charl+0.006
 ask+0.005
 rinse+0.005
 stret+0.005
Neg logit contributions
 ever-0.007
years-0.007
bridge-0.007
ad-0.007
rest-0.007
Token.
Token ID13
Feature activation-1.01e-03

Pos logit contributions
+0.114
Charl+0.113
 stret+0.105
 ask+0.104
 insists+0.104
Neg logit contributions
 ever-0.105
ad-0.092
bridge-0.091
years-0.090
aces-0.089
Token Lucy
Token ID22162
Feature activation-1.14e-02

Pos logit contributions
Charl+0.002
+0.002
 stret+0.002
itch+0.002
arl+0.002
Neg logit contributions
 ever-0.002
 days-0.001
aces-0.001
ad-0.001
years-0.001
Token grabbed
Token ID13176
Feature activation-1.64e-02

Pos logit contributions
+0.018
Charl+0.018
 ask+0.017
 insists+0.017
die+0.017
Neg logit contributions
 ever-0.018
bridge-0.017
ad-0.017
years-0.017
rest-0.016
Token the
Token ID262
Feature activation+1.19e-03

Pos logit contributions
+0.032
Charl+0.031
 ask+0.030
 Benjamin+0.030
 Midnight+0.029
Neg logit contributions
 ever-0.022
bridge-0.019
ad-0.019
years-0.018
rest-0.018
Token lettuce
Token ID39406
Feature activation-5.76e-02

Pos logit contributions
 ever+0.002
ad+0.002
bridge+0.002
years+0.002
aces+0.002
Neg logit contributions
Charl-0.002
-0.002
 stret-0.001
 ask-0.001
 insists-0.001
Token it
Token ID340
Feature activation-2.03e-04

Pos logit contributions
+0.039
Charl+0.037
 ask+0.035
 Benjamin+0.035
 Sonny+0.035
Neg logit contributions
 ever-0.036
ad-0.032
years-0.032
bridge-0.032
aces-0.031
Token in
Token ID287
Feature activation-8.91e-03

Pos logit contributions
+0.000
 rinse+0.000
 swap+0.000
 Midnight+0.000
 ask+0.000
Neg logit contributions
ad-0.000
years-0.000
 ever-0.000
bridge-0.000
rd-0.000
Token a
Token ID257
Feature activation-1.29e-02

Pos logit contributions
+0.016
Charl+0.016
 stret+0.015
 ask+0.015
 insists+0.015
Neg logit contributions
 ever-0.013
ad-0.011
bridge-0.011
years-0.011
aces-0.011
Token bowl
Token ID9396
Feature activation-1.63e-02

Pos logit contributions
Charl+0.023
ucker+0.022
 insists+0.022
severe+0.022
 Benjamin+0.021
Neg logit contributions
 ever-0.019
 days-0.017
bridge-0.017
 next-0.015
 of-0.015
Token with
Token ID351
Feature activation+1.02e-02

Pos logit contributions
+0.021
 rinse+0.019
 ask+0.019
arl+0.018
ucker+0.018
Neg logit contributions
years-0.031
 ever-0.029
rest-0.029
ad-0.029
bridge-0.029
Token lettuce
Token ID39406
Feature activation-6.73e-02

Pos logit contributions
 ever+0.016
bridge+0.015
ad+0.015
years+0.015
aces+0.015
Neg logit contributions
-0.016
Charl-0.016
 ask-0.015
 rinse-0.015
 Sonny-0.015
Token,
Token ID11
Feature activation-1.64e-02

Pos logit contributions
Charl+0.131
+0.126
 stret+0.119
 insists+0.117
 Benjamin+0.117
Neg logit contributions
 ever-0.096
aces-0.079
ad-0.076
 days-0.076
bridge-0.076
Token tomatoes
Token ID23972
Feature activation-3.50e-02

Pos logit contributions
+0.021
Charl+0.020
 ask+0.019
 rinse+0.019
 stret+0.018
Neg logit contributions
 ever-0.032
ad-0.030
years-0.029
bridge-0.029
rest-0.029
Token,
Token ID11
Feature activation-8.58e-03

Pos logit contributions
+0.058
Charl+0.057
 stret+0.053
 ask+0.052
 insists+0.052
Neg logit contributions
 ever-0.057
ad-0.049
bridge-0.049
aces-0.048
years-0.048
Token cheese
Token ID9891
Feature activation-3.33e-02

Pos logit contributions
+0.011
Charl+0.010
 ask+0.009
 rinse+0.009
 Sonny+0.009
Neg logit contributions
 ever-0.017
ad-0.016
years-0.016
rest-0.016
bridge-0.016
Token and
Token ID290
Feature activation+3.47e-03

Pos logit contributions
Charl+0.056
+0.055
 stret+0.051
 insists+0.051
 ask+0.051
Neg logit contributions
 ever-0.054
ad-0.046
bridge-0.046
aces-0.046
 days-0.045
Token.
Token ID13
Feature activation-3.89e-03

Pos logit contributions
+0.016
 ask+0.015
Charl+0.015
ench+0.015
 stret+0.015
Neg logit contributions
years-0.022
 ever-0.022
bridge-0.021
rest-0.020
ad-0.020
Token The
Token ID383
Feature activation-2.44e-02

Pos logit contributions
Charl+0.006
+0.006
 stret+0.006
 rinse+0.006
arl+0.006
Neg logit contributions
 ever-0.006
ad-0.005
bridge-0.005
years-0.005
aces-0.005
Token bee
Token ID20697
Feature activation-1.81e-02

Pos logit contributions
+0.030
Charl+0.029
 ask+0.027
 stret+0.026
 insists+0.026
Neg logit contributions
 ever-0.050
ad-0.046
bridge-0.045
years-0.045
aces-0.044
Token asked
Token ID1965
Feature activation-7.24e-03

Pos logit contributions
+0.029
Charl+0.028
die+0.026
 ask+0.026
 insists+0.025
Neg logit contributions
 ever-0.030
bridge-0.028
aces-0.027
years-0.027
ad-0.027
Token the
Token ID262
Feature activation-2.85e-02

Pos logit contributions
+0.013
Charl+0.013
 ask+0.012
 insists+0.012
 Benjamin+0.012
Neg logit contributions
 ever-0.011
bridge-0.010
ad-0.009
years-0.009
aces-0.009
Token rad
Token ID2511
Feature activation-6.70e-02

Pos logit contributions
Charl+0.043
+0.042
 stret+0.040
 Benjamin+0.038
ucker+0.038
Neg logit contributions
 ever-0.051
ad-0.045
 days-0.044
bridge-0.044
years-0.043
Tokenish
Token ID680
Feature activation-4.13e-02

Pos logit contributions
 stret+0.086
Charl+0.084
+0.075
 Benjamin+0.074
 rinse+0.073
Neg logit contributions
 ever-0.138
years-0.131
ad-0.125
rest-0.119
we-0.119
Token,
Token ID11
Feature activation-1.41e-02

Pos logit contributions
+0.054
Charl+0.053
 ask+0.050
 insists+0.048
 Sonny+0.048
Neg logit contributions
 ever-0.079
bridge-0.072
ad-0.072
years-0.071
aces-0.070
Token "
Token ID366
Feature activation-5.61e-03

Pos logit contributions
+0.020
Charl+0.019
 stret+0.018
ucker+0.017
itch+0.017
Neg logit contributions
 ever-0.027
years-0.024
ad-0.023
 days-0.022
year-0.022
TokenWill
Token ID8743
Feature activation-8.50e-04

Pos logit contributions
+0.007
Charl+0.007
 ask+0.006
 stret+0.006
 insists+0.006
Neg logit contributions
 ever-0.011
ad-0.010
bridge-0.010
years-0.010
aces-0.010
Token you
Token ID345
Feature activation-1.31e-02

Pos logit contributions
+0.001
 ask+0.001
Charl+0.001
 Sonny+0.001
 insists+0.001
Neg logit contributions
 ever-0.001
bridge-0.001
aces-0.001
years-0.001
year-0.001
Token had
Token ID550
Feature activation+1.81e-02

Pos logit contributions
 ever+0.001
years+0.001
aces+0.001
bridge+0.001
ad+0.001
Neg logit contributions
-0.001
 ask-0.001
Charl-0.001
die-0.001
 Benjamin-0.001
Token meat
Token ID6174
Feature activation-2.71e-02

Pos logit contributions
 ever+0.028
years+0.028
rest+0.026
lo+0.026
ad+0.026
Neg logit contributions
-0.027
 ask-0.026
 Sonny-0.026
 Benjamin-0.025
 insists-0.025
Token and
Token ID290
Feature activation+1.51e-04

Pos logit contributions
+0.044
Charl+0.042
 ask+0.040
 stret+0.040
 insists+0.040
Neg logit contributions
 ever-0.043
years-0.039
ad-0.039
bridge-0.038
rest-0.037
Token cheese
Token ID9891
Feature activation-3.14e-02

Pos logit contributions
 ever+0.000
ad+0.000
years+0.000
bridge+0.000
rest+0.000
Neg logit contributions
-0.000
Charl-0.000
 ask-0.000
 stret-0.000
 Benjamin-0.000
Token and
Token ID290
Feature activation+1.24e-03

Pos logit contributions
+0.053
Charl+0.052
 stret+0.049
 ask+0.049
 insists+0.048
Neg logit contributions
 ever-0.049
ad-0.043
years-0.043
bridge-0.043
aces-0.041
Token lettuce
Token ID39406
Feature activation-6.67e-02

Pos logit contributions
 ever+0.002
ad+0.002
years+0.002
rest+0.002
bridge+0.002
Neg logit contributions
-0.002
Charl-0.001
 ask-0.001
 Benjamin-0.001
die-0.001
Token.
Token ID13
Feature activation-1.34e-03

Pos logit contributions
+0.116
Charl+0.116
 stret+0.107
 ask+0.106
 insists+0.105
Neg logit contributions
 ever-0.102
ad-0.089
bridge-0.088
years-0.086
aces-0.086
Token He
Token ID679
Feature activation-4.33e-03

Pos logit contributions
Charl+0.002
+0.002
 stret+0.002
 insists+0.002
 fuss+0.002
Neg logit contributions
 ever-0.002
bridge-0.002
ad-0.002
aces-0.002
years-0.002
Token liked
Token ID8288
Feature activation-2.75e-03

Pos logit contributions
+0.007
Charl+0.006
 ask+0.006
 insists+0.006
die+0.006
Neg logit contributions
 ever-0.007
bridge-0.007
rest-0.007
ad-0.007
aces-0.007
Token burger
Token ID26593
Feature activation-1.36e-02

Pos logit contributions
+0.004
Charl+0.004
 ask+0.004
 Benjamin+0.004
 Sonny+0.004
Neg logit contributions
 ever-0.005
bridge-0.004
ad-0.004
years-0.004
aces-0.004
Token.
Token ID13
Feature activation+3.29e-03

Pos logit contributions
+0.020
 ask+0.018
 Benjamin+0.018
 insists+0.017
 Sonny+0.017
Neg logit contributions
years-0.023
 ever-0.023
bridge-0.022
ad-0.021
aces-0.021
Token They
Token ID1119
Feature activation-3.90e-03

Pos logit contributions
 ever+0.006
ad+0.005
years+0.005
bridge+0.005
rest+0.005
Neg logit contributions
-0.003
Charl-0.003
 ask-0.003
 insists-0.003
 Benjamin-0.003
Token went
Token ID1816
Feature activation-6.57e-03

Pos logit contributions
+0.006
Charl+0.005
 ask+0.005
 Sonny+0.005
die+0.005
Neg logit contributions
 ever-0.007
bridge-0.006
ad-0.006
aces-0.006
rest-0.006
Token past
Token ID1613
Feature activation+1.24e-02

Pos logit contributions
+0.011
Charl+0.010
 ask+0.010
 stret+0.010
 rinse+0.009
Neg logit contributions
 ever-0.010
bridge-0.010
ad-0.010
years-0.010
aces-0.009
Token rocks
Token ID12586
Feature activation-7.92e-03

Pos logit contributions
bridge+0.022
 ever+0.021
years+0.020
ad+0.020
aces+0.019
Neg logit contributions
-0.018
 ask-0.016
 Sonny-0.016
Charl-0.016
die-0.016
Token and
Token ID290
Feature activation-3.02e-03

Pos logit contributions
 ask+0.007
+0.007
 agree+0.007
 difference+0.007
Charl+0.006
Neg logit contributions
years-0.017
bridge-0.017
rest-0.016
ad-0.016
 ever-0.016
Token seaw
Token ID32085
Feature activation-6.65e-02

Pos logit contributions
 ask+0.004
die+0.004
+0.003
 Midnight+0.003
 Sonny+0.003
Neg logit contributions
bridge-0.006
aces-0.006
ad-0.006
rest-0.005
anes-0.005
Tokeneed
Token ID2308
Feature activation-3.39e-02

Pos logit contributions
Charl+0.103
+0.100
 Midnight+0.095
 stret+0.090
 Cathy+0.090
Neg logit contributions
 ever-0.119
aces-0.115
ad-0.113
bridge-0.107
ers-0.103
Token.
Token ID13
Feature activation-1.51e-03

Pos logit contributions
+0.036
 ask+0.035
 agree+0.034
 stret+0.032
 insists+0.032
Neg logit contributions
years-0.068
ad-0.064
bridge-0.063
 ever-0.063
rest-0.061
Token They
Token ID1119
Feature activation-4.26e-03

Pos logit contributions
+0.002
Charl+0.002
 ask+0.002
 insists+0.002
 stret+0.002
Neg logit contributions
 ever-0.003
ad-0.003
bridge-0.003
years-0.003
rest-0.002
Token saw
Token ID2497
Feature activation+1.47e-02

Pos logit contributions
+0.006
 ask+0.006
Charl+0.006
 Sonny+0.006
 rinse+0.006
Neg logit contributions
 ever-0.007
bridge-0.007
aces-0.007
ad-0.007
rest-0.006
Token other
Token ID584
Feature activation-1.70e-02

Pos logit contributions
 ever+0.025
bridge+0.024
aces+0.024
ad+0.023
rest+0.022
Neg logit contributions
 ask-0.020
-0.020
 Sonny-0.020
 difference-0.019
 Benjamin-0.019
Token off
Token ID572
Feature activation-9.35e-03

Pos logit contributions
+0.028
Charl+0.028
 insists+0.026
 stret+0.026
 ask+0.026
Neg logit contributions
 ever-0.023
ad-0.020
bridge-0.020
years-0.020
aces-0.019
Token in
Token ID287
Feature activation-1.51e-02

Pos logit contributions
+0.015
Charl+0.015
 stret+0.014
 ask+0.014
 Benjamin+0.014
Neg logit contributions
 ever-0.014
bridge-0.014
ad-0.014
years-0.013
aces-0.013
Token search
Token ID2989
Feature activation-2.61e-03

Pos logit contributions
+0.026
Charl+0.026
 ask+0.024
 stret+0.024
 Benjamin+0.024
Neg logit contributions
 ever-0.023
bridge-0.020
ad-0.020
years-0.020
aces-0.020
Token of
Token ID286
Feature activation-1.69e-02

Pos logit contributions
+0.005
Charl+0.004
 rinse+0.004
 ask+0.004
 difference+0.004
Neg logit contributions
 ever-0.003
bridge-0.003
ad-0.003
years-0.003
aces-0.003
Token b
Token ID275
Feature activation-1.62e-02

Pos logit contributions
+0.029
Charl+0.029
 stret+0.027
 ask+0.027
 insists+0.027
Neg logit contributions
 ever-0.026
ad-0.023
bridge-0.022
years-0.022
aces-0.022
Tokenunn
Token ID20935
Feature activation-6.63e-02

Pos logit contributions
+0.021
Charl+0.020
 ask+0.018
 stret+0.018
 insists+0.018
Neg logit contributions
 ever-0.032
ad-0.029
bridge-0.029
years-0.029
aces-0.028
Tokenies
Token ID444
Feature activation-3.35e-02

Pos logit contributions
+0.084
Charl+0.083
die+0.077
 ask+0.076
 Sonny+0.075
Neg logit contributions
 ever-0.130
bridge-0.121
ad-0.119
years-0.116
rest-0.114
Token.
Token ID13
Feature activation+2.25e-03

Pos logit contributions
+0.054
Charl+0.053
 ask+0.049
 Benjamin+0.049
 stret+0.049
Neg logit contributions
 ever-0.052
ad-0.049
bridge-0.049
years-0.049
aces-0.047
Token They
Token ID1119
Feature activation-9.53e-03

Pos logit contributions
 ever+0.004
ad+0.003
years+0.003
aces+0.003
bridge+0.003
Neg logit contributions
-0.003
 fuss-0.003
Charl-0.003
 stret-0.003
 difference-0.003
Token found
Token ID1043
Feature activation-4.57e-03

Pos logit contributions
Charl+0.015
 ask+0.015
+0.015
 Sonny+0.014
 rinse+0.014
Neg logit contributions
 ever-0.015
bridge-0.014
aces-0.014
ad-0.014
rest-0.013
Token a
Token ID257
Feature activation-1.58e-02

Pos logit contributions
Charl+0.008
+0.008
 Sonny+0.007
 Benjamin+0.007
 Midnight+0.007
Neg logit contributions
 ever-0.007
bridge-0.006
ad-0.006
aces-0.006
years-0.006
Token with
Token ID351
Feature activation+9.14e-03

Pos logit contributions
aces+0.053
bridge+0.051
years+0.050
anes+0.047
 ever+0.047
Neg logit contributions
-0.042
Charl-0.039
die-0.036
 Benjamin-0.036
 Midnight-0.036
Token cheese
Token ID9891
Feature activation-2.37e-02

Pos logit contributions
 ever+0.016
bridge+0.015
aces+0.015
years+0.015
ad+0.015
Neg logit contributions
-0.012
Charl-0.012
 Benjamin-0.012
 rinse-0.012
 Sonny-0.012
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
+0.037
Charl+0.035
 stret+0.033
 Benjamin+0.033
 ask+0.033
Neg logit contributions
 ever-0.039
years-0.037
ad-0.036
bridge-0.035
rest-0.035
Token tomatoes
Token ID23972
Feature activation-3.13e-02

Pos logit contributions
+0.014
 ask+0.012
die+0.012
 Midnight+0.012
Charl+0.012
Neg logit contributions
 ever-0.021
years-0.020
lo-0.020
rest-0.020
ad-0.020
Token and
Token ID290
Feature activation+8.53e-04

Pos logit contributions
+0.046
Charl+0.045
 ask+0.042
 Benjamin+0.041
 stret+0.041
Neg logit contributions
 ever-0.053
years-0.051
ad-0.049
bridge-0.049
rest-0.048
Token lettuce
Token ID39406
Feature activation-6.63e-02

Pos logit contributions
 ever+0.002
lo+0.002
ad+0.002
rest+0.002
years+0.002
Neg logit contributions
-0.001
die-0.001
 Midnight-0.001
Charl-0.001
 ask-0.001
Token.
Token ID13
Feature activation+1.53e-04

Pos logit contributions
+0.104
Charl+0.100
 ask+0.095
 insists+0.093
 stret+0.093
Neg logit contributions
 ever-0.107
years-0.101
ad-0.099
bridge-0.097
rest-0.095
Token She
Token ID1375
Feature activation-7.43e-03

Pos logit contributions
 ever+0.000
ad+0.000
bridge+0.000
years+0.000
aces+0.000
Neg logit contributions
-0.000
Charl-0.000
 stret-0.000
 insists-0.000
 ask-0.000
Token put
Token ID1234
Feature activation-1.86e-02

Pos logit contributions
+0.012
Charl+0.011
 ask+0.011
die+0.011
 rinse+0.011
Neg logit contributions
 ever-0.012
years-0.011
bridge-0.011
ad-0.011
aces-0.011
Token it
Token ID340
Feature activation+2.81e-03

Pos logit contributions
+0.030
Charl+0.029
 Benjamin+0.027
 Midnight+0.027
 ask+0.027
Neg logit contributions
 ever-0.030
bridge-0.027
ad-0.027
years-0.027
aces-0.027
Token inside
Token ID2641
Feature activation-3.11e-02

Pos logit contributions
ad+0.004
lo+0.004
years+0.004
bridge+0.004
 ever+0.004
Neg logit contributions
-0.004
die-0.004
 Midnight-0.004
 rinse-0.004
Charl-0.004
Token buckets
Token ID38674
Feature activation+1.47e-04

Pos logit contributions
+0.016
Charl+0.015
 ask+0.015
 rinse+0.014
 Benjamin+0.014
Neg logit contributions
 ever-0.019
years-0.017
bridge-0.017
ad-0.017
aces-0.017
Token and
Token ID290
Feature activation-9.38e-03

Pos logit contributions
years+0.000
 ever+0.000
rest+0.000
bridge+0.000
ad+0.000
Neg logit contributions
-0.000
 ask-0.000
 rinse-0.000
arl-0.000
Charl-0.000
Token shovel
Token ID33677
Feature activation-4.42e-02

Pos logit contributions
+0.013
 ask+0.013
 rinse+0.012
Charl+0.012
 stret+0.011
Neg logit contributions
 ever-0.017
rest-0.016
years-0.016
ad-0.016
bridge-0.016
Tokens
Token ID82
Feature activation+1.91e-03

Pos logit contributions
+0.052
Charl+0.045
 ask+0.044
 insists+0.043
die+0.042
Neg logit contributions
 ever-0.091
years-0.086
bridge-0.086
ad-0.086
rest-0.083
Token and
Token ID290
Feature activation-9.93e-03

Pos logit contributions
 ever+0.003
years+0.003
ad+0.003
bridge+0.003
rest+0.003
Neg logit contributions
-0.003
 ask-0.003
Charl-0.003
 rinse-0.003
 stret-0.003
Token seaw
Token ID32085
Feature activation-6.63e-02

Pos logit contributions
+0.014
 ask+0.013
Charl+0.013
 rinse+0.013
 stret+0.013
Neg logit contributions
 ever-0.018
ad-0.017
years-0.017
bridge-0.016
rest-0.016
Tokeneed
Token ID2308
Feature activation-3.50e-02

Pos logit contributions
Charl+0.110
 Midnight+0.104
 Cathy+0.100
+0.097
 Benjamin+0.094
Neg logit contributions
aces-0.113
 ever-0.109
bridge-0.107
ad-0.106
ers-0.100
Token.
Token ID13
Feature activation-9.82e-03

Pos logit contributions
+0.056
Charl+0.053
 ask+0.051
 stret+0.050
 insists+0.050
Neg logit contributions
 ever-0.057
ad-0.053
years-0.053
bridge-0.052
rest-0.050
Token Then
Token ID3244
Feature activation-1.57e-02

Pos logit contributions
Charl+0.014
+0.013
 stret+0.013
 fuss+0.012
die+0.012
Neg logit contributions
 ever-0.018
bridge-0.016
ad-0.016
aces-0.016
years-0.016
Token we
Token ID356
Feature activation-1.82e-02

Pos logit contributions
Charl+0.026
+0.025
 stret+0.024
die+0.023
 insists+0.023
Neg logit contributions
 ever-0.026
ad-0.022
bridge-0.022
 days-0.022
years-0.021
Token can
Token ID460
Feature activation-8.16e-04

Pos logit contributions
Charl+0.017
+0.017
 stret+0.015
 Benjamin+0.014
 insists+0.014
Neg logit contributions
 ever-0.043
ad-0.039
bridge-0.039
years-0.038
aces-0.038
Token shore
Token ID15191
Feature activation-2.14e-02

Pos logit contributions
Charl+0.008
+0.008
ucker+0.007
 stret+0.007
 Midnight+0.007
Neg logit contributions
 ever-0.012
ad-0.011
bridge-0.011
 days-0.011
rest-0.011
Token,
Token ID11
Feature activation-4.63e-03

Pos logit contributions
+0.023
 ask+0.022
 agree+0.021
 stret+0.020
 difference+0.020
Neg logit contributions
years-0.042
 ever-0.040
rest-0.039
year-0.039
bridge-0.039
Token collecting
Token ID13157
Feature activation-9.26e-03

Pos logit contributions
+0.007
Charl+0.007
 ask+0.007
 stret+0.007
 Benjamin+0.007
Neg logit contributions
 ever-0.008
ad-0.007
bridge-0.007
years-0.007
aces-0.007
Token shells
Token ID19679
Feature activation-2.23e-02

Pos logit contributions
+0.015
Charl+0.014
 stret+0.014
 ask+0.014
 rinse+0.014
Neg logit contributions
 ever-0.015
years-0.014
bridge-0.013
ad-0.013
rest-0.013
Token and
Token ID290
Feature activation-4.18e-03

Pos logit contributions
+0.029
Charl+0.028
 ask+0.027
 Benjamin+0.027
 Sonny+0.026
Neg logit contributions
years-0.039
 ever-0.038
bridge-0.037
ad-0.037
rest-0.036
Token seaw
Token ID32085
Feature activation-6.62e-02

Pos logit contributions
 ask+0.006
die+0.006
+0.006
 Benjamin+0.006
Charl+0.006
Neg logit contributions
 ever-0.006
bridge-0.006
aces-0.006
years-0.006
ad-0.006
Tokeneed
Token ID2308
Feature activation-3.82e-02

Pos logit contributions
Charl+0.092
+0.091
 Midnight+0.086
 insists+0.083
 ask+0.082
Neg logit contributions
 ever-0.127
aces-0.121
ad-0.121
bridge-0.119
ers-0.109
Token.
Token ID13
Feature activation+2.79e-03

Pos logit contributions
+0.051
Charl+0.049
 stret+0.049
 ask+0.048
 Benjamin+0.047
Neg logit contributions
years-0.064
 ever-0.063
ad-0.061
bridge-0.060
rest-0.058
Token Jimmy
Token ID12963
Feature activation-1.19e-02

Pos logit contributions
 ever+0.005
ad+0.004
aces+0.004
years+0.004
bridge+0.004
Neg logit contributions
-0.005
Charl-0.004
 stret-0.004
 fuss-0.004
 ask-0.004
Token took
Token ID1718
Feature activation-6.34e-03

Pos logit contributions
+0.019
Charl+0.019
 ask+0.018
 insists+0.018
 Benjamin+0.017
Neg logit contributions
 ever-0.018
bridge-0.017
ad-0.017
years-0.017
aces-0.017
Token time
Token ID640
Feature activation-1.40e-02

Pos logit contributions
+0.009
 Benjamin+0.009
Charl+0.009
 ask+0.009
 Sonny+0.009
Neg logit contributions
 ever-0.010
bridge-0.009
years-0.009
aces-0.009
we-0.009
Token and
Token ID290
Feature activation-5.00e-03

Pos logit contributions
+0.025
 ask+0.023
ccoli+0.023
Charl+0.023
die+0.022
Neg logit contributions
years-0.029
 ever-0.029
ad-0.028
bridge-0.028
rest-0.027
Token cheese
Token ID9891
Feature activation-2.82e-02

Pos logit contributions
+0.007
 ask+0.006
Charl+0.006
 rinse+0.006
 insists+0.006
Neg logit contributions
 ever-0.009
years-0.009
ad-0.009
bridge-0.009
rest-0.008
Token and
Token ID290
Feature activation-5.91e-03

Pos logit contributions
+0.045
Charl+0.042
 ask+0.040
 stret+0.040
 insists+0.039
Neg logit contributions
 ever-0.045
years-0.043
ad-0.042
bridge-0.042
rest-0.041
Token ham
Token ID8891
Feature activation-3.63e-02

Pos logit contributions
+0.008
Charl+0.007
 ask+0.007
 rinse+0.007
 insists+0.007
Neg logit contributions
 ever-0.011
ad-0.010
years-0.010
bridge-0.010
rest-0.010
Token and
Token ID290
Feature activation-7.40e-03

Pos logit contributions
+0.062
Charl+0.061
 ask+0.057
 stret+0.056
 insists+0.056
Neg logit contributions
 ever-0.056
ad-0.050
bridge-0.049
years-0.049
aces-0.048
Token lettuce
Token ID39406
Feature activation-6.58e-02

Pos logit contributions
+0.010
Charl+0.009
 ask+0.009
 rinse+0.009
 stret+0.009
Neg logit contributions
 ever-0.014
ad-0.013
years-0.013
bridge-0.013
rest-0.013
Token at
Token ID379
Feature activation+2.22e-02

Pos logit contributions
+0.107
Charl+0.103
 ask+0.098
 stret+0.097
 insists+0.096
Neg logit contributions
 ever-0.106
ad-0.096
years-0.096
bridge-0.094
rest-0.091
Token home
Token ID1363
Feature activation-2.85e-02

Pos logit contributions
 ever+0.039
bridge+0.035
ad+0.035
years+0.034
aces+0.034
Neg logit contributions
-0.034
Charl-0.033
 ask-0.030
 stret-0.030
 Benjamin-0.030
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
+0.039
 ask+0.038
Charl+0.035
 insists+0.035
 Benjamin+0.035
Neg logit contributions
 ever-0.049
bridge-0.049
ad-0.049
years-0.049
rest-0.046
Token She
Token ID1375
Feature activation-1.17e-02

Pos logit contributions
Charl+0.020
die+0.020
 habit+0.020
ench+0.019
 stret+0.019
Neg logit contributions
 ever-0.015
ad-0.013
aces-0.012
anes-0.012
 days-0.011
Token says
Token ID1139
Feature activation-5.21e-03

Pos logit contributions
Charl+0.012
+0.011
 stret+0.011
arl+0.010
ench+0.010
Neg logit contributions
 ever-0.027
ad-0.024
bridge-0.024
aces-0.024
years-0.023
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
+0.016
Charl+0.016
 ask+0.015
 insists+0.015
 stret+0.014
Neg logit contributions
 ever-0.018
ad-0.017
bridge-0.017
years-0.017
aces-0.016
Token It
Token ID632
Feature activation-6.94e-03

Pos logit contributions
Charl+0.017
 stret+0.017
+0.017
 fuss+0.016
die+0.016
Neg logit contributions
 ever-0.019
ad-0.017
bridge-0.016
aces-0.016
years-0.016
Token has
Token ID468
Feature activation+1.49e-02

Pos logit contributions
+0.009
Charl+0.009
 ask+0.008
 stret+0.008
 insists+0.008
Neg logit contributions
 ever-0.014
ad-0.013
bridge-0.012
years-0.012
aces-0.012
Token carrots
Token ID34397
Feature activation-4.01e-02

Pos logit contributions
years+0.025
 ever+0.025
ad+0.024
rest+0.024
lo+0.024
Neg logit contributions
-0.021
 ask-0.019
Charl-0.019
 rinse-0.019
die-0.019
Token and
Token ID290
Feature activation+5.32e-03

Pos logit contributions
+0.068
Charl+0.068
 stret+0.063
 ask+0.062
 insists+0.062
Neg logit contributions
 ever-0.062
ad-0.055
bridge-0.054
years-0.053
aces-0.053
Token lettuce
Token ID39406
Feature activation-6.56e-02

Pos logit contributions
 ever+0.011
ad+0.010
years+0.010
bridge+0.010
rest+0.010
Neg logit contributions
-0.007
Charl-0.006
 ask-0.006
die-0.006
 rinse-0.006
Token and
Token ID290
Feature activation+4.86e-03

Pos logit contributions
Charl+0.123
+0.116
 stret+0.111
 Benjamin+0.110
 insists+0.108
Neg logit contributions
 ever-0.099
aces-0.082
bridge-0.080
 days-0.079
ad-0.079
Token tomatoes
Token ID23972
Feature activation-3.39e-02

Pos logit contributions
 ever+0.010
ad+0.009
years+0.009
bridge+0.009
rest+0.009
Neg logit contributions
-0.006
Charl-0.006
 ask-0.006
 stret-0.005
die-0.005
Token."
Token ID526
Feature activation-1.33e-02

Pos logit contributions
+0.055
Charl+0.055
 stret+0.051
 ask+0.050
 insists+0.050
Neg logit contributions
 ever-0.055
ad-0.048
bridge-0.048
years-0.047
aces-0.047
Token
Token ID198
Feature activation-2.50e-03

Pos logit contributions
Charl+0.018
+0.016
 stret+0.016
die+0.016
 insists+0.015
Neg logit contributions
 ever-0.026
ad-0.024
 days-0.023
bridge-0.022
aces-0.022
Token
Token ID198
Feature activation-3.70e-03

Pos logit contributions
Charl+0.004
ccoli+0.004
 stret+0.004
 habit+0.004
ench+0.004
Neg logit contributions
 ever-0.004
ad-0.004
lo-0.003
 days-0.003
 next-0.003
Token had
Token ID550
Feature activation+1.27e-02

Pos logit contributions
+0.005
Charl+0.005
 insists+0.005
 ask+0.005
die+0.005
Neg logit contributions
 ever-0.005
years-0.005
bridge-0.005
aces-0.005
ad-0.004
Token cheese
Token ID9891
Feature activation-2.72e-02

Pos logit contributions
lo+0.020
years+0.020
 ever+0.019
rest+0.019
year+0.019
Neg logit contributions
-0.018
 rinse-0.018
 insists-0.017
 ask-0.017
 Midnight-0.017
Token and
Token ID290
Feature activation-4.95e-04

Pos logit contributions
+0.040
Charl+0.037
 rinse+0.036
 Midnight+0.036
ucker+0.036
Neg logit contributions
 ever-0.045
years-0.045
ad-0.042
rest-0.042
bridge-0.041
Token ham
Token ID8891
Feature activation-3.68e-02

Pos logit contributions
+0.001
Charl+0.001
die+0.001
 ask+0.001
 Midnight+0.001
Neg logit contributions
 ever-0.001
years-0.001
ad-0.001
rest-0.001
bridge-0.001
Token and
Token ID290
Feature activation+3.13e-04

Pos logit contributions
Charl+0.063
+0.063
 stret+0.058
 ask+0.057
 insists+0.057
Neg logit contributions
 ever-0.058
ad-0.050
bridge-0.050
aces-0.049
years-0.048
Token lettuce
Token ID39406
Feature activation-6.55e-02

Pos logit contributions
 ever+0.001
ad+0.001
bridge+0.001
years+0.001
rest+0.001
Neg logit contributions
-0.000
Charl-0.000
 ask-0.000
 stret-0.000
 insists-0.000
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
Charl+0.116
+0.115
 stret+0.107
 ask+0.105
 insists+0.105
Neg logit contributions
 ever-0.099
ad-0.086
bridge-0.085
aces-0.083
years-0.082
Token She
Token ID1375
Feature activation-8.61e-03

Pos logit contributions
 stret+0.019
+0.019
Charl+0.019
 fuss+0.019
heit+0.018
Neg logit contributions
 ever-0.014
aces-0.013
ad-0.012
bridge-0.012
years-0.012
Token did
Token ID750
Feature activation+2.57e-02

Pos logit contributions
Charl+0.014
+0.014
 stret+0.013
 ask+0.013
 Sonny+0.013
Neg logit contributions
 ever-0.014
ad-0.012
bridge-0.012
years-0.012
aces-0.012
Token not
Token ID407
Feature activation-9.23e-03

Pos logit contributions
 ever+0.037
ad+0.032
bridge+0.032
years+0.031
aces+0.031
Neg logit contributions
-0.047
Charl-0.046
 ask-0.044
 stret-0.043
 insists-0.043
Token like
Token ID588
Feature activation-7.00e-03

Pos logit contributions
Charl+0.013
+0.012
 stret+0.011
aman+0.011
 Sonny+0.011
Neg logit contributions
 ever-0.019
ad-0.016
bridge-0.016
rest-0.016
aces-0.015
Token has
Token ID468
Feature activation+1.64e-02

Pos logit contributions
Charl+0.004
+0.004
 stret+0.004
arl+0.003
 Sonny+0.003
Neg logit contributions
 ever-0.005
ad-0.005
bridge-0.005
aces-0.005
rest-0.004
Token cheese
Token ID9891
Feature activation-2.33e-02

Pos logit contributions
 ever+0.027
rest+0.025
years+0.025
lo+0.025
year+0.024
Neg logit contributions
-0.024
Charl-0.023
die-0.023
 Midnight-0.023
 Sonny-0.022
Token and
Token ID290
Feature activation+3.12e-03

Pos logit contributions
+0.038
Charl+0.036
 ask+0.034
 Benjamin+0.034
 Midnight+0.034
Neg logit contributions
 ever-0.037
years-0.034
ad-0.033
bridge-0.033
rest-0.033
Token ham
Token ID8891
Feature activation-3.60e-02

Pos logit contributions
 ever+0.006
years+0.006
ad+0.006
bridge+0.006
rest+0.006
Neg logit contributions
-0.004
Charl-0.003
die-0.003
 ask-0.003
 Benjamin-0.003
Token and
Token ID290
Feature activation-2.49e-03

Pos logit contributions
Charl+0.062
+0.062
 stret+0.058
 ask+0.057
 insists+0.056
Neg logit contributions
 ever-0.056
ad-0.048
bridge-0.048
aces-0.047
years-0.047
Token lettuce
Token ID39406
Feature activation-6.55e-02

Pos logit contributions
+0.003
Charl+0.003
 ask+0.003
die+0.003
 Benjamin+0.003
Neg logit contributions
 ever-0.005
ad-0.005
years-0.005
bridge-0.005
rest-0.005
Token.
Token ID13
Feature activation-4.57e-03

Pos logit contributions
Charl+0.118
+0.117
 stret+0.109
 ask+0.107
 insists+0.106
Neg logit contributions
 ever-0.098
ad-0.084
bridge-0.083
aces-0.082
years-0.081
Token Tom
Token ID4186
Feature activation+1.79e-03

Pos logit contributions
Charl+0.008
+0.007
 stret+0.007
die+0.007
 ask+0.007
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.006
years-0.006
aces-0.006
Token is
Token ID318
Feature activation-6.69e-03

Pos logit contributions
 ever+0.003
ad+0.003
aces+0.003
bridge+0.003
years+0.003
Neg logit contributions
Charl-0.003
 stret-0.003
arl-0.002
-0.002
aman-0.002
Token hungry
Token ID14720
Feature activation-5.30e-03

Pos logit contributions
+0.009
Charl+0.009
 ask+0.009
 Benjamin+0.009
 insists+0.009
Neg logit contributions
 ever-0.012
ad-0.011
bridge-0.011
aces-0.011
years-0.011
Token.
Token ID13
Feature activation+9.29e-03

Pos logit contributions
 ask+0.006
+0.006
 fuss+0.006
 insists+0.006
 difference+0.006
Neg logit contributions
years-0.010
lo-0.009
 ever-0.009
bridge-0.009
rest-0.009
Tokenate
Token ID378
Feature activation-1.84e-02

Pos logit contributions
 ever+0.024
years+0.022
aces+0.020
bridge+0.020
year+0.020
Neg logit contributions
-0.016
 ask-0.013
 rinse-0.013
 Benjamin-0.013
ucker-0.013
Token it
Token ID340
Feature activation-1.43e-02

Pos logit contributions
+0.021
 rinse+0.021
 ask+0.020
 Benjamin+0.020
 difference+0.019
Neg logit contributions
years-0.037
 ever-0.036
bridge-0.034
aces-0.033
ad-0.033
Token with
Token ID351
Feature activation-1.93e-03

Pos logit contributions
+0.023
 ask+0.021
 rinse+0.021
 swap+0.020
 difference+0.020
Neg logit contributions
years-0.024
 ever-0.022
ad-0.022
rest-0.021
bridge-0.021
Token shells
Token ID19679
Feature activation-2.62e-02

Pos logit contributions
+0.003
 rinse+0.003
Charl+0.003
 ask+0.002
 Benjamin+0.002
Neg logit contributions
 ever-0.004
years-0.003
rest-0.003
bridge-0.003
aces-0.003
Token and
Token ID290
Feature activation-8.32e-03

Pos logit contributions
+0.041
Charl+0.039
 ask+0.038
 stret+0.037
 rinse+0.037
Neg logit contributions
 ever-0.043
years-0.040
ad-0.039
bridge-0.039
rest-0.038
Token seaw
Token ID32085
Feature activation-6.54e-02

Pos logit contributions
+0.012
 ask+0.012
 rinse+0.011
 swap+0.011
 stret+0.011
Neg logit contributions
 ever-0.014
years-0.014
rest-0.014
year-0.013
ad-0.013
Tokeneed
Token ID2308
Feature activation-4.06e-02

Pos logit contributions
Charl+0.105
 Midnight+0.095
+0.093
 Cathy+0.091
 insists+0.090
Neg logit contributions
aces-0.116
 ever-0.114
bridge-0.111
ad-0.109
ers-0.103
Token.
Token ID13
Feature activation-9.04e-04

Pos logit contributions
+0.069
Charl+0.068
 stret+0.063
 ask+0.063
 insists+0.063
Neg logit contributions
 ever-0.063
ad-0.056
years-0.055
bridge-0.055
rest-0.053
Token They
Token ID1119
Feature activation-1.32e-02

Pos logit contributions
heit+0.002
Charl+0.002
 fuss+0.002
aman+0.002
 stret+0.002
Neg logit contributions
 ever-0.001
 days-0.001
aces-0.001
bridge-0.001
lights-0.001
Token find
Token ID1064
Feature activation-3.78e-04

Pos logit contributions
+0.018
Charl+0.018
 stret+0.017
 insists+0.016
 ask+0.016
Neg logit contributions
 ever-0.025
ad-0.022
bridge-0.022
years-0.021
aces-0.021
Token a
Token ID257
Feature activation-1.91e-02

Pos logit contributions
+0.001
 rinse+0.001
 Benjamin+0.001
 ask+0.001
 Sonny+0.001
Neg logit contributions
 ever-0.001
years-0.001
ad-0.001
rest-0.001
bridge-0.001
Token some
Token ID617
Feature activation+8.45e-03

Pos logit contributions
 ever+0.031
aces+0.027
rest+0.027
years+0.026
bridge+0.026
Neg logit contributions
 Benjamin-0.024
 ask-0.024
 Sonny-0.024
 rinse-0.024
 Midnight-0.023
Token shells
Token ID19679
Feature activation-1.02e-02

Pos logit contributions
 ever+0.016
years+0.014
aces+0.014
ad+0.014
rest+0.014
Neg logit contributions
-0.011
 rinse-0.011
Charl-0.011
 ask-0.011
 fuss-0.011
Token and
Token ID290
Feature activation-2.24e-03

Pos logit contributions
+0.013
 ask+0.012
 rinse+0.012
 Benjamin+0.012
Charl+0.012
Neg logit contributions
years-0.019
 ever-0.019
year-0.018
bridge-0.018
rest-0.018
Token rocks
Token ID12586
Feature activation-9.65e-03

Pos logit contributions
 ask+0.003
+0.003
die+0.003
 rinse+0.003
 fuss+0.003
Neg logit contributions
 ever-0.004
rest-0.004
lo-0.004
years-0.004
ad-0.004
Token and
Token ID290
Feature activation-6.13e-03

Pos logit contributions
+0.011
 ask+0.011
 stret+0.011
 rinse+0.011
ucker+0.011
Neg logit contributions
years-0.018
 ever-0.017
bridge-0.017
year-0.016
ad-0.016
Token seaw
Token ID32085
Feature activation-6.53e-02

Pos logit contributions
 ask+0.009
+0.008
 rinse+0.008
 fuss+0.008
die+0.008
Neg logit contributions
 ever-0.010
rest-0.010
years-0.010
lo-0.010
ad-0.010
Tokeneed
Token ID2308
Feature activation-3.64e-02

Pos logit contributions
Charl+0.106
+0.100
 Midnight+0.098
 Cathy+0.094
 difference+0.092
Neg logit contributions
aces-0.114
 ever-0.110
ad-0.108
bridge-0.107
ers-0.101
Token.
Token ID13
Feature activation+3.25e-03

Pos logit contributions
+0.047
 ask+0.045
 insists+0.045
 stret+0.044
 rinse+0.044
Neg logit contributions
years-0.065
 ever-0.063
ad-0.060
bridge-0.059
rest-0.058
Token He
Token ID679
Feature activation-1.29e-03

Pos logit contributions
 ever+0.006
rest+0.005
years+0.005
ad+0.005
bridge+0.005
Neg logit contributions
-0.005
Charl-0.004
 ask-0.004
 insists-0.004
 Benjamin-0.004
Token picked
Token ID6497
Feature activation-5.33e-03

Pos logit contributions
+0.002
Charl+0.002
 ask+0.002
die+0.002
 insists+0.002
Neg logit contributions
 ever-0.002
bridge-0.002
rest-0.002
aces-0.002
ad-0.002
Token them
Token ID606
Feature activation+1.10e-03

Pos logit contributions
+0.007
 ask+0.007
 Benjamin+0.007
 Sonny+0.007
Charl+0.007
Neg logit contributions
 ever-0.010
years-0.009
bridge-0.009
ad-0.009
aces-0.008
Token she
Token ID673
Feature activation-4.05e-03

Pos logit contributions
+0.009
 Midnight+0.008
Charl+0.008
 ask+0.008
 Benjamin+0.008
Neg logit contributions
ad-0.010
 ever-0.010
bridge-0.009
aces-0.009
years-0.009
Token would
Token ID561
Feature activation+5.11e-03

Pos logit contributions
+0.006
Charl+0.006
 stret+0.005
 ask+0.005
 insists+0.005
Neg logit contributions
 ever-0.007
ad-0.006
bridge-0.006
years-0.006
aces-0.006
Token buy
Token ID2822
Feature activation+6.04e-03

Pos logit contributions
 ever+0.010
ad+0.009
bridge+0.009
years+0.009
aces+0.009
Neg logit contributions
-0.006
Charl-0.006
 stret-0.006
 insists-0.006
 Benjamin-0.005
Token carrots
Token ID34397
Feature activation-4.03e-02

Pos logit contributions
 ever+0.010
bridge+0.010
ad+0.009
years+0.009
rest+0.009
Neg logit contributions
-0.009
Charl-0.009
 Midnight-0.009
 ask-0.009
 Coc-0.008
Token and
Token ID290
Feature activation+3.71e-04

Pos logit contributions
+0.063
Charl+0.060
 ask+0.058
 Sonny+0.055
 Benjamin+0.055
Neg logit contributions
 ever-0.066
years-0.063
bridge-0.062
ad-0.062
rest-0.059
Token lettuce
Token ID39406
Feature activation-6.53e-02

Pos logit contributions
 ever+0.001
ad+0.001
bridge+0.001
years+0.001
aces+0.001
Neg logit contributions
-0.001
Charl-0.001
 stret-0.000
 insists-0.000
 ask-0.000
Token to
Token ID284
Feature activation-4.12e-03

Pos logit contributions
+0.110
Charl+0.108
 ask+0.101
 stret+0.100
 insists+0.100
Neg logit contributions
 ever-0.102
ad-0.090
bridge-0.089
years-0.089
aces-0.086
Token eat
Token ID4483
Feature activation-2.13e-02

Pos logit contributions
Charl+0.005
+0.005
 insists+0.005
ucker+0.005
die+0.005
Neg logit contributions
 ever-0.008
ad-0.008
bridge-0.007
years-0.007
 days-0.007
Token.
Token ID13
Feature activation-2.49e-03

Pos logit contributions
+0.037
Charl+0.036
 stret+0.033
 ask+0.033
 insists+0.033
Neg logit contributions
 ever-0.033
ad-0.029
bridge-0.029
years-0.028
aces-0.028
Token
Token ID220
Feature activation-3.35e-03

Pos logit contributions
 stret+0.004
 fuss+0.004
heit+0.004
Charl+0.004
ealing+0.004
Neg logit contributions
 ever-0.004
 days-0.004
ad-0.004
aces-0.004
years-0.003
Token
Token ID198
Feature activation-3.64e-03

Pos logit contributions
Charl+0.004
+0.004
 stret+0.004
 fuss+0.004
 insists+0.004
Neg logit contributions
 ever-0.007
ad-0.006
aces-0.006
bridge-0.006
years-0.006
Token a
Token ID257
Feature activation-8.84e-03

Pos logit contributions
lo+0.023
 ever+0.023
aces+0.022
years+0.022
rest+0.022
Neg logit contributions
Charl-0.020
-0.019
 Midnight-0.019
 Benjamin-0.018
die-0.018
Token little
Token ID1310
Feature activation-3.15e-02

Pos logit contributions
 insists+0.015
Charl+0.015
severe+0.015
heit+0.015
ucker+0.015
Neg logit contributions
 ever-0.013
 days-0.011
 next-0.011
years-0.010
bridge-0.010
Token girl
Token ID2576
Feature activation-2.83e-03

Pos logit contributions
Charl+0.041
+0.040
 insists+0.038
 stret+0.038
ucker+0.037
Neg logit contributions
 ever-0.061
ad-0.054
 days-0.053
years-0.052
bridge-0.052
Token named
Token ID3706
Feature activation+1.03e-02

Pos logit contributions
+0.004
Charl+0.004
 ask+0.004
 stret+0.003
 Midnight+0.003
Neg logit contributions
 ever-0.005
bridge-0.005
aces-0.005
ad-0.005
rest-0.005
Token L
Token ID406
Feature activation+1.30e-02

Pos logit contributions
 ever+0.021
bridge+0.020
ad+0.020
aces+0.019
years+0.019
Neg logit contributions
-0.012
Charl-0.012
 ask-0.011
 Midnight-0.011
 rinse-0.010
Tokenyl
Token ID2645
Feature activation+6.15e-02

Pos logit contributions
 ever+0.020
bridge+0.018
years+0.018
 days+0.018
aces+0.017
Neg logit contributions
-0.022
Charl-0.022
 rinse-0.020
 ask-0.020
 Benjamin-0.020
Tokena
Token ID64
Feature activation-2.03e-03

Pos logit contributions
 ever+0.130
 days+0.123
ad+0.122
aces+0.122
bridge+0.121
Neg logit contributions
-0.056
Charl-0.054
 ask-0.052
 stret-0.048
 habit-0.048
Token who
Token ID508
Feature activation-2.39e-02

Pos logit contributions
Charl+0.004
+0.004
 insists+0.004
 Benjamin+0.004
 Sonny+0.004
Neg logit contributions
 ever-0.003
ad-0.002
years-0.002
 days-0.002
rest-0.002
Token was
Token ID373
Feature activation+2.73e-03

Pos logit contributions
+0.040
Charl+0.039
 stret+0.037
 insists+0.036
 Benjamin+0.036
Neg logit contributions
 ever-0.039
ad-0.034
years-0.033
bridge-0.033
rest-0.033
Token always
Token ID1464
Feature activation-5.32e-03

Pos logit contributions
bridge+0.005
aces+0.005
 ever+0.005
ad+0.005
lights+0.005
Neg logit contributions
 ask-0.004
Charl-0.003
 Midnight-0.003
-0.003
 Coc-0.003
Token looking
Token ID2045
Feature activation-7.35e-03

Pos logit contributions
Charl+0.009
+0.009
 ask+0.008
 Benjamin+0.008
 Sonny+0.008
Neg logit contributions
 ever-0.008
bridge-0.008
ad-0.008
aces-0.007
years-0.007
Token of
Token ID286
Feature activation+2.27e-02

Pos logit contributions
years+0.064
 ever+0.053
rest+0.052
bridge+0.051
aces+0.051
Neg logit contributions
-0.064
 ask-0.063
 swap-0.059
 insists-0.058
 agree-0.058
Token the
Token ID262
Feature activation+1.88e-02

Pos logit contributions
 ever+0.037
bridge+0.033
aces+0.033
years+0.033
rest+0.032
Neg logit contributions
Charl-0.035
-0.034
 ask-0.034
 Benjamin-0.034
 Sonny-0.034
Token merry
Token ID44570
Feature activation+4.51e-02

Pos logit contributions
 ever+0.032
ad+0.028
bridge+0.028
 days+0.028
aces+0.027
Neg logit contributions
Charl-0.029
-0.029
ucker-0.028
die-0.028
 Benjamin-0.027
Token-
Token ID12
Feature activation+9.18e-02

Pos logit contributions
 ever+0.068
years+0.067
year+0.061
bridge+0.060
ad+0.059
Neg logit contributions
-0.079
 stret-0.074
 ask-0.072
 fuss-0.071
Charl-0.071
Tokengo
Token ID2188
Feature activation+6.01e-02

Pos logit contributions
years+0.131
 ever+0.128
 days+0.123
ad+0.117
aces+0.115
Neg logit contributions
-0.147
 stret-0.145
 ask-0.131
Charl-0.131
arl-0.125
Token-
Token ID12
Feature activation+8.10e-02

Pos logit contributions
years+0.111
year+0.096
 ever+0.095
aces+0.093
bridge+0.092
Neg logit contributions
-0.088
 stret-0.079
 ask-0.077
 swap-0.074
itch-0.070
Tokenround
Token ID744
Feature activation+1.22e-02

Pos logit contributions
 ever+0.168
years+0.164
bridge+0.159
 days+0.157
aces+0.155
Neg logit contributions
-0.089
 stret-0.079
Charl-0.079
 ask-0.073
 swap-0.065
Token.
Token ID13
Feature activation+2.12e-03

Pos logit contributions
years+0.023
 ever+0.022
ad+0.021
year+0.021
 days+0.021
Neg logit contributions
-0.017
 ask-0.015
 stret-0.014
 swap-0.014
 insists-0.014
Token He
Token ID679
Feature activation+5.94e-03

Pos logit contributions
 ever+0.003
ad+0.003
bridge+0.003
aces+0.003
years+0.003
Neg logit contributions
Charl-0.004
-0.004
 stret-0.004
die-0.003
 fuss-0.003
Token thought
Token ID1807
Feature activation+5.13e-03

Pos logit contributions
 ever+0.011
rest+0.010
bridge+0.010
ad+0.010
lo+0.010
Neg logit contributions
-0.008
Charl-0.008
 ask-0.008
 insists-0.007
die-0.007
Token it
Token ID340
Feature activation+6.36e-03

Pos logit contributions
years+0.011
bridge+0.010
ad+0.010
rest+0.010
 ever+0.010
Neg logit contributions
 Benjamin-0.005
 ask-0.005
 rinse-0.005
-0.005
 insists-0.005
Token She
Token ID1375
Feature activation-3.24e-03

Pos logit contributions
+0.006
Charl+0.005
 ask+0.005
 insists+0.005
 Benjamin+0.005
Neg logit contributions
 ever-0.007
ad-0.007
bridge-0.006
years-0.006
rest-0.006
Token loved
Token ID6151
Feature activation+2.36e-03

Pos logit contributions
+0.005
Charl+0.005
 ask+0.004
 Midnight+0.004
die+0.004
Neg logit contributions
 ever-0.006
bridge-0.005
ad-0.005
years-0.005
aces-0.005
Token to
Token ID284
Feature activation+1.76e-02

Pos logit contributions
 ever+0.004
bridge+0.004
aces+0.004
ad+0.004
years+0.003
Neg logit contributions
Charl-0.004
-0.003
 ask-0.003
 stret-0.003
 Midnight-0.003
Token play
Token ID711
Feature activation+1.56e-02

Pos logit contributions
 ever+0.038
years+0.036
bridge+0.035
aces+0.034
rest+0.034
Neg logit contributions
-0.020
Charl-0.018
 ask-0.018
 rinse-0.017
 stret-0.017
Token hide
Token ID7808
Feature activation+4.57e-04

Pos logit contributions
 ever+0.021
ad+0.018
bridge+0.018
years+0.018
aces+0.017
Neg logit contributions
-0.030
Charl-0.030
 stret-0.028
 ask-0.028
 insists-0.028
Token-
Token ID12
Feature activation+7.15e-02

Pos logit contributions
 ever+0.001
bridge+0.001
ad+0.001
anes+0.001
years+0.001
Neg logit contributions
Charl-0.001
-0.001
 stret-0.001
 Midnight-0.000
 Woo-0.000
Tokenand
Token ID392
Feature activation+7.11e-03

Pos logit contributions
 ever+0.104
bridge+0.100
lights+0.094
ad+0.094
aces+0.091
Neg logit contributions
Charl-0.108
-0.103
 stret-0.100
oodle-0.100
 ask-0.097
Token-
Token ID12
Feature activation+5.84e-02

Pos logit contributions
 ever+0.011
bridge+0.011
ad+0.010
years+0.010
aces+0.010
Neg logit contributions
Charl-0.011
-0.011
 stret-0.011
 ask-0.010
 Midnight-0.010
Tokenseek
Token ID36163
Feature activation-3.56e-03

Pos logit contributions
bridge+0.082
 ever+0.078
lights+0.075
ad+0.075
years+0.072
Neg logit contributions
-0.093
Charl-0.093
 Woo-0.086
 ask-0.086
 stret-0.084
Token with
Token ID351
Feature activation+5.29e-03

Pos logit contributions
+0.003
 ask+0.003
Charl+0.003
 lot+0.003
 agree+0.003
Neg logit contributions
bridge-0.007
years-0.007
ad-0.007
rest-0.007
anes-0.007
Token her
Token ID607
Feature activation+3.35e-03

Pos logit contributions
 ever+0.008
bridge+0.007
ad+0.007
years+0.007
aces+0.007
Neg logit contributions
-0.009
Charl-0.009
 ask-0.009
 stret-0.008
 rinse-0.008
Token the
Token ID262
Feature activation+9.74e-03

Pos logit contributions
+0.010
Charl+0.009
 stret+0.009
 insists+0.009
 ask+0.009
Neg logit contributions
 ever-0.006
ad-0.005
years-0.005
bridge-0.005
 days-0.005
Token store
Token ID3650
Feature activation+2.06e-03

Pos logit contributions
 ever+0.017
ad+0.016
 days+0.015
years+0.015
bridge+0.015
Neg logit contributions
Charl-0.014
-0.014
 Benjamin-0.013
 insists-0.013
 Sonny-0.013
Token with
Token ID351
Feature activation-8.65e-03

Pos logit contributions
bridge+0.004
rest+0.004
 ever+0.004
years+0.004
ad+0.004
Neg logit contributions
 ask-0.002
-0.002
 agree-0.002
 stret-0.002
 difference-0.002
Token the
Token ID262
Feature activation+8.48e-03

Pos logit contributions
+0.014
 Benjamin+0.014
Charl+0.014
 Sonny+0.013
 ask+0.013
Neg logit contributions
 ever-0.013
bridge-0.012
aces-0.012
rest-0.012
years-0.012
Token ice
Token ID4771
Feature activation+6.84e-03

Pos logit contributions
 ever+0.015
years+0.014
bridge+0.014
ad+0.014
aces+0.014
Neg logit contributions
-0.013
Charl-0.011
 stret-0.011
 insists-0.011
 difference-0.011
Token-
Token ID12
Feature activation+6.49e-02

Pos logit contributions
years+0.011
 ever+0.011
bridge+0.010
ad+0.010
aces+0.010
Neg logit contributions
-0.011
 stret-0.010
ucker-0.010
Charl-0.010
 rinse-0.009
Tokencream
Token ID36277
Feature activation-1.63e-02

Pos logit contributions
 ever+0.103
aces+0.101
bridge+0.098
 days+0.095
ad+0.090
Neg logit contributions
-0.103
Charl-0.090
ucker-0.086
 Sonny-0.086
 Enjoy-0.085
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
+0.025
Charl+0.025
 stret+0.022
 ask+0.022
 insists+0.022
Neg logit contributions
 ever-0.028
ad-0.025
bridge-0.025
years-0.025
aces-0.024
Token He
Token ID679
Feature activation+2.57e-03

Pos logit contributions
 ever+0.014
aces+0.012
ad+0.012
bridge+0.011
years+0.011
Neg logit contributions
 stret-0.022
-0.022
 fuss-0.022
Charl-0.022
 difference-0.021
Token sat
Token ID3332
Feature activation-5.62e-03

Pos logit contributions
 ever+0.004
bridge+0.004
aces+0.004
ad+0.004
rest+0.004
Neg logit contributions
-0.004
Charl-0.004
 ask-0.004
 insists-0.004
 Benjamin-0.004
Token on
Token ID319
Feature activation+1.37e-02

Pos logit contributions
+0.008
Charl+0.007
 stret+0.006
 ask+0.006
 Benjamin+0.006
Neg logit contributions
 ever-0.011
ad-0.010
rest-0.010
aces-0.010
bridge-0.010
Token.
Token ID13
Feature activation-5.65e-03

Pos logit contributions
years+0.003
 ever+0.003
ad+0.003
bridge+0.003
 days+0.003
Neg logit contributions
-0.002
 stret-0.002
 insists-0.002
Charl-0.002
 rinse-0.002
Token It
Token ID632
Feature activation+5.30e-04

Pos logit contributions
+0.009
Charl+0.009
 stret+0.008
 ask+0.008
 insists+0.008
Neg logit contributions
 ever-0.010
ad-0.009
bridge-0.009
years-0.008
aces-0.008
Token is
Token ID318
Feature activation+4.04e-03

Pos logit contributions
 ever+0.001
ad+0.001
bridge+0.001
years+0.001
aces+0.001
Neg logit contributions
-0.001
Charl-0.001
 stret-0.001
 ask-0.001
 insists-0.001
Token the
Token ID262
Feature activation+1.22e-02

Pos logit contributions
 ever+0.006
ad+0.005
bridge+0.005
years+0.005
aces+0.005
Neg logit contributions
-0.007
Charl-0.007
 stret-0.007
 ask-0.007
 insists-0.007
Token door
Token ID3420
Feature activation+3.77e-02

Pos logit contributions
 ever+0.020
years+0.019
ad+0.019
rest+0.018
bridge+0.018
Neg logit contributions
-0.019
Charl-0.018
 ask-0.017
 stret-0.017
 insists-0.017
Tokenbell
Token ID7923
Feature activation+6.35e-02

Pos logit contributions
years+0.079
aces+0.074
bridge+0.072
ad+0.070
pter+0.070
Neg logit contributions
-0.044
 rinse-0.043
 swap-0.042
 ask-0.041
 insists-0.040
Token.
Token ID13
Feature activation-6.00e-03

Pos logit contributions
 ever+0.110
years+0.107
ad+0.101
bridge+0.100
 days+0.098
Neg logit contributions
-0.096
 ask-0.088
 insists-0.087
 stret-0.086
Charl-0.085
Token Mom
Token ID11254
Feature activation-1.03e-02

Pos logit contributions
+0.009
Charl+0.009
 stret+0.008
 ask+0.008
 insists+0.008
Neg logit contributions
 ever-0.010
ad-0.009
bridge-0.009
years-0.009
aces-0.009
Tokenmy
Token ID1820
Feature activation-1.88e-02

Pos logit contributions
Charl+0.017
+0.016
 habit+0.016
 Sonny+0.016
ench+0.015
Neg logit contributions
 ever-0.017
ad-0.015
aces-0.014
ers-0.014
years-0.014
Token is
Token ID318
Feature activation-1.71e-02

Pos logit contributions
Charl+0.030
 habit+0.029
+0.029
ench+0.028
die+0.028
Neg logit contributions
 ever-0.031
ad-0.027
ers-0.025
aces-0.025
bridge-0.024
Token home
Token ID1363
Feature activation-6.11e-03

Pos logit contributions
+0.026
Charl+0.026
 stret+0.025
 ask+0.025
 insists+0.024
Neg logit contributions
 ever-0.029
ad-0.026
bridge-0.026
years-0.026
aces-0.026
Token very
Token ID845
Feature activation-1.34e-02

Pos logit contributions
+0.011
 ask+0.011
Charl+0.011
 stret+0.011
 insists+0.011
Neg logit contributions
 ever-0.015
ad-0.014
bridge-0.014
aces-0.014
years-0.013
Token excited
Token ID6568
Feature activation+1.23e-02

Pos logit contributions
+0.024
Charl+0.024
 stret+0.022
 ask+0.022
 insists+0.022
Neg logit contributions
 ever-0.020
ad-0.017
bridge-0.017
years-0.017
aces-0.017
Token because
Token ID780
Feature activation+1.81e-03

Pos logit contributions
bridge+0.023
years+0.023
 ever+0.021
aces+0.021
year+0.021
Neg logit contributions
-0.016
 ask-0.016
 fuss-0.015
Charl-0.014
 insists-0.014
Token he
Token ID339
Feature activation-5.56e-03

Pos logit contributions
aces+0.004
years+0.004
ad+0.004
chie+0.004
bridge+0.003
Neg logit contributions
-0.002
 ask-0.002
 Mr-0.002
 Bruno-0.002
 Coc-0.002
Token had
Token ID550
Feature activation+8.08e-03

Pos logit contributions
+0.009
Charl+0.008
 ask+0.008
 insists+0.008
die+0.008
Neg logit contributions
 ever-0.009
bridge-0.009
aces-0.009
ad-0.009
years-0.008
Token never
Token ID1239
Feature activation+2.05e-02

Pos logit contributions
years+0.012
ad+0.012
aces+0.012
lo+0.012
ions+0.011
Neg logit contributions
-0.012
 ask-0.012
Charl-0.012
 insists-0.011
 stret-0.011
Token been
Token ID587
Feature activation-9.65e-04

Pos logit contributions
lo+0.032
bridge+0.031
aces+0.031
ions+0.031
lights+0.030
Neg logit contributions
 ask-0.032
-0.029
 fuss-0.029
 insists-0.028
Charl-0.027
Token to
Token ID284
Feature activation+1.04e-02

Pos logit contributions
Charl+0.001
+0.001
 ask+0.001
 Benjamin+0.001
 insists+0.001
Neg logit contributions
ad-0.002
bridge-0.001
 ever-0.001
aces-0.001
years-0.001
Token a
Token ID257
Feature activation-1.20e-02

Pos logit contributions
aces+0.020
 ever+0.019
bridge+0.019
years+0.019
ad+0.018
Neg logit contributions
 ask-0.013
-0.013
 fuss-0.012
 rinse-0.012
Charl-0.012
Token movie
Token ID3807
Feature activation+1.63e-02

Pos logit contributions
Charl+0.020
ucker+0.019
+0.019
die+0.019
 stret+0.019
Neg logit contributions
 ever-0.020
 days-0.016
bridge-0.016
rest-0.016
ad-0.016
Token theater
Token ID13766
Feature activation+1.28e-02

Pos logit contributions
 ever+0.024
ad+0.023
years+0.023
aces+0.023
bridge+0.022
Neg logit contributions
-0.028
Charl-0.026
 ask-0.025
 Benjamin-0.025
 insists-0.024
Token but
Token ID475
Feature activation-1.38e-03

Pos logit contributions
Charl+0.017
+0.017
 stret+0.016
 ask+0.016
 insists+0.016
Neg logit contributions
 ever-0.026
ad-0.024
bridge-0.024
rest-0.024
years-0.023
Token she
Token ID673
Feature activation-2.58e-03

Pos logit contributions
+0.002
Charl+0.002
 Midnight+0.002
 Benjamin+0.002
 rinse+0.002
Neg logit contributions
bridge-0.002
ad-0.002
 ever-0.002
aces-0.002
rest-0.002
Token could
Token ID714
Feature activation+4.73e-03

Pos logit contributions
+0.004
Charl+0.004
 insists+0.004
 Midnight+0.003
 rinse+0.003
Neg logit contributions
 ever-0.004
bridge-0.004
ad-0.004
rest-0.004
years-0.004
Token not
Token ID407
Feature activation+3.63e-03

Pos logit contributions
 ever+0.007
years+0.006
ad+0.006
bridge+0.006
aces+0.006
Neg logit contributions
-0.008
Charl-0.008
 ask-0.008
 rinse-0.008
 insists-0.007
Token get
Token ID651
Feature activation+1.75e-03

Pos logit contributions
 ever+0.007
years+0.006
bridge+0.006
ad+0.006
aces+0.006
Neg logit contributions
-0.005
Charl-0.005
 ask-0.005
 rinse-0.004
 stret-0.004
Token the
Token ID262
Feature activation+1.62e-02

Pos logit contributions
 ever+0.003
bridge+0.003
ad+0.003
years+0.003
aces+0.003
Neg logit contributions
-0.003
Charl-0.003
 ask-0.002
 insists-0.002
 rinse-0.002
Token tape
Token ID9154
Feature activation+1.54e-02

Pos logit contributions
 ever+0.029
ad+0.026
years+0.025
bridge+0.025
aces+0.025
Neg logit contributions
-0.024
Charl-0.024
 stret-0.022
 ask-0.022
 insists-0.021
Token off
Token ID572
Feature activation+1.25e-02

Pos logit contributions
years+0.029
ad+0.026
 ever+0.026
year+0.025
 days+0.025
Neg logit contributions
-0.021
 stret-0.020
 insists-0.019
 rinse-0.019
 ask-0.019
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
years+0.023
ad+0.022
bridge+0.022
 ever+0.022
aces+0.022
Neg logit contributions
-0.016
Charl-0.014
 Midnight-0.014
 rinse-0.014
 Benjamin-0.014
Token roll
Token ID4836
Feature activation+1.91e-02

Pos logit contributions
 ever+0.029
ad+0.027
years+0.026
bridge+0.026
rest+0.026
Neg logit contributions
-0.026
Charl-0.025
 stret-0.024
 ask-0.023
 insists-0.023
Token.
Token ID13
Feature activation+6.91e-03

Pos logit contributions
years+0.036
 ever+0.033
ad+0.031
bridge+0.031
year+0.031
Neg logit contributions
-0.026
 insists-0.023
 stret-0.023
 knot-0.022
Charl-0.022
Token sorry
Token ID7926
Feature activation-6.98e-03

Pos logit contributions
+0.024
Charl+0.024
 stret+0.022
 ask+0.022
 insists+0.022
Neg logit contributions
 ever-0.033
ad-0.030
bridge-0.030
years-0.030
aces-0.029
Token.
Token ID13
Feature activation-8.37e-03

Pos logit contributions
+0.011
Charl+0.011
 ask+0.010
 insists+0.010
 stret+0.010
Neg logit contributions
 ever-0.012
bridge-0.011
years-0.011
ad-0.010
aces-0.010
Token He
Token ID679
Feature activation-1.59e-02

Pos logit contributions
+0.014
Charl+0.014
 stret+0.013
 ask+0.013
 insists+0.012
Neg logit contributions
 ever-0.014
ad-0.012
bridge-0.012
years-0.012
aces-0.012
Token turns
Token ID4962
Feature activation+1.57e-02

Pos logit contributions
Charl+0.017
+0.016
 stret+0.014
 Sonny+0.014
 Benjamin+0.014
Neg logit contributions
 ever-0.035
ad-0.032
bridge-0.032
aces-0.031
years-0.031
Token the
Token ID262
Feature activation+1.36e-02

Pos logit contributions
 ever+0.021
ad+0.017
rest+0.017
aces+0.016
bridge+0.016
Neg logit contributions
Charl-0.032
-0.032
die-0.029
 Sonny-0.029
 stret-0.029
Token truck
Token ID7779
Feature activation+2.34e-02

Pos logit contributions
 ever+0.025
bridge+0.022
ad+0.022
aces+0.022
 days+0.021
Neg logit contributions
Charl-0.020
-0.019
 Benjamin-0.018
 Sonny-0.017
 stret-0.017
Token around
Token ID1088
Feature activation-8.74e-03

Pos logit contributions
years+0.046
 ever+0.042
ad+0.041
year+0.040
aces+0.040
Neg logit contributions
-0.030
 ask-0.029
 insists-0.028
 swap-0.026
 stret-0.026
Token.
Token ID13
Feature activation-5.99e-03

Pos logit contributions
 ask+0.011
+0.011
 insists+0.010
 fuss+0.010
 stret+0.010
Neg logit contributions
bridge-0.015
 ever-0.015
years-0.015
aces-0.014
rest-0.014
Token He
Token ID679
Feature activation-1.09e-02

Pos logit contributions
+0.009
Charl+0.009
 ask+0.009
 insists+0.009
 stret+0.009
Neg logit contributions
 ever-0.010
ad-0.009
years-0.009
bridge-0.009
rest-0.009
Token goes
Token ID2925
Feature activation-1.16e-03

Pos logit contributions
Charl+0.013
+0.012
 stret+0.011
 Sonny+0.011
 Benjamin+0.011
Neg logit contributions
 ever-0.023
ad-0.021
bridge-0.021
years-0.020
aces-0.020
Token away
Token ID1497
Feature activation-7.06e-03

Pos logit contributions
+0.001
 ask+0.001
 stret+0.001
 fuss+0.001
arl+0.001
Neg logit contributions
aces-0.002
ad-0.002
 ever-0.002
bridge-0.002
years-0.002
Token tried
Token ID3088
Feature activation-3.47e-03

Pos logit contributions
+0.009
Charl+0.009
 ask+0.008
 stret+0.008
 insists+0.008
Neg logit contributions
 ever-0.010
ad-0.009
bridge-0.009
years-0.009
aces-0.009
Token to
Token ID284
Feature activation-2.01e-02

Pos logit contributions
+0.008
Charl+0.008
 stret+0.007
 Sonny+0.007
arl+0.007
Neg logit contributions
 ever-0.004
ad-0.003
 days-0.003
years-0.003
rest-0.003
Token get
Token ID651
Feature activation-2.30e-02

Pos logit contributions
Charl+0.030
+0.030
ucker+0.029
ccoli+0.028
 Sonny+0.026
Neg logit contributions
 ever-0.038
ad-0.034
rest-0.030
 next-0.029
bridge-0.029
Token the
Token ID262
Feature activation+1.44e-02

Pos logit contributions
+0.040
Charl+0.040
 stret+0.037
 ask+0.037
 insists+0.036
Neg logit contributions
 ever-0.035
ad-0.031
bridge-0.030
years-0.030
aces-0.030
Token doll
Token ID3654
Feature activation+7.40e-03

Pos logit contributions
 ever+0.027
bridge+0.024
ad+0.024
aces+0.024
rest+0.024
Neg logit contributions
-0.020
Charl-0.020
die-0.018
 Sonny-0.018
 insists-0.017
Token back
Token ID736
Feature activation+1.83e-02

Pos logit contributions
 ever+0.014
years+0.014
bridge+0.013
ad+0.013
 days+0.013
Neg logit contributions
-0.009
 ask-0.009
Charl-0.009
 stret-0.009
 insists-0.008
Token.
Token ID13
Feature activation-1.55e-03

Pos logit contributions
 ever+0.030
bridge+0.029
years+0.029
ad+0.028
rest+0.027
Neg logit contributions
-0.027
Charl-0.027
 ask-0.026
 insists-0.025
 stret-0.025
Token They
Token ID1119
Feature activation-5.50e-03

Pos logit contributions
Charl+0.003
+0.003
 stret+0.003
die+0.003
 difference+0.003
Neg logit contributions
 ever-0.002
ad-0.002
aces-0.002
 days-0.002
years-0.002
Token ran
Token ID4966
Feature activation-4.35e-03

Pos logit contributions
+0.008
Charl+0.008
 ask+0.008
 rinse+0.008
 insists+0.008
Neg logit contributions
 ever-0.009
bridge-0.009
ad-0.008
rest-0.008
aces-0.008
Token into
Token ID656
Feature activation-1.37e-02

Pos logit contributions
+0.007
Charl+0.007
 Sonny+0.007
 stret+0.007
die+0.007
Neg logit contributions
 ever-0.007
ad-0.006
years-0.006
bridge-0.006
 days-0.006
Token the
Token ID262
Feature activation+2.12e-03

Pos logit contributions
Charl+0.022
+0.022
 fuss+0.021
 ask+0.021
 Benjamin+0.021
Neg logit contributions
 ever-0.022
bridge-0.021
rest-0.020
aces-0.020
ad-0.019
Token at
Token ID379
Feature activation+1.01e-02

Pos logit contributions
+0.005
Charl+0.005
 ask+0.005
 insists+0.004
 stret+0.004
Neg logit contributions
 ever-0.005
ad-0.005
years-0.005
bridge-0.005
rest-0.005
Token them
Token ID606
Feature activation+8.77e-03

Pos logit contributions
bridge+0.019
 ever+0.018
aces+0.018
ad+0.018
years+0.017
Neg logit contributions
 ask-0.013
-0.012
 Benjamin-0.012
 Sonny-0.012
 fuss-0.011
Token.
Token ID13
Feature activation+1.64e-03

Pos logit contributions
years+0.016
 ever+0.015
bridge+0.015
ad+0.015
rest+0.014
Neg logit contributions
-0.012
 ask-0.012
 insists-0.011
 fuss-0.011
 stret-0.011
Token
Token ID198
Feature activation+5.01e-03

Pos logit contributions
 ever+0.003
 days+0.003
bridge+0.003
aces+0.002
ad+0.002
Neg logit contributions
Charl-0.002
-0.002
 stret-0.002
 fuss-0.002
aman-0.002
Token
Token ID198
Feature activation+6.73e-03

Pos logit contributions
 ever+0.009
ad+0.007
 days+0.007
lo+0.007
 of+0.007
Neg logit contributions
Charl-0.008
 stret-0.008
 habit-0.007
 fuss-0.007
 difference-0.007
Token"
Token ID1
Feature activation+2.30e-02

Pos logit contributions
 ever+0.013
bridge+0.011
 days+0.011
years+0.011
ad+0.011
Neg logit contributions
Charl-0.009
 difference-0.009
-0.009
 stret-0.008
ucker-0.008
TokenHello
Token ID15496
Feature activation-1.08e-02

Pos logit contributions
 ever+0.048
ad+0.043
years+0.043
bridge+0.042
aces+0.042
Neg logit contributions
-0.028
Charl-0.027
 ask-0.025
 stret-0.024
 insists-0.024
Token!"
Token ID2474
Feature activation-1.75e-03

Pos logit contributions
Charl+0.018
+0.017
 stret+0.016
 rinse+0.016
 insists+0.016
Neg logit contributions
 ever-0.018
ad-0.016
bridge-0.015
 days-0.015
rest-0.015
Token Anna
Token ID11735
Feature activation+2.75e-02

Pos logit contributions
+0.002
Charl+0.002
 ask+0.002
 insists+0.002
 Benjamin+0.002
Neg logit contributions
 ever-0.004
years-0.004
bridge-0.004
ad-0.004
rest-0.004
Token says
Token ID1139
Feature activation+1.39e-02

Pos logit contributions
 ever+0.062
ad+0.057
aces+0.055
bridge+0.054
years+0.053
Neg logit contributions
Charl-0.028
-0.027
 stret-0.025
 rinse-0.024
arl-0.024
Token.
Token ID13
Feature activation+9.24e-03

Pos logit contributions
bridge+0.026
 ever+0.025
rest+0.025
years+0.025
ad+0.025
Neg logit contributions
 ask-0.018
-0.017
 agree-0.016
 insists-0.016
 nod-0.016
Token house
Token ID2156
Feature activation+4.13e-03

Pos logit contributions
+0.010
Charl+0.010
 stret+0.009
 insists+0.009
 ask+0.009
Neg logit contributions
 ever-0.011
ad-0.010
bridge-0.010
years-0.010
aces-0.010
Token and
Token ID290
Feature activation+9.59e-03

Pos logit contributions
bridge+0.007
ad+0.007
rest+0.007
years+0.006
 ever+0.006
Neg logit contributions
-0.005
Charl-0.005
 ask-0.005
 Midnight-0.005
 stret-0.005
Token loved
Token ID6151
Feature activation+1.19e-03

Pos logit contributions
bridge+0.017
ad+0.016
aces+0.016
lo+0.015
 ever+0.015
Neg logit contributions
 ask-0.014
-0.013
Charl-0.013
 rinse-0.013
 Midnight-0.013
Token it
Token ID340
Feature activation+8.52e-03

Pos logit contributions
bridge+0.002
ad+0.002
 ever+0.002
aces+0.002
rest+0.002
Neg logit contributions
Charl-0.002
-0.002
 ask-0.002
 Midnight-0.002
die-0.002
Token there
Token ID612
Feature activation-6.30e-03

Pos logit contributions
bridge+0.018
ad+0.017
years+0.017
anes+0.016
pter+0.016
Neg logit contributions
Charl-0.010
-0.009
 Midnight-0.009
 ask-0.009
 habit-0.008
Token.
Token ID13
Feature activation-1.57e-03

Pos logit contributions
+0.007
Charl+0.007
 ask+0.007
 habit+0.006
 difference+0.006
Neg logit contributions
bridge-0.013
ad-0.012
years-0.012
aces-0.011
rest-0.011
Token Every
Token ID3887
Feature activation-6.35e-04

Pos logit contributions
Charl+0.002
+0.002
 stret+0.002
 rinse+0.002
 Benjamin+0.002
Neg logit contributions
 ever-0.003
ad-0.002
 days-0.002
aces-0.002
years-0.002
Token day
Token ID1110
Feature activation-7.88e-03

Pos logit contributions
+0.001
Charl+0.001
 ask+0.001
 insists+0.001
die+0.001
Neg logit contributions
 ever-0.001
years-0.001
bridge-0.001
aces-0.001
ad-0.001
Token,
Token ID11
Feature activation+8.05e-03

Pos logit contributions
+0.012
Charl+0.011
 ask+0.011
 Midnight+0.010
 Benjamin+0.010
Neg logit contributions
 ever-0.014
bridge-0.013
ad-0.013
years-0.012
aces-0.012
Token she
Token ID673
Feature activation+4.01e-03

Pos logit contributions
ad+0.016
bridge+0.016
rest+0.015
 ever+0.015
aces+0.015
Neg logit contributions
-0.010
 Midnight-0.010
 ask-0.010
 massage-0.009
Charl-0.009
Token would
Token ID561
Feature activation+1.22e-02

Pos logit contributions
 ever+0.008
ad+0.008
years+0.008
bridge+0.008
aces+0.007
Neg logit contributions
-0.005
Charl-0.005
 ask-0.004
 insists-0.004
 stret-0.004
Token tang
Token ID13875
Feature activation-3.92e-04

Pos logit contributions
 ever+0.021
ad+0.018
bridge+0.018
years+0.018
aces+0.018
Neg logit contributions
-0.016
Charl-0.016
 stret-0.014
 ask-0.014
 insists-0.014
Tokeny
Token ID88
Feature activation-1.60e-02

Pos logit contributions
+0.001
Charl+0.001
 stret+0.001
 ask+0.001
 insists+0.001
Neg logit contributions
 ever-0.001
ad-0.001
bridge-0.001
years-0.001
aces-0.001
Token sensation
Token ID18098
Feature activation+4.29e-03

Pos logit contributions
+0.027
Charl+0.027
 stret+0.025
 ask+0.025
 insists+0.025
Neg logit contributions
 ever-0.025
ad-0.022
bridge-0.022
years-0.022
aces-0.021
Token in
Token ID287
Feature activation+1.11e-02

Pos logit contributions
years+0.008
ad+0.007
 ever+0.007
bridge+0.007
aces+0.007
Neg logit contributions
 rinse-0.006
-0.005
 stret-0.005
 insists-0.005
 Benjamin-0.005
Token their
Token ID511
Feature activation+9.64e-03

Pos logit contributions
 ever+0.018
ad+0.016
 days+0.015
bridge+0.015
years+0.015
Neg logit contributions
-0.018
Charl-0.018
 stret-0.017
 insists-0.016
 ask-0.016
Token mouths
Token ID28552
Feature activation-1.79e-03

Pos logit contributions
 ever+0.017
ad+0.015
 days+0.015
years+0.014
aces+0.014
Neg logit contributions
Charl-0.015
-0.015
 Benjamin-0.014
 stret-0.013
 Sonny-0.013
Token.
Token ID13
Feature activation-5.55e-03

Pos logit contributions
+0.003
Charl+0.003
 rinse+0.002
 ask+0.002
 insists+0.002
Neg logit contributions
 ever-0.003
years-0.003
ad-0.003
bridge-0.003
rest-0.003
Token They
Token ID1119
Feature activation-1.14e-02

Pos logit contributions
Charl+0.010
 stret+0.010
heit+0.010
 difference+0.010
+0.010
Neg logit contributions
 ever-0.007
 days-0.006
ad-0.006
 sill-0.006
we-0.006
Token made
Token ID925
Feature activation+1.89e-02

Pos logit contributions
Charl+0.020
+0.019
 stret+0.019
arl+0.018
 difference+0.018
Neg logit contributions
 ever-0.018
ad-0.015
bridge-0.015
years-0.015
aces-0.014
Token funny
Token ID8258
Feature activation-1.85e-02

Pos logit contributions
 ever+0.023
ad+0.020
bridge+0.019
years+0.019
aces+0.018
Neg logit contributions
-0.039
Charl-0.039
 stret-0.036
 ask-0.036
 insists-0.036
Token faces
Token ID6698
Feature activation-8.09e-03

Pos logit contributions
+0.025
Charl+0.025
 stret+0.022
 ask+0.022
 insists+0.022
Neg logit contributions
 ever-0.035
ad-0.032
bridge-0.031
years-0.031
aces-0.031
Token?
Token ID30
Feature activation-7.24e-03

Pos logit contributions
Charl+0.001
+0.001
 stret+0.001
 insists+0.001
 ask+0.001
Neg logit contributions
 ever-0.002
ad-0.002
bridge-0.002
aces-0.002
years-0.002
Token Do
Token ID2141
Feature activation+2.53e-03

Pos logit contributions
+0.010
Charl+0.010
 ask+0.009
 stret+0.009
 insists+0.009
Neg logit contributions
 ever-0.013
ad-0.012
bridge-0.012
years-0.012
aces-0.012
Token you
Token ID345
Feature activation+3.80e-03

Pos logit contributions
year+0.005
bridge+0.005
 ever+0.005
years+0.005
iest+0.005
Neg logit contributions
-0.003
 ask-0.003
 Midnight-0.003
 Benjamin-0.003
Charl-0.003
Token know
Token ID760
Feature activation-4.24e-03

Pos logit contributions
 ever+0.008
ad+0.008
bridge+0.008
years+0.008
aces+0.008
Neg logit contributions
-0.004
Charl-0.004
 ask-0.003
 stret-0.003
 insists-0.003
Token how
Token ID703
Feature activation+1.21e-03

Pos logit contributions
+0.006
Charl+0.006
 stret+0.005
 insists+0.005
die+0.005
Neg logit contributions
 ever-0.008
ad-0.008
bridge-0.007
years-0.007
rest-0.007
Token dangerous
Token ID4923
Feature activation-9.89e-03

Pos logit contributions
 ever+0.002
ad+0.002
bridge+0.002
years+0.002
aces+0.002
Neg logit contributions
-0.002
Charl-0.002
 ask-0.002
 insists-0.002
 stret-0.002
Token this
Token ID428
Feature activation+1.44e-02

Pos logit contributions
+0.016
Charl+0.015
 ask+0.014
 stret+0.014
 Benjamin+0.014
Neg logit contributions
 ever-0.016
years-0.015
ad-0.015
bridge-0.015
aces-0.014
Token is
Token ID318
Feature activation+3.71e-02

Pos logit contributions
 ever+0.026
ad+0.023
bridge+0.023
rest+0.022
aces+0.022
Neg logit contributions
Charl-0.021
-0.021
 stret-0.019
 insists-0.019
 ask-0.019
Token?
Token ID30
Feature activation-2.20e-03

Pos logit contributions
 ever+0.072
rest+0.061
ad+0.060
 days+0.059
aces+0.059
Neg logit contributions
Charl-0.053
-0.049
 rinse-0.047
 mental-0.047
 stret-0.046
Token You
Token ID921
Feature activation-3.73e-04

Pos logit contributions
+0.003
Charl+0.003
 ask+0.003
 stret+0.003
 insists+0.003
Neg logit contributions
 ever-0.004
ad-0.004
bridge-0.004
years-0.004
aces-0.004
Token could
Token ID714
Feature activation+8.98e-04

Pos logit contributions
+0.000
Charl+0.000
 ask+0.000
 insists+0.000
 rinse+0.000
Neg logit contributions
 ever-0.001
years-0.001
bridge-0.001
ad-0.001
 days-0.001
Token looked
Token ID3114
Feature activation+3.43e-03

Pos logit contributions
years+0.018
ad+0.018
bridge+0.017
 ever+0.017
aces+0.017
Neg logit contributions
-0.015
Charl-0.014
 insists-0.014
 rinse-0.013
 ask-0.013
Token like
Token ID588
Feature activation+1.22e-02

Pos logit contributions
 ever+0.006
ad+0.005
bridge+0.005
years+0.005
aces+0.005
Neg logit contributions
-0.006
Charl-0.005
 stret-0.005
 ask-0.005
 insists-0.005
Token it
Token ID340
Feature activation+1.05e-02

Pos logit contributions
years+0.020
 ever+0.020
aces+0.019
bridge+0.019
ad+0.019
Neg logit contributions
-0.017
Charl-0.017
 Benjamin-0.017
 Sonny-0.016
 Midnight-0.016
Token was
Token ID373
Feature activation+1.30e-02

Pos logit contributions
years+0.019
ad+0.018
year+0.017
bridge+0.017
 ever+0.016
Neg logit contributions
-0.015
 ask-0.013
Charl-0.013
 Midnight-0.013
 insists-0.013
Token going
Token ID1016
Feature activation+3.34e-02

Pos logit contributions
 ever+0.019
years+0.018
bridge+0.018
ad+0.018
aces+0.017
Neg logit contributions
-0.022
Charl-0.021
 ask-0.020
 stret-0.020
 rinse-0.020
Token to
Token ID284
Feature activation+3.79e-03

Pos logit contributions
years+0.057
bridge+0.057
ad+0.056
 ever+0.056
aces+0.055
Neg logit contributions
-0.047
 ask-0.042
 stret-0.041
Charl-0.040
 Benjamin-0.039
Token fall
Token ID2121
Feature activation-5.15e-03

Pos logit contributions
 ever+0.007
years+0.006
bridge+0.006
aces+0.006
ad+0.006
Neg logit contributions
-0.005
Charl-0.005
 ask-0.005
 stret-0.005
 rinse-0.005
Token out
Token ID503
Feature activation+1.66e-02

Pos logit contributions
+0.008
Charl+0.008
 stret+0.007
 ask+0.007
 insists+0.007
Neg logit contributions
 ever-0.009
years-0.008
ad-0.008
bridge-0.008
aces-0.007
Token of
Token ID286
Feature activation-1.97e-04

Pos logit contributions
years+0.027
bridge+0.025
aces+0.025
ad+0.025
 ever+0.024
Neg logit contributions
-0.024
 ask-0.023
 rinse-0.023
 difference-0.022
 fuss-0.022
Token the
Token ID262
Feature activation+8.90e-03

Pos logit contributions
+0.000
Charl+0.000
 stret+0.000
 ask+0.000
 fuss+0.000
Neg logit contributions
 ever-0.000
years-0.000
bridge-0.000
aces-0.000
ad-0.000
Token sky
Token ID6766
Feature activation+4.18e-03

Pos logit contributions
 ever+0.015
ad+0.013
bridge+0.013
years+0.013
aces+0.013
Neg logit contributions
-0.014
Charl-0.014
 ask-0.013
 stret-0.013
 insists-0.013
Token.
Token ID13
Feature activation+8.43e-03

Pos logit contributions
 ask+0.010
+0.009
 agree+0.009
 promise+0.008
 stret+0.008
Neg logit contributions
years-0.017
bridge-0.017
rest-0.017
 ever-0.017
aces-0.016
Token He
Token ID679
Feature activation-3.65e-03

Pos logit contributions
 ever+0.013
ad+0.012
bridge+0.012
years+0.012
aces+0.011
Neg logit contributions
-0.014
Charl-0.014
 stret-0.013
 ask-0.013
 insists-0.013
Token tried
Token ID3088
Feature activation-1.44e-02

Pos logit contributions
+0.005
Charl+0.005
 ask+0.005
 insists+0.004
die+0.004
Neg logit contributions
 ever-0.007
bridge-0.006
ad-0.006
aces-0.006
years-0.006
Token to
Token ID284
Feature activation-1.90e-02

Pos logit contributions
+0.028
Charl+0.027
 stret+0.026
 insists+0.025
 Benjamin+0.025
Neg logit contributions
 ever-0.020
ad-0.017
years-0.016
bridge-0.016
 days-0.016
Token rock
Token ID3881
Feature activation-4.01e-02

Pos logit contributions
+0.023
Charl+0.022
 ask+0.022
 stret+0.021
 rinse+0.021
Neg logit contributions
 ever-0.038
years-0.035
bridge-0.035
aces-0.035
ad-0.034
Token the
Token ID262
Feature activation-8.69e-03

Pos logit contributions
 ask+0.052
+0.051
 stret+0.047
 insists+0.047
 rinse+0.047
Neg logit contributions
years-0.071
 ever-0.071
bridge-0.070
aces-0.066
rd-0.065
Token big
Token ID1263
Feature activation-8.92e-03

Pos logit contributions
+0.014
Charl+0.014
 stret+0.013
 ask+0.013
 Benjamin+0.013
Neg logit contributions
 ever-0.014
ad-0.013
bridge-0.013
years-0.012
aces-0.012
Token rock
Token ID3881
Feature activation-3.54e-03

Pos logit contributions
+0.012
 ask+0.012
 insists+0.011
 fuss+0.011
 difference+0.011
Neg logit contributions
 ever-0.017
years-0.016
bridge-0.015
rest-0.015
ad-0.015
Token.
Token ID13
Feature activation+3.18e-03

Pos logit contributions
 ask+0.003
+0.003
 insists+0.003
 agree+0.003
 promise+0.003
Neg logit contributions
years-0.008
bridge-0.007
year-0.007
ad-0.007
rest-0.007
Token But
Token ID887
Feature activation-1.16e-02

Pos logit contributions
 ever+0.006
ad+0.006
bridge+0.006
years+0.006
rest+0.005
Neg logit contributions
-0.004
Charl-0.004
 ask-0.004
 insists-0.004
 stret-0.004
Token the
Token ID262
Feature activation-1.71e-02

Pos logit contributions
+0.016
 ask+0.015
 Benjamin+0.014
 rinse+0.014
 Sonny+0.014
Neg logit contributions
bridge-0.021
years-0.020
 ever-0.020
ad-0.020
aces-0.020
Token took
Token ID1718
Feature activation-2.97e-03

Pos logit contributions
ad+0.021
bridge+0.021
 ever+0.021
aces+0.020
rest+0.020
Neg logit contributions
-0.017
 rinse-0.016
 ask-0.016
 Midnight-0.015
 insists-0.015
Token a
Token ID257
Feature activation-1.12e-02

Pos logit contributions
+0.005
Charl+0.005
 ask+0.004
 stret+0.004
 insists+0.004
Neg logit contributions
 ever-0.005
ad-0.004
bridge-0.004
years-0.004
aces-0.004
Token long
Token ID890
Feature activation+1.27e-02

Pos logit contributions
Charl+0.021
 insists+0.019
die+0.019
ealing+0.019
ucker+0.019
Neg logit contributions
 ever-0.017
 of-0.014
t-0.013
 days-0.012
iest-0.012
Token time
Token ID640
Feature activation-1.64e-03

Pos logit contributions
 ever+0.022
ad+0.019
bridge+0.019
 days+0.018
aces+0.018
Neg logit contributions
Charl-0.020
-0.019
 insists-0.018
 ask-0.018
 Sonny-0.018
Token to
Token ID284
Feature activation+3.42e-03

Pos logit contributions
+0.002
 ask+0.002
 agree+0.002
Charl+0.002
 rinse+0.002
Neg logit contributions
ad-0.003
years-0.003
bridge-0.003
rest-0.003
 ever-0.003
Token cook
Token ID4255
Feature activation-3.16e-02

Pos logit contributions
 ever+0.007
ad+0.006
bridge+0.006
 days+0.006
rest+0.006
Neg logit contributions
Charl-0.005
-0.004
die-0.004
ucker-0.004
 stret-0.004
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
+0.053
Charl+0.053
 stret+0.049
 ask+0.049
 insists+0.049
Neg logit contributions
 ever-0.050
ad-0.044
bridge-0.043
years-0.043
aces-0.042
Token pizza
Token ID14256
Feature activation-2.27e-02

Pos logit contributions
+0.016
Charl+0.015
 ask+0.014
 stret+0.014
 insists+0.014
Neg logit contributions
 ever-0.019
ad-0.017
years-0.017
bridge-0.017
aces-0.016
Token.
Token ID13
Feature activation-5.81e-03

Pos logit contributions
+0.038
Charl+0.036
 ask+0.034
 stret+0.034
 insists+0.034
Neg logit contributions
 ever-0.035
years-0.032
ad-0.032
bridge-0.032
aces-0.031
Token Finally
Token ID9461
Feature activation+3.10e-03

Pos logit contributions
Charl+0.011
heit+0.010
 stret+0.010
itch+0.010
 Sonny+0.010
Neg logit contributions
 ever-0.007
 days-0.007
 of-0.006
bridge-0.006
 next-0.006
Token,
Token ID11
Feature activation-4.28e-03

Pos logit contributions
 ever+0.005
ad+0.004
 days+0.004
bridge+0.004
years+0.004
Neg logit contributions
Charl-0.005
-0.005
 stret-0.005
die-0.005
 insists-0.005
Token?"
Token ID1701
Feature activation-4.06e-03

Pos logit contributions
+0.000
Charl+0.000
 stret+0.000
 ask+0.000
 insists+0.000
Neg logit contributions
 ever-0.001
ad-0.001
bridge-0.001
years-0.001
aces-0.001
Token Lily
Token ID20037
Feature activation+6.90e-03

Pos logit contributions
Charl+0.006
arl+0.006
heit+0.006
 insists+0.006
+0.006
Neg logit contributions
 ever-0.007
ad-0.006
 days-0.006
aces-0.005
years-0.005
Token said
Token ID531
Feature activation+6.92e-03

Pos logit contributions
 ever+0.012
ad+0.011
years+0.010
bridge+0.010
aces+0.010
Neg logit contributions
Charl-0.010
-0.010
 stret-0.010
arl-0.010
 rinse-0.009
Token,
Token ID11
Feature activation+8.47e-03

Pos logit contributions
 ever+0.012
ad+0.011
bridge+0.011
years+0.011
aces+0.011
Neg logit contributions
-0.010
Charl-0.010
 stret-0.009
 ask-0.009
 insists-0.009
Token "
Token ID366
Feature activation+1.67e-02

Pos logit contributions
 ever+0.017
ad+0.015
years+0.015
bridge+0.014
 days+0.014
Neg logit contributions
-0.011
Charl-0.011
 difference-0.010
 insists-0.010
ucker-0.010
TokenI
Token ID40
Feature activation-3.16e-02

Pos logit contributions
 ever+0.034
aces+0.033
ad+0.033
 days+0.032
years+0.032
Neg logit contributions
Charl-0.020
-0.018
Elsa-0.016
Ben-0.015
Ba-0.015
Token'm
Token ID1101
Feature activation-9.03e-03

Pos logit contributions
+0.038
Charl+0.035
 ask+0.034
 insists+0.032
 rinse+0.032
Neg logit contributions
 ever-0.063
years-0.062
bridge-0.061
aces-0.061
ad-0.061
Token helping
Token ID5742
Feature activation-8.44e-03

Pos logit contributions
Charl+0.015
+0.014
 ask+0.014
 Benjamin+0.014
 stret+0.014
Neg logit contributions
 ever-0.014
ad-0.013
bridge-0.013
aces-0.013
years-0.013
Token my
Token ID616
Feature activation-1.44e-02

Pos logit contributions
+0.014
Charl+0.014
 stret+0.013
 insists+0.013
ucker+0.013
Neg logit contributions
 ever-0.014
ad-0.012
years-0.012
rest-0.011
 days-0.011
Token mom
Token ID1995
Feature activation+3.02e-03

Pos logit contributions
+0.019
Charl+0.019
 stret+0.017
 ask+0.017
 insists+0.017
Neg logit contributions
 ever-0.028
ad-0.025
bridge-0.025
years-0.024
aces-0.024
Tokenmy
Token ID1820
Feature activation-1.28e-02

Pos logit contributions
 ever+0.005
ad+0.005
bridge+0.005
years+0.005
aces+0.005
Neg logit contributions
-0.004
Charl-0.004
 ask-0.004
 insists-0.004
 stret-0.004
Token She
Token ID1375
Feature activation-3.52e-03

Pos logit contributions
 ever+0.002
ad+0.002
aces+0.002
 sill+0.002
years+0.001
Neg logit contributions
 stret-0.005
ench-0.005
heit-0.005
 habit-0.005
-0.005
Token picked
Token ID6497
Feature activation-1.22e-02

Pos logit contributions
+0.005
Charl+0.005
 stret+0.005
 ask+0.005
 insists+0.005
Neg logit contributions
 ever-0.006
ad-0.006
bridge-0.005
years-0.005
aces-0.005
Token up
Token ID510
Feature activation+3.73e-03

Pos logit contributions
Charl+0.023
+0.022
 stret+0.021
 difference+0.020
die+0.020
Neg logit contributions
 ever-0.017
ad-0.016
rest-0.015
years-0.015
bridge-0.014
Token the
Token ID262
Feature activation+7.45e-03

Pos logit contributions
 ever+0.007
bridge+0.007
rest+0.007
years+0.007
aces+0.007
Neg logit contributions
 Benjamin-0.005
 Midnight-0.005
 Coc-0.005
 Woo-0.004
 ask-0.004
Token other
Token ID584
Feature activation+2.88e-03

Pos logit contributions
 ever+0.013
ad+0.012
bridge+0.011
years+0.011
rest+0.011
Neg logit contributions
Charl-0.012
-0.011
 stret-0.010
 Midnight-0.010
 rinse-0.010
Token oy
Token ID35104
Feature activation-3.60e-02

Pos logit contributions
 ever+0.005
years+0.005
bridge+0.005
aces+0.005
year+0.005
Neg logit contributions
-0.004
 ask-0.004
 fuss-0.004
 insists-0.003
 difference-0.003
Tokenster
Token ID1706
Feature activation-7.73e-03

Pos logit contributions
Charl+0.053
+0.051
 stret+0.048
 insists+0.047
 Benjamin+0.046
Neg logit contributions
 ever-0.066
ad-0.060
bridge-0.059
aces-0.057
years-0.057
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
+0.010
 ask+0.009
 rinse+0.009
Charl+0.009
die+0.009
Neg logit contributions
 ever-0.014
years-0.014
bridge-0.014
ad-0.013
rest-0.013
Token did
Token ID750
Feature activation+2.71e-02

Pos logit contributions
+0.017
Charl+0.017
 stret+0.015
 insists+0.015
die+0.015
Neg logit contributions
 ever-0.021
ad-0.019
bridge-0.018
years-0.018
aces-0.018
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
 ever+0.040
ad+0.035
bridge+0.034
years+0.034
aces+0.033
Neg logit contributions
-0.049
Charl-0.049
 stret-0.045
 ask-0.045
 insists-0.045
Token same
Token ID976
Feature activation-1.21e-03

Pos logit contributions
Charl+0.032
+0.028
 Midnight+0.028
 stret+0.028
ucker+0.027
Neg logit contributions
 ever-0.021
ad-0.019
rest-0.017
bridge-0.017
 next-0.017
Token of
Token ID286
Feature activation+2.11e-02

Pos logit contributions
years+0.008
 ever+0.008
ad+0.007
rest+0.007
aces+0.007
Neg logit contributions
-0.017
 rinse-0.016
Charl-0.016
 stret-0.016
arl-0.015
Token hot
Token ID3024
Feature activation-1.46e-02

Pos logit contributions
 ever+0.041
bridge+0.037
ad+0.037
years+0.037
aces+0.037
Neg logit contributions
-0.027
Charl-0.026
 ask-0.025
 stret-0.024
 rinse-0.024
Token water
Token ID1660
Feature activation-3.55e-02

Pos logit contributions
+0.020
Charl+0.018
 rinse+0.017
 ask+0.017
 stret+0.017
Neg logit contributions
 ever-0.028
years-0.027
bridge-0.026
ad-0.026
aces-0.025
Token.
Token ID13
Feature activation-3.59e-03

Pos logit contributions
+0.058
Charl+0.056
 stret+0.053
 ask+0.053
 rinse+0.052
Neg logit contributions
 ever-0.057
years-0.052
ad-0.051
bridge-0.051
aces-0.049
Token She
Token ID1375
Feature activation-9.46e-03

Pos logit contributions
 stret+0.007
 difference+0.007
 fuss+0.007
Charl+0.007
 habit+0.007
Neg logit contributions
 ever-0.004
aces-0.004
ad-0.004
years-0.004
 days-0.004
Token drank
Token ID24070
Feature activation-3.98e-02

Pos logit contributions
+0.013
Charl+0.012
 rinse+0.012
 ask+0.012
 insists+0.011
Neg logit contributions
 ever-0.018
ad-0.017
bridge-0.017
years-0.017
rest-0.016
Token some
Token ID617
Feature activation+3.55e-03

Pos logit contributions
+0.073
Charl+0.071
 stret+0.067
 ask+0.066
 rinse+0.066
Neg logit contributions
 ever-0.057
ad-0.050
years-0.050
bridge-0.049
aces-0.048
Token of
Token ID286
Feature activation-4.71e-03

Pos logit contributions
 ever+0.006
ad+0.006
years+0.006
bridge+0.006
aces+0.006
Neg logit contributions
-0.005
Charl-0.005
 rinse-0.005
 stret-0.005
 ask-0.005
Token the
Token ID262
Feature activation+4.48e-03

Pos logit contributions
+0.009
Charl+0.009
 stret+0.008
 ask+0.008
 insists+0.008
Neg logit contributions
 ever-0.007
ad-0.006
bridge-0.006
years-0.006
aces-0.006
Token water
Token ID1660
Feature activation-3.13e-02

Pos logit contributions
 ever+0.009
years+0.009
ad+0.009
bridge+0.009
aces+0.009
Neg logit contributions
-0.005
 rinse-0.005
 stret-0.005
 fuss-0.005
 ask-0.004
Token and
Token ID290
Feature activation-5.19e-03

Pos logit contributions
+0.046
Charl+0.042
 rinse+0.042
 ask+0.041
 stret+0.040
Neg logit contributions
 ever-0.054
years-0.053
ad-0.051
bridge-0.051
rest-0.048
Token Jack
Token ID3619
Feature activation-1.52e-02

Pos logit contributions
+0.028
Charl+0.027
 stret+0.025
 ask+0.025
 insists+0.025
Neg logit contributions
 ever-0.033
ad-0.030
years-0.029
bridge-0.029
aces-0.029
Token,
Token ID11
Feature activation-1.85e-03

Pos logit contributions
+0.026
Charl+0.025
 stret+0.024
 ask+0.023
 rinse+0.023
Neg logit contributions
 ever-0.024
ad-0.021
years-0.021
bridge-0.021
aces-0.020
Token asked
Token ID1965
Feature activation-4.63e-03

Pos logit contributions
+0.002
Charl+0.002
 stret+0.002
 ask+0.002
 insists+0.002
Neg logit contributions
 ever-0.004
ad-0.004
bridge-0.004
years-0.004
aces-0.004
Token L
Token ID406
Feature activation-4.55e-03

Pos logit contributions
+0.007
Charl+0.007
 ask+0.006
 Benjamin+0.006
 Sonny+0.006
Neg logit contributions
 ever-0.008
bridge-0.007
ad-0.007
aces-0.007
years-0.007
Tokenizz
Token ID6457
Feature activation+7.49e-04

Pos logit contributions
+0.009
Charl+0.009
 stret+0.008
 ask+0.008
 insists+0.008
Neg logit contributions
 ever-0.006
ad-0.005
bridge-0.005
years-0.005
aces-0.005
Tokenie
Token ID494
Feature activation-3.25e-02

Pos logit contributions
 ever+0.001
ad+0.001
years+0.001
rest+0.001
bridge+0.001
Neg logit contributions
-0.002
Charl-0.002
 stret-0.001
 rinse-0.001
 insists-0.001
Token to
Token ID284
Feature activation-9.85e-03

Pos logit contributions
+0.048
Charl+0.047
 stret+0.044
 rinse+0.042
 insists+0.042
Neg logit contributions
 ever-0.059
ad-0.053
years-0.052
aces-0.051
bridge-0.050
Token give
Token ID1577
Feature activation-3.84e-02

Pos logit contributions
+0.013
Charl+0.013
 stret+0.012
 insists+0.012
die+0.012
Neg logit contributions
 ever-0.019
ad-0.017
bridge-0.017
years-0.017
rest-0.016
Token him
Token ID683
Feature activation-1.03e-02

Pos logit contributions
+0.061
Charl+0.060
 Benjamin+0.059
 ask+0.058
 Sonny+0.057
Neg logit contributions
 ever-0.061
bridge-0.059
aces-0.056
years-0.054
ad-0.054
Token her
Token ID607
Feature activation+8.86e-04

Pos logit contributions
+0.017
Charl+0.016
 ask+0.016
die+0.016
 Benjamin+0.016
Neg logit contributions
 ever-0.015
bridge-0.015
years-0.014
aces-0.014
ad-0.013
Token stick
Token ID4859
Feature activation-2.35e-03

Pos logit contributions
 ever+0.001
years+0.001
bridge+0.001
ad+0.001
aces+0.001
Neg logit contributions
-0.001
Charl-0.001
 ask-0.001
 stret-0.001
 rinse-0.001