TOP ACTIVATIONS
MAX = 0.956

a questionable choice against rocket launchers and grenades .
marketing push for its Surface tablets as well as the Xbox
it , Cance ll ara said .
costly war in the Middle East and for saying the fight
The president claimed that Flake was c aught
Pelosi , producing a miss hap en mass of special -
ak city and parts of Roh t ak district and H
C ance ll ara saw it as an
by blocking national highway connecting Roh t ak to Delhi .
lit ers into the mash tun , then add the mal
in the road from Cast aic to his home in Lake
Sunday that Jeff Flake ( y )
news here , Flake tweeted Saturday after his comments
, a professor of Middle East history at Shawn ee State
LO OM Ra ising the debt ceiling is one
specific countries in the Middle East . The author
slain by a company of Roh ir rim . Merry and
five Google Android Honey comb tablets that have come out since
Senate floor last month , Flake announced his plans to retire
the OG . Nor the FG . However , if we

MIN ACTIVATIONS
MIN = -1.004

1987 - 1989 - 4 Pierce Bros nan films , 1995
for a few other fr atern ities are also in a
higher in charter schools because charter school teachers are unhappy or
turnover may be higher in charter schools because charter school teachers
few that do practice Lac anian psycho analysis in such settings
was twice as high at charter schools ( St uit and
traditional public schools and at charter schools . Te
retailer ? Fred Pierce : I 'll tell what
relationship with the CEO . Blank fe in and Cohn vacation
in a time when Lac anian clinical practice is not even
it means to practice Lac anian psycho analysis . This is
Exc iting
scope , and practice Lac anian psycho analysis every day .
. Wells Fargo , JPMorgan Chase , and Cit ib ank
of the bank . JPMorgan Chase , Bank of America ,
. Lines are going to pile on for AAA games ,
losing ground to rivals like Dom ino 's Pizza .
https
Choice at Vanderbilt University compared charter schools with traditional public schools
the person typically enjoys . Blank et for ts are good

INTERVAL 0.466 - 0.956
CONTAINS 0.509%

NS via Getty Images ) Indiana Gov . Mike Pence Pence
Arabs or Muslims sav ages , nor
financial results in conjunction with tax filings . Stephen
have changed . So checks um everything and compare the checks
good launch conditions . The sun was setting . The king

INTERVAL -0.024 - 0.466
CONTAINS 56.370%

try to attack . I think tomorrow is the best for
after the bigger fish at Sea World
is simply not worth it . What
Trump closing the gap with Mrs . Clinton largely because
ills and talents Secondly , the content gives some

INTERVAL -0.514 - -0.024
CONTAINS 42.900%

. Cand ace Hilton said she s
. The risk comes after the rule change when
or Twitter , Lawrence lashed out at the sites that permitted
2013 Starting in 2013 , some EC 2 instance
with Red fer ne , who reports seeing a party of

INTERVAL -1.004 - -0.514
CONTAINS 0.220%

s making in Miami . He s
manager . He had an aura , as did his assistant
Your Inner Ass hole is never off the alert
retailer ? Fred Pierce : I 'll tell what
{ ( 6 s )} Ng 6 { ( 7 s
Token a
Token ID257
Feature activation-4.03e-02

Pos logit contributions
 GOODMAN+0.113
 wip+0.109
inav+0.108
 exceptions+0.106
 sparing+0.104
Neg logit contributions
naire-0.185
-0.182
naissance-0.179
��-0.178
-0.172
Token questionable
Token ID18269
Feature activation+2.85e-01

Pos logit contributions
naire+0.036
+0.035
naissance+0.034
��+0.034
+0.033
Neg logit contributions
 GOODMAN-0.029
 wip-0.028
 exceptions-0.028
inav-0.028
 sparing-0.027
Token choice
Token ID3572
Feature activation+2.60e-01

Pos logit contributions
 GOODMAN+0.199
 wip+0.192
inav+0.192
 exceptions+0.189
 sparing+0.185
Neg logit contributions
naire-0.257
-0.253
naissance-0.249
��-0.247
-0.237
Token against
Token ID1028
Feature activation+2.06e-01

Pos logit contributions
 GOODMAN+0.196
inav+0.190
 wip+0.189
 exceptions+0.185
 sparing+0.182
Neg logit contributions
naire-0.220
-0.217
naissance-0.212
��-0.210
-0.202
Token rocket
Token ID10701
Feature activation+1.85e-01

Pos logit contributions
 GOODMAN+0.130
inav+0.125
 wip+0.124
 exceptions+0.121
 sparing+0.119
Neg logit contributions
naire-0.199
-0.197
naissance-0.193
��-0.192
-0.185
Token launchers
Token ID41065
Feature activation+9.56e-01

Pos logit contributions
 GOODMAN+0.123
 wip+0.118
inav+0.118
 exceptions+0.116
 sparing+0.114
Neg logit contributions
naire-0.174
-0.171
naissance-0.168
��-0.167
-0.161
Token and
Token ID290
Feature activation+1.35e-01

Pos logit contributions
 GOODMAN+0.729
inav+0.706
 wip+0.705
 exceptions+0.692
 sparing+0.679
Neg logit contributions
naire-0.799
-0.788
naissance-0.773
��-0.765
-0.734
Token grenades
Token ID28850
Feature activation+5.14e-01

Pos logit contributions
 GOODMAN+0.091
inav+0.088
 wip+0.088
 exceptions+0.086
 sparing+0.084
Neg logit contributions
naire-0.124
-0.122
naissance-0.120
��-0.119
-0.114
Token.
Token ID13
Feature activation+1.23e-01

Pos logit contributions
 GOODMAN+0.404
inav+0.392
 wip+0.391
 exceptions+0.384
 sparing+0.377
Neg logit contributions
naire-0.418
-0.412
naissance-0.404
��-0.400
-0.383
Token
Token ID198
Feature activation+9.55e-02

Pos logit contributions
 GOODMAN+0.099
 wip+0.096
inav+0.096
 exceptions+0.095
 sparing+0.093
Neg logit contributions
naire-0.098
-0.096
naissance-0.094
��-0.093
-0.089
Token
Token ID198
Feature activation+6.59e-02

Pos logit contributions
 GOODMAN+0.076
 wip+0.074
inav+0.074
 exceptions+0.072
 sparing+0.071
Neg logit contributions
naire-0.077
-0.075
naissance-0.074
��-0.073
-0.070
Token marketing
Token ID7124
Feature activation-1.62e-01

Pos logit contributions
naire+0.054
+0.053
naissance+0.052
��+0.052
+0.050
Neg logit contributions
 GOODMAN-0.040
 wip-0.038
inav-0.038
 exceptions-0.038
 sparing-0.037
Token push
Token ID4574
Feature activation-2.05e-01

Pos logit contributions
naire+0.141
+0.140
naissance+0.137
��+0.137
+0.130
Neg logit contributions
 GOODMAN-0.116
 wip-0.114
inav-0.113
 exceptions-0.112
 sparing-0.110
Token for
Token ID329
Feature activation-1.09e-01

Pos logit contributions
naire+0.178
+0.176
naissance+0.173
��+0.173
+0.165
Neg logit contributions
 GOODMAN-0.149
 wip-0.145
inav-0.144
 exceptions-0.143
 sparing-0.141
Token its
Token ID663
Feature activation+1.30e-03

Pos logit contributions
naire+0.105
+0.104
naissance+0.102
��+0.101
+0.097
Neg logit contributions
 GOODMAN-0.069
inav-0.066
 wip-0.066
 exceptions-0.065
 sparing-0.063
Token Surface
Token ID20321
Feature activation+3.37e-02

Pos logit contributions
 GOODMAN+0.001
 wip+0.001
inav+0.001
 exceptions+0.001
 sparing+0.001
Neg logit contributions
naire-0.001
-0.001
naissance-0.001
��-0.001
-0.001
Token tablets
Token ID17255
Feature activation+9.13e-01

Pos logit contributions
 GOODMAN+0.011
 wip+0.010
inav+0.010
 exceptions+0.010
 sparing+0.009
Neg logit contributions
naire-0.043
-0.042
��-0.042
naissance-0.042
-0.041
Token as
Token ID355
Feature activation+1.23e-01

Pos logit contributions
 GOODMAN+0.691
 wip+0.672
inav+0.669
 exceptions+0.661
 sparing+0.651
Neg logit contributions
naire-0.768
-0.756
naissance-0.741
��-0.739
-0.705
Token well
Token ID880
Feature activation+1.65e-01

Pos logit contributions
 GOODMAN+0.076
inav+0.073
 wip+0.073
 exceptions+0.072
 sparing+0.070
Neg logit contributions
naire-0.121
-0.119
naissance-0.117
��-0.116
-0.112
Token as
Token ID355
Feature activation+1.91e-01

Pos logit contributions
 GOODMAN+0.095
inav+0.091
 wip+0.091
 exceptions+0.088
 sparing+0.086
Neg logit contributions
naire-0.168
-0.167
naissance-0.164
��-0.162
-0.157
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
 GOODMAN+0.111
inav+0.106
 wip+0.106
 exceptions+0.103
 sparing+0.101
Neg logit contributions
naire-0.195
-0.193
naissance-0.190
��-0.188
-0.182
Token Xbox
Token ID9445
Feature activation-1.70e-02

Pos logit contributions
 GOODMAN+0.089
 wip+0.085
inav+0.085
 exceptions+0.084
 sparing+0.082
Neg logit contributions
naire-0.116
-0.115
naissance-0.113
��-0.112
-0.107
Token it
Token ID340
Feature activation-1.68e-01

Pos logit contributions
naire+0.088
+0.086
naissance+0.085
��+0.084
+0.081
Neg logit contributions
 GOODMAN-0.066
 wip-0.063
inav-0.063
 exceptions-0.062
 sparing-0.061
Token,
Token ID11
Feature activation-1.16e-01

Pos logit contributions
naire+0.136
+0.134
naissance+0.131
��+0.130
+0.124
Neg logit contributions
 GOODMAN-0.133
 wip-0.129
inav-0.129
 exceptions-0.127
 sparing-0.125
Token
Token ID447
Feature activation+5.51e-02

Pos logit contributions
naire+0.098
+0.096
naissance+0.094
��+0.094
+0.090
Neg logit contributions
 GOODMAN-0.088
 wip-0.085
inav-0.085
 exceptions-0.084
 sparing-0.082
Token
Token ID251
Feature activation-2.84e-01

Pos logit contributions
 GOODMAN+0.074
 wip+0.072
inav+0.072
 exceptions+0.072
 sparing+0.071
Neg logit contributions
naire-0.014
-0.013
naissance-0.013
��-0.012
 dominates-0.010
Token Cance
Token ID43780
Feature activation-1.45e-01

Pos logit contributions
naire+0.239
+0.235
naissance+0.231
��+0.229
+0.219
Neg logit contributions
 GOODMAN-0.215
inav-0.209
 wip-0.208
 exceptions-0.205
 sparing-0.201
Tokenll
Token ID297
Feature activation+8.99e-01

Pos logit contributions
naire+0.172
+0.169
naissance+0.167
��+0.165
+0.161
Neg logit contributions
 GOODMAN-0.061
 wip-0.058
inav-0.057
 exceptions-0.055
 sparing-0.054
Tokenara
Token ID3301
Feature activation+5.34e-02

Pos logit contributions
 GOODMAN+0.759
inav+0.743
 wip+0.736
 exceptions+0.730
 sparing+0.717
Neg logit contributions
naire-0.671
-0.662
naissance-0.648
��-0.644
-0.612
Token said
Token ID531
Feature activation+3.83e-01

Pos logit contributions
 GOODMAN+0.038
 wip+0.037
inav+0.037
 exceptions+0.036
 sparing+0.036
Neg logit contributions
naire-0.047
-0.046
naissance-0.046
��-0.045
-0.043
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
 GOODMAN+0.299
 wip+0.289
inav+0.289
 exceptions+0.284
 sparing+0.280
Neg logit contributions
naire-0.314
-0.309
naissance-0.303
��-0.301
-0.288
Token
Token ID564
Feature activation+3.34e-02

Pos logit contributions
 GOODMAN+0.190
 wip+0.184
inav+0.184
 exceptions+0.181
 sparing+0.178
Neg logit contributions
naire-0.186
-0.183
naissance-0.180
��-0.178
-0.170
Token
Token ID250
Feature activation+3.87e-02

Pos logit contributions
 GOODMAN+0.041
 wip+0.041
inav+0.041
 exceptions+0.040
 sparing+0.040
Neg logit contributions
naire-0.012
-0.011
naissance-0.011
��-0.011
 dominates-0.009
Token costly
Token ID16378
Feature activation+2.70e-01

Pos logit contributions
 GOODMAN+0.082
 wip+0.079
inav+0.079
 exceptions+0.077
 sparing+0.076
Neg logit contributions
naire-0.122
-0.120
naissance-0.118
��-0.117
-0.113
Token war
Token ID1175
Feature activation+2.04e-01

Pos logit contributions
 GOODMAN+0.179
 wip+0.172
inav+0.172
 exceptions+0.168
 sparing+0.165
Neg logit contributions
naire-0.253
-0.250
naissance-0.246
��-0.243
-0.234
Token in
Token ID287
Feature activation+2.67e-01

Pos logit contributions
 GOODMAN+0.157
 wip+0.152
inav+0.152
 exceptions+0.150
 sparing+0.147
Neg logit contributions
naire-0.169
-0.167
naissance-0.164
��-0.162
-0.155
Token the
Token ID262
Feature activation+2.58e-01

Pos logit contributions
 GOODMAN+0.168
 wip+0.161
inav+0.160
 exceptions+0.157
 sparing+0.153
Neg logit contributions
naire-0.260
-0.257
naissance-0.252
��-0.251
-0.242
Token Middle
Token ID6046
Feature activation+3.38e-01

Pos logit contributions
 GOODMAN+0.177
 wip+0.171
inav+0.171
 exceptions+0.167
 sparing+0.164
Neg logit contributions
naire-0.235
-0.232
naissance-0.227
��-0.226
-0.217
Token East
Token ID3687
Feature activation+8.80e-01

Pos logit contributions
 GOODMAN+0.202
inav+0.195
 wip+0.194
 exceptions+0.191
 sparing+0.186
Neg logit contributions
naire-0.338
-0.332
naissance-0.328
��-0.326
-0.315
Token and
Token ID290
Feature activation+1.55e-01

Pos logit contributions
 GOODMAN+0.679
 wip+0.659
inav+0.658
 exceptions+0.648
 sparing+0.637
Neg logit contributions
naire-0.727
-0.715
naissance-0.703
��-0.698
-0.666
Token for
Token ID329
Feature activation+1.58e-01

Pos logit contributions
 GOODMAN+0.114
 wip+0.110
inav+0.110
 exceptions+0.108
 sparing+0.106
Neg logit contributions
naire-0.135
-0.133
naissance-0.130
��-0.129
-0.124
Token saying
Token ID2282
Feature activation+3.39e-01

Pos logit contributions
 GOODMAN+0.098
inav+0.094
 wip+0.094
 exceptions+0.092
 sparing+0.089
Neg logit contributions
naire-0.155
-0.153
naissance-0.150
��-0.149
-0.144
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
 GOODMAN+0.237
 wip+0.229
inav+0.229
 exceptions+0.224
 sparing+0.220
Neg logit contributions
naire-0.306
-0.301
naissance-0.296
��-0.294
-0.282
Token fight
Token ID1907
Feature activation+1.48e-01

Pos logit contributions
 GOODMAN+0.146
inav+0.140
 wip+0.140
 exceptions+0.136
 sparing+0.134
Neg logit contributions
naire-0.215
-0.212
naissance-0.208
��-0.207
-0.199
Token
Token ID251
Feature activation-3.26e-01

Pos logit contributions
 GOODMAN+0.003
 wip+0.003
inav+0.003
 exceptions+0.003
 sparing+0.003
Neg logit contributions
naire-0.001
naissance-0.001
-0.001
��-0.001
 dominates-0.001
Token The
Token ID383
Feature activation-6.81e-02

Pos logit contributions
naire+0.245
+0.241
naissance+0.235
��+0.233
+0.222
Neg logit contributions
 GOODMAN-0.277
inav-0.269
 wip-0.269
 exceptions-0.265
 sparing-0.261
Token president
Token ID1893
Feature activation+1.06e-01

Pos logit contributions
naire+0.062
+0.061
naissance+0.060
��+0.060
+0.057
Neg logit contributions
 GOODMAN-0.047
inav-0.046
 wip-0.045
 exceptions-0.044
 sparing-0.043
Token claimed
Token ID4752
Feature activation+8.55e-02

Pos logit contributions
 GOODMAN+0.094
 wip+0.092
inav+0.091
 exceptions+0.091
 sparing+0.090
Neg logit contributions
naire-0.076
-0.074
naissance-0.073
��-0.072
-0.068
Token that
Token ID326
Feature activation+1.72e-01

Pos logit contributions
 GOODMAN+0.054
inav+0.052
 wip+0.052
 exceptions+0.051
 sparing+0.050
Neg logit contributions
naire-0.083
-0.081
naissance-0.080
��-0.080
-0.077
Token Flake
Token ID39727
Feature activation+8.76e-01

Pos logit contributions
 GOODMAN+0.095
inav+0.091
 wip+0.091
 exceptions+0.088
 sparing+0.086
Neg logit contributions
naire-0.179
-0.177
naissance-0.174
��-0.173
-0.168
Token was
Token ID373
Feature activation+7.78e-02

Pos logit contributions
 GOODMAN+0.860
 wip+0.845
inav+0.839
 exceptions+0.836
 sparing+0.823
Neg logit contributions
naire-0.536
-0.524
naissance-0.515
��-0.504
-0.471
Token
Token ID564
Feature activation+1.57e-01

Pos logit contributions
 GOODMAN+0.051
 wip+0.049
inav+0.049
 exceptions+0.048
 sparing+0.047
Neg logit contributions
naire-0.073
-0.072
naissance-0.071
��-0.071
-0.068
Token
Token ID250
Feature activation+5.68e-02

Pos logit contributions
 GOODMAN+0.194
 wip+0.190
inav+0.190
 exceptions+0.188
 sparing+0.186
Neg logit contributions
naire-0.057
-0.054
naissance-0.052
��-0.051
-0.045
Tokenc
Token ID66
Feature activation+7.99e-02

Pos logit contributions
 GOODMAN+0.042
inav+0.041
 wip+0.041
 exceptions+0.040
 sparing+0.040
Neg logit contributions
naire-0.048
-0.048
naissance-0.047
��-0.046
-0.044
Tokenaught
Token ID3413
Feature activation+3.49e-01

Pos logit contributions
 GOODMAN+0.063
inav+0.062
 wip+0.061
 exceptions+0.061
 sparing+0.059
Neg logit contributions
naire-0.064
-0.064
naissance-0.062
��-0.062
-0.059
Token Pelosi
Token ID29611
Feature activation-2.75e-01

Pos logit contributions
naire+0.130
+0.125
naissance+0.124
��+0.122
+0.113
Neg logit contributions
 GOODMAN-0.251
 wip-0.247
inav-0.246
 exceptions-0.243
 sparing-0.241
Token,
Token ID11
Feature activation-1.21e-01

Pos logit contributions
naire+0.221
+0.217
naissance+0.213
��+0.211
+0.201
Neg logit contributions
 GOODMAN-0.219
 wip-0.213
inav-0.213
 exceptions-0.210
 sparing-0.206
Token producing
Token ID9194
Feature activation+2.10e-01

Pos logit contributions
naire+0.109
+0.107
naissance+0.105
��+0.104
+0.100
Neg logit contributions
 GOODMAN-0.085
inav-0.082
 wip-0.082
 exceptions-0.080
 sparing-0.079
Token a
Token ID257
Feature activation-1.22e-02

Pos logit contributions
 GOODMAN+0.128
 wip+0.123
inav+0.123
 exceptions+0.121
 sparing+0.118
Neg logit contributions
naire-0.208
-0.205
naissance-0.202
��-0.201
-0.194
Token miss
Token ID2051
Feature activation+1.86e-01

Pos logit contributions
naire+0.011
+0.011
naissance+0.011
��+0.011
+0.010
Neg logit contributions
 GOODMAN-0.008
 wip-0.008
inav-0.008
 exceptions-0.008
 sparing-0.008
Tokenhap
Token ID45897
Feature activation+8.53e-01

Pos logit contributions
 GOODMAN+0.121
inav+0.117
 wip+0.117
 exceptions+0.115
 sparing+0.113
Neg logit contributions
naire-0.176
-0.173
naissance-0.170
��-0.169
-0.162
Tokenen
Token ID268
Feature activation+1.53e-01

Pos logit contributions
 GOODMAN+0.594
inav+0.580
 wip+0.579
 exceptions+0.566
 sparing+0.559
Neg logit contributions
naire-0.768
-0.756
naissance-0.741
��-0.736
-0.707
Token mass
Token ID2347
Feature activation-3.87e-02

Pos logit contributions
 GOODMAN+0.114
 wip+0.111
inav+0.111
 exceptions+0.110
 sparing+0.107
Neg logit contributions
naire-0.131
-0.129
naissance-0.127
��-0.126
-0.120
Token of
Token ID286
Feature activation-4.78e-02

Pos logit contributions
naire+0.024
+0.024
naissance+0.024
��+0.023
+0.022
Neg logit contributions
 GOODMAN-0.037
 wip-0.036
inav-0.036
 exceptions-0.036
 sparing-0.036
Token special
Token ID2041
Feature activation+2.09e-01

Pos logit contributions
naire+0.046
+0.046
naissance+0.045
��+0.044
+0.043
Neg logit contributions
 GOODMAN-0.030
inav-0.029
 wip-0.029
 exceptions-0.028
 sparing-0.028
Token-
Token ID12
Feature activation+1.05e-02

Pos logit contributions
 GOODMAN+0.144
 wip+0.140
inav+0.140
 exceptions+0.138
 sparing+0.135
Neg logit contributions
naire-0.190
-0.187
naissance-0.184
��-0.182
-0.175
Tokenak
Token ID461
Feature activation+2.51e-01

Pos logit contributions
naire+0.027
+0.027
naissance+0.026
��+0.026
+0.025
Neg logit contributions
 GOODMAN-0.022
 wip-0.022
inav-0.021
 exceptions-0.021
 sparing-0.021
Token city
Token ID1748
Feature activation-2.25e-01

Pos logit contributions
 GOODMAN+0.193
 wip+0.188
inav+0.187
 exceptions+0.184
 sparing+0.181
Neg logit contributions
naire-0.208
-0.205
naissance-0.201
��-0.199
-0.190
Token and
Token ID290
Feature activation+5.37e-03

Pos logit contributions
naire+0.186
+0.184
naissance+0.180
��+0.179
+0.171
Neg logit contributions
 GOODMAN-0.173
 wip-0.168
inav-0.167
 exceptions-0.165
 sparing-0.162
Token parts
Token ID3354
Feature activation+5.20e-02

Pos logit contributions
 GOODMAN+0.003
 wip+0.003
inav+0.003
 exceptions+0.003
 sparing+0.003
Neg logit contributions
naire-0.006
-0.006
naissance-0.005
��-0.005
-0.005
Token of
Token ID286
Feature activation-7.46e-02

Pos logit contributions
 GOODMAN+0.055
 wip+0.054
inav+0.054
 exceptions+0.053
 sparing+0.052
Neg logit contributions
naire-0.028
-0.028
naissance-0.027
��-0.026
-0.025
Token Roh
Token ID32694
Feature activation+8.53e-01

Pos logit contributions
naire+0.077
+0.076
naissance+0.075
��+0.074
+0.072
Neg logit contributions
 GOODMAN-0.042
inav-0.041
 wip-0.041
 exceptions-0.040
 sparing-0.039
Tokent
Token ID83
Feature activation+3.22e-02

Pos logit contributions
 GOODMAN+0.771
inav+0.754
 wip+0.751
 exceptions+0.741
 sparing+0.730
Neg logit contributions
naire-0.592
-0.581
naissance-0.567
��-0.563
-0.533
Tokenak
Token ID461
Feature activation+3.17e-01

Pos logit contributions
 GOODMAN+0.023
 wip+0.022
inav+0.022
 exceptions+0.022
 sparing+0.022
Neg logit contributions
naire-0.028
-0.028
naissance-0.027
��-0.027
-0.026
Token district
Token ID4783
Feature activation-4.44e-02

Pos logit contributions
 GOODMAN+0.230
 wip+0.222
inav+0.221
 exceptions+0.218
 sparing+0.214
Neg logit contributions
naire-0.278
-0.274
naissance-0.269
��-0.267
-0.256
Token and
Token ID290
Feature activation-3.87e-03

Pos logit contributions
naire+0.036
+0.036
naissance+0.035
��+0.035
+0.033
Neg logit contributions
 GOODMAN-0.035
 wip-0.034
inav-0.034
 exceptions-0.033
 sparing-0.033
Token H
Token ID367
Feature activation-7.97e-02

Pos logit contributions
naire+0.004
+0.004
naissance+0.004
��+0.004
+0.003
Neg logit contributions
 GOODMAN-0.003
 wip-0.002
inav-0.002
 exceptions-0.002
 sparing-0.002
Token
Token ID251
Feature activation-2.34e-01

Pos logit contributions
 GOODMAN+0.167
 wip+0.164
inav+0.164
 exceptions+0.163
 sparing+0.161
Neg logit contributions
naire-0.041
-0.038
naissance-0.037
��-0.035
 dominates-0.030
Token
Token ID198
Feature activation+1.26e-01

Pos logit contributions
naire+0.192
+0.189
naissance+0.185
��+0.184
+0.175
Neg logit contributions
 GOODMAN-0.183
 wip-0.177
inav-0.177
 exceptions-0.174
 sparing-0.171
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
 GOODMAN+0.100
 wip+0.097
inav+0.097
 exceptions+0.095
 sparing+0.094
Neg logit contributions
naire-0.101
-0.099
naissance-0.096
��-0.096
-0.092
TokenC
Token ID34
Feature activation-9.23e-02

Pos logit contributions
 GOODMAN+0.084
 wip+0.081
inav+0.081
 exceptions+0.080
 sparing+0.079
Neg logit contributions
naire-0.079
-0.078
naissance-0.077
��-0.076
-0.072
Tokenance
Token ID590
Feature activation+1.96e-01

Pos logit contributions
naire+0.084
+0.083
naissance+0.081
��+0.081
+0.078
Neg logit contributions
 GOODMAN-0.064
inav-0.061
 wip-0.061
 exceptions-0.060
 sparing-0.059
Tokenll
Token ID297
Feature activation+8.50e-01

Pos logit contributions
 GOODMAN+0.079
 wip+0.074
inav+0.074
 exceptions+0.071
 sparing+0.069
Neg logit contributions
naire-0.235
-0.232
naissance-0.229
��-0.227
-0.221
Tokenara
Token ID3301
Feature activation+1.34e-02

Pos logit contributions
 GOODMAN+0.704
inav+0.691
 wip+0.681
 exceptions+0.678
 sparing+0.665
Neg logit contributions
naire-0.644
-0.636
naissance-0.624
��-0.622
-0.591
Token saw
Token ID2497
Feature activation+7.06e-02

Pos logit contributions
 GOODMAN+0.012
 wip+0.012
inav+0.012
 exceptions+0.011
 sparing+0.011
Neg logit contributions
naire-0.009
-0.009
naissance-0.009
��-0.009
-0.009
Token it
Token ID340
Feature activation-2.79e-02

Pos logit contributions
 GOODMAN+0.043
 wip+0.041
inav+0.041
 exceptions+0.040
 sparing+0.039
Neg logit contributions
naire-0.070
-0.070
naissance-0.068
��-0.068
-0.066
Token as
Token ID355
Feature activation+1.29e-01

Pos logit contributions
naire+0.028
+0.028
naissance+0.027
��+0.027
+0.026
Neg logit contributions
 GOODMAN-0.016
inav-0.016
 wip-0.016
 exceptions-0.015
 sparing-0.015
Token an
Token ID281
Feature activation+8.55e-02

Pos logit contributions
 GOODMAN+0.081
 wip+0.078
inav+0.078
 exceptions+0.076
 sparing+0.075
Neg logit contributions
naire-0.126
-0.124
naissance-0.122
��-0.121
-0.117
Token by
Token ID416
Feature activation+6.56e-02

Pos logit contributions
 GOODMAN+0.243
 wip+0.238
inav+0.236
 exceptions+0.234
 sparing+0.230
Neg logit contributions
naire-0.222
-0.218
naissance-0.215
��-0.212
-0.200
Token blocking
Token ID12013
Feature activation+3.44e-01

Pos logit contributions
 GOODMAN+0.044
 wip+0.043
inav+0.043
 exceptions+0.042
 sparing+0.041
Neg logit contributions
naire-0.061
-0.060
naissance-0.059
��-0.058
-0.056
Token national
Token ID2260
Feature activation+1.93e-01

Pos logit contributions
 GOODMAN+0.303
 wip+0.295
inav+0.293
 exceptions+0.291
 sparing+0.286
Neg logit contributions
naire-0.247
-0.242
naissance-0.238
��-0.234
-0.222
Token highway
Token ID12763
Feature activation-2.91e-02

Pos logit contributions
 GOODMAN+0.138
 wip+0.134
inav+0.133
 exceptions+0.132
 sparing+0.129
Neg logit contributions
naire-0.170
-0.167
naissance-0.165
��-0.163
-0.156
Token connecting
Token ID14320
Feature activation-1.68e-02

Pos logit contributions
naire+0.024
+0.023
naissance+0.023
��+0.023
+0.022
Neg logit contributions
 GOODMAN-0.023
 wip-0.022
inav-0.022
 exceptions-0.022
 sparing-0.021
Token Roh
Token ID32694
Feature activation+8.42e-01

Pos logit contributions
naire+0.014
+0.013
naissance+0.013
��+0.013
+0.012
Neg logit contributions
 GOODMAN-0.013
 wip-0.013
inav-0.013
 exceptions-0.013
 sparing-0.012
Tokent
Token ID83
Feature activation-2.73e-03

Pos logit contributions
 GOODMAN+0.741
inav+0.729
 wip+0.725
 exceptions+0.709
 iod+0.695
Neg logit contributions
naire-0.603
-0.589
naissance-0.578
��-0.574
-0.542
Tokenak
Token ID461
Feature activation+3.16e-01

Pos logit contributions
naire+0.002
+0.002
naissance+0.002
��+0.002
+0.002
Neg logit contributions
 GOODMAN-0.002
 wip-0.002
inav-0.002
 exceptions-0.002
 sparing-0.002
Token to
Token ID284
Feature activation+8.36e-02

Pos logit contributions
 GOODMAN+0.237
 wip+0.231
inav+0.229
 exceptions+0.226
 sparing+0.222
Neg logit contributions
naire-0.267
-0.261
naissance-0.258
��-0.256
-0.244
Token Delhi
Token ID12517
Feature activation+1.86e-01

Pos logit contributions
 GOODMAN+0.069
 wip+0.067
inav+0.067
 exceptions+0.066
 sparing+0.065
Neg logit contributions
naire-0.065
-0.064
naissance-0.063
��-0.062
-0.059
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
 GOODMAN+0.147
 wip+0.143
inav+0.142
 exceptions+0.140
 sparing+0.138
Neg logit contributions
naire-0.151
-0.148
naissance-0.146
��-0.144
-0.138
Token lit
Token ID6578
Feature activation+1.92e-01

Pos logit contributions
 GOODMAN+0.059
inav+0.057
 wip+0.057
 exceptions+0.056
 sparing+0.055
Neg logit contributions
naire-0.070
-0.069
naissance-0.067
��-0.067
-0.064
Tokeners
Token ID364
Feature activation-1.72e-01

Pos logit contributions
 GOODMAN+0.159
 wip+0.155
inav+0.155
 exceptions+0.152
 sparing+0.150
Neg logit contributions
naire-0.147
-0.145
naissance-0.141
��-0.141
-0.135
Token into
Token ID656
Feature activation-2.66e-01

Pos logit contributions
naire+0.103
+0.101
naissance+0.098
��+0.097
+0.091
Neg logit contributions
 GOODMAN-0.172
 wip-0.168
inav-0.168
 exceptions-0.166
 sparing-0.164
Token the
Token ID262
Feature activation+6.30e-02

Pos logit contributions
naire+0.276
+0.273
naissance+0.268
��+0.267
+0.259
Neg logit contributions
 GOODMAN-0.148
inav-0.142
 wip-0.141
 exceptions-0.137
 sparing-0.133
Token mash
Token ID30407
Feature activation+2.74e-01

Pos logit contributions
 GOODMAN+0.040
inav+0.038
 wip+0.038
 exceptions+0.038
 sparing+0.037
Neg logit contributions
naire-0.061
-0.060
naissance-0.059
��-0.058
-0.056
Token tun
Token ID6278
Feature activation+8.41e-01

Pos logit contributions
 GOODMAN+0.209
inav+0.202
 wip+0.202
 exceptions+0.199
 sparing+0.195
Neg logit contributions
naire-0.229
-0.226
naissance-0.222
��-0.219
-0.211
Token,
Token ID11
Feature activation-9.79e-02

Pos logit contributions
 GOODMAN+0.673
 wip+0.653
inav+0.652
 exceptions+0.642
 sparing+0.632
Neg logit contributions
naire-0.672
-0.661
naissance-0.648
��-0.642
-0.613
Token then
Token ID788
Feature activation+2.97e-01

Pos logit contributions
naire+0.088
+0.087
naissance+0.086
��+0.085
+0.082
Neg logit contributions
 GOODMAN-0.068
inav-0.066
 wip-0.065
 exceptions-0.064
 sparing-0.062
Token add
Token ID751
Feature activation+3.89e-01

Pos logit contributions
 GOODMAN+0.215
 wip+0.208
inav+0.208
 exceptions+0.204
 sparing+0.201
Neg logit contributions
naire-0.259
-0.255
naissance-0.250
��-0.248
-0.238
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
 GOODMAN+0.211
inav+0.203
 wip+0.201
 exceptions+0.195
 sparing+0.189
Neg logit contributions
naire-0.408
-0.404
naissance-0.399
��-0.396
-0.384
Token mal
Token ID6428
Feature activation+2.66e-01

Pos logit contributions
 GOODMAN+0.114
inav+0.109
 wip+0.108
 exceptions+0.106
 sparing+0.103
Neg logit contributions
naire-0.209
-0.207
naissance-0.204
��-0.203
-0.196
Token in
Token ID287
Feature activation+1.62e-01

Pos logit contributions
naire+0.039
+0.039
naissance+0.038
��+0.038
+0.036
Neg logit contributions
 GOODMAN-0.037
 wip-0.036
inav-0.036
 exceptions-0.035
 sparing-0.034
Token the
Token ID262
Feature activation+1.66e-01

Pos logit contributions
 GOODMAN+0.107
 wip+0.103
inav+0.103
 exceptions+0.101
 sparing+0.099
Neg logit contributions
naire-0.151
-0.149
naissance-0.147
��-0.146
-0.140
Token road
Token ID2975
Feature activation+1.85e-01

Pos logit contributions
 GOODMAN+0.144
inav+0.140
 wip+0.140
 exceptions+0.138
 sparing+0.136
Neg logit contributions
naire-0.122
-0.120
naissance-0.118
��-0.117
-0.111
Token from
Token ID422
Feature activation-1.40e-01

Pos logit contributions
 GOODMAN+0.143
 wip+0.138
inav+0.138
 exceptions+0.136
 sparing+0.134
Neg logit contributions
naire-0.154
-0.151
naissance-0.148
��-0.147
-0.141
Token Cast
Token ID5833
Feature activation+6.86e-02

Pos logit contributions
naire+0.120
+0.118
naissance+0.116
��+0.115
+0.110
Neg logit contributions
 GOODMAN-0.103
 wip-0.100
inav-0.100
 exceptions-0.098
 sparing-0.097
Tokenaic
Token ID18452
Feature activation+8.39e-01

Pos logit contributions
 GOODMAN+0.052
inav+0.051
 wip+0.051
 exceptions+0.050
 sparing+0.049
Neg logit contributions
naire-0.057
-0.056
naissance-0.055
��-0.055
-0.053
Token to
Token ID284
Feature activation+8.88e-02

Pos logit contributions
 GOODMAN+0.699
 wip+0.677
inav+0.673
 exceptions+0.669
 sparing+0.658
Neg logit contributions
naire-0.641
-0.633
naissance-0.619
��-0.613
-0.583
Token his
Token ID465
Feature activation-9.09e-02

Pos logit contributions
 GOODMAN+0.073
 wip+0.071
inav+0.071
 exceptions+0.070
 sparing+0.069
Neg logit contributions
naire-0.069
-0.068
naissance-0.066
��-0.066
-0.063
Token home
Token ID1363
Feature activation-7.54e-02

Pos logit contributions
naire+0.071
+0.070
naissance+0.068
��+0.068
+0.064
Neg logit contributions
 GOODMAN-0.075
 wip-0.073
inav-0.073
 exceptions-0.072
 sparing-0.071
Token in
Token ID287
Feature activation+1.16e-01

Pos logit contributions
naire+0.064
+0.063
naissance+0.062
��+0.061
+0.059
Neg logit contributions
 GOODMAN-0.056
 wip-0.055
inav-0.055
 exceptions-0.054
 sparing-0.053
Token Lake
Token ID6233
Feature activation+1.06e-01

Pos logit contributions
 GOODMAN+0.093
 wip+0.090
inav+0.090
 exceptions+0.089
 sparing+0.087
Neg logit contributions
naire-0.092
-0.091
naissance-0.089
��-0.088
-0.084
Token Sunday
Token ID3502
Feature activation+1.47e-02

Pos logit contributions
 GOODMAN+0.063
 wip+0.061
inav+0.061
 exceptions+0.060
 sparing+0.059
Neg logit contributions
naire-0.082
-0.081
naissance-0.080
��-0.079
-0.076
Token that
Token ID326
Feature activation+1.29e-01

Pos logit contributions
 GOODMAN+0.009
 wip+0.009
inav+0.009
 exceptions+0.008
 sparing+0.008
Neg logit contributions
naire-0.015
-0.015
naissance-0.014
��-0.014
-0.014
Token
Token ID564
Feature activation+1.70e-02

Pos logit contributions
 GOODMAN+0.069
inav+0.066
 wip+0.066
 exceptions+0.064
 sparing+0.063
Neg logit contributions
naire-0.136
-0.135
naissance-0.133
��-0.132
-0.128
Token
Token ID250
Feature activation-5.20e-03

Pos logit contributions
 GOODMAN+0.021
 wip+0.021
inav+0.021
 exceptions+0.021
 sparing+0.021
Neg logit contributions
naire-0.006
-0.006
naissance-0.005
��-0.005
-0.005
TokenJeff
Token ID19139
Feature activation-2.64e-02

Pos logit contributions
naire+0.004
+0.004
naissance+0.004
��+0.004
+0.004
Neg logit contributions
 GOODMAN-0.004
 wip-0.004
inav-0.004
 exceptions-0.004
 sparing-0.004
Token Flake
Token ID39727
Feature activation+8.37e-01

Pos logit contributions
naire+0.032
+0.032
naissance+0.032
��+0.031
+0.030
Neg logit contributions
 GOODMAN-0.010
 wip-0.009
inav-0.009
 exceptions-0.009
 sparing-0.009
Token(
Token ID7
Feature activation-1.23e-01

Pos logit contributions
 GOODMAN+0.749
 wip+0.733
inav+0.725
 exceptions+0.724
 sparing+0.711
Neg logit contributions
naire-0.587
-0.576
naissance-0.569
��-0.558
-0.527
Tokeny
Token ID88
Feature activation+1.66e-01

Pos logit contributions
naire+0.069
+0.067
naissance+0.066
��+0.063
+0.059
Neg logit contributions
 GOODMAN-0.128
 wip-0.125
inav-0.124
 exceptions-0.124
 sparing-0.122
Token)
Token ID8
Feature activation+2.56e-01

Pos logit contributions
 GOODMAN+0.111
 wip+0.107
inav+0.107
 exceptions+0.105
 sparing+0.103
Neg logit contributions
naire-0.154
-0.152
naissance-0.149
��-0.148
-0.142
Token
Token ID447
Feature activation+2.48e-02

Pos logit contributions
 GOODMAN+0.223
 wip+0.218
inav+0.216
 exceptions+0.214
 sparing+0.211
Neg logit contributions
naire-0.186
-0.182
naissance-0.179
��-0.177
-0.167
Token
Token ID251
Feature activation-3.18e-01

Pos logit contributions
 GOODMAN+0.030
 wip+0.030
 exceptions+0.030
inav+0.030
 sparing+0.029
Neg logit contributions
naire-0.009
naissance-0.009
-0.008
��-0.008
 dominates-0.007
Token news
Token ID1705
Feature activation+9.60e-02

Pos logit contributions
naire+0.128
+0.127
naissance+0.124
��+0.123
+0.118
Neg logit contributions
 GOODMAN-0.097
 wip-0.094
inav-0.094
 exceptions-0.092
 sparing-0.090
Token here
Token ID994
Feature activation+6.93e-02

Pos logit contributions
 GOODMAN+0.074
 wip+0.072
inav+0.072
 exceptions+0.071
 sparing+0.069
Neg logit contributions
naire-0.080
-0.078
naissance-0.077
��-0.076
-0.073
Token,
Token ID11
Feature activation+1.71e-03

Pos logit contributions
 GOODMAN+0.054
 wip+0.053
inav+0.053
 exceptions+0.052
 sparing+0.051
Neg logit contributions
naire-0.056
-0.056
naissance-0.054
��-0.054
-0.052
Token
Token ID447
Feature activation+8.00e-02

Pos logit contributions
 GOODMAN+0.001
inav+0.001
 wip+0.001
 exceptions+0.001
 sparing+0.001
Neg logit contributions
naire-0.002
-0.002
naissance-0.002
��-0.002
-0.001
Token
Token ID251
Feature activation-2.60e-01

Pos logit contributions
 GOODMAN+0.101
 wip+0.100
inav+0.099
 exceptions+0.099
 sparing+0.098
Neg logit contributions
naire-0.026
-0.024
naissance-0.024
��-0.023
 dominates-0.020
Token Flake
Token ID39727
Feature activation+8.34e-01

Pos logit contributions
naire+0.252
+0.248
��+0.244
naissance+0.243
+0.235
Neg logit contributions
 GOODMAN-0.164
inav-0.160
 wip-0.157
 exceptions-0.153
 sparing-0.151
Token tweeted
Token ID10830
Feature activation+1.47e-01

Pos logit contributions
 GOODMAN+0.675
 wip+0.656
inav+0.654
 exceptions+0.645
 sparing+0.634
Neg logit contributions
naire-0.659
-0.648
naissance-0.636
��-0.629
-0.601
Token Saturday
Token ID3909
Feature activation+2.89e-01

Pos logit contributions
 GOODMAN+0.113
inav+0.109
 wip+0.109
 exceptions+0.107
 sparing+0.105
Neg logit contributions
naire-0.122
-0.120
naissance-0.118
��-0.117
-0.112
Token after
Token ID706
Feature activation+1.98e-01

Pos logit contributions
 GOODMAN+0.203
inav+0.196
 wip+0.196
 exceptions+0.192
 sparing+0.188
Neg logit contributions
naire-0.259
-0.256
naissance-0.250
��-0.249
-0.239
Token his
Token ID465
Feature activation-9.62e-03

Pos logit contributions
 GOODMAN+0.111
inav+0.107
 wip+0.106
 exceptions+0.102
 sparing+0.100
Neg logit contributions
naire-0.206
-0.203
��-0.200
naissance-0.200
-0.193
Token comments
Token ID3651
Feature activation+2.36e-01

Pos logit contributions
naire+0.009
+0.009
naissance+0.009
��+0.009
+0.008
Neg logit contributions
 GOODMAN-0.006
inav-0.006
 wip-0.006
 exceptions-0.006
 sparing-0.006
Token,
Token ID11
Feature activation+8.73e-03

Pos logit contributions
 GOODMAN+0.063
inav+0.061
 wip+0.061
 exceptions+0.060
 sparing+0.059
Neg logit contributions
naire-0.058
-0.057
naissance-0.056
��-0.056
-0.053
Token a
Token ID257
Feature activation+7.33e-02

Pos logit contributions
 GOODMAN+0.006
 wip+0.005
inav+0.005
 exceptions+0.005
 sparing+0.005
Neg logit contributions
naire-0.008
-0.008
naissance-0.008
��-0.008
-0.008
Token professor
Token ID6240
Feature activation-5.31e-02

Pos logit contributions
 GOODMAN+0.053
 wip+0.051
inav+0.051
 exceptions+0.051
 sparing+0.050
Neg logit contributions
naire-0.064
-0.063
naissance-0.062
��-0.062
-0.059
Token of
Token ID286
Feature activation-1.85e-01

Pos logit contributions
naire+0.039
+0.038
naissance+0.037
��+0.037
+0.035
Neg logit contributions
 GOODMAN-0.046
 wip-0.045
inav-0.045
 exceptions-0.045
 sparing-0.044
Token Middle
Token ID6046
Feature activation+2.60e-01

Pos logit contributions
naire+0.165
+0.163
naissance+0.160
��+0.159
+0.153
Neg logit contributions
 GOODMAN-0.131
inav-0.126
 wip-0.126
 exceptions-0.124
 sparing-0.121
Token East
Token ID3687
Feature activation+8.34e-01

Pos logit contributions
 GOODMAN+0.160
inav+0.155
 wip+0.154
 exceptions+0.151
 sparing+0.148
Neg logit contributions
naire-0.255
-0.250
naissance-0.246
��-0.246
-0.236
Token history
Token ID2106
Feature activation-1.87e-01

Pos logit contributions
 GOODMAN+0.581
 wip+0.567
inav+0.565
 exceptions+0.561
 sparing+0.546
Neg logit contributions
naire-0.749
-0.734
naissance-0.720
��-0.719
-0.686
Token at
Token ID379
Feature activation+1.17e-01

Pos logit contributions
naire+0.159
+0.157
naissance+0.153
��+0.153
+0.146
Neg logit contributions
 GOODMAN-0.140
inav-0.135
 wip-0.135
 exceptions-0.134
 sparing-0.131
Token Shawn
Token ID25225
Feature activation-2.45e-01

Pos logit contributions
 GOODMAN+0.076
 wip+0.073
inav+0.073
 exceptions+0.072
 sparing+0.070
Neg logit contributions
naire-0.111
-0.110
naissance-0.108
��-0.107
-0.104
Tokenee
Token ID1453
Feature activation-8.17e-02

Pos logit contributions
naire+0.166
+0.162
naissance+0.159
��+0.157
+0.147
Neg logit contributions
 GOODMAN-0.227
inav-0.222
 wip-0.221
 exceptions-0.217
 sparing-0.214
Token State
Token ID1812
Feature activation+7.06e-02

Pos logit contributions
naire+0.053
+0.052
naissance+0.051
��+0.050
+0.047
Neg logit contributions
 GOODMAN-0.078
 wip-0.076
inav-0.076
 exceptions-0.075
 sparing-0.074
Token LO
Token ID17579
Feature activation+5.10e-01

Pos logit contributions
 GOODMAN+0.281
 wip+0.271
inav+0.269
 exceptions+0.267
 sparing+0.262
Neg logit contributions
naire-0.295
-0.291
naissance-0.287
��-0.284
-0.271
TokenOM
Token ID2662
Feature activation+2.88e-01

Pos logit contributions
 GOODMAN+0.358
inav+0.342
 wip+0.341
 exceptions+0.339
 sparing+0.329
Neg logit contributions
naire-0.460
-0.452
naissance-0.448
��-0.443
-0.423
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
 GOODMAN+0.230
 wip+0.222
inav+0.221
 exceptions+0.218
 sparing+0.214
Neg logit contributions
naire-0.231
-0.228
naissance-0.224
��-0.221
-0.211
Token
Token ID198
Feature activation+1.97e-01

Pos logit contributions
 GOODMAN+0.163
 wip+0.158
inav+0.158
 exceptions+0.155
 sparing+0.153
Neg logit contributions
naire-0.170
-0.167
naissance-0.164
��-0.162
-0.155
TokenRa
Token ID21762
Feature activation+2.07e-01

Pos logit contributions
 GOODMAN+0.158
inav+0.153
 wip+0.153
 exceptions+0.151
 sparing+0.148
Neg logit contributions
naire-0.157
-0.155
naissance-0.152
��-0.150
-0.143
Tokenising
Token ID1710
Feature activation+8.26e-01

Pos logit contributions
 GOODMAN+0.095
inav+0.091
 wip+0.091
 exceptions+0.088
 sparing+0.085
Neg logit contributions
naire-0.236
-0.233
naissance-0.230
��-0.229
-0.221
Token the
Token ID262
Feature activation+2.94e-01

Pos logit contributions
 GOODMAN+0.367
inav+0.355
 wip+0.350
 exceptions+0.332
 sparing+0.328
Neg logit contributions
naire-0.948
-0.940
naissance-0.925
��-0.923
-0.896
Token debt
Token ID5057
Feature activation+2.09e-01

Pos logit contributions
 GOODMAN+0.209
inav+0.202
 wip+0.202
 exceptions+0.198
 sparing+0.194
Neg logit contributions
naire-0.260
-0.257
naissance-0.252
��-0.250
-0.240
Token ceiling
Token ID13387
Feature activation-3.27e-02

Pos logit contributions
 GOODMAN+0.191
 wip+0.188
inav+0.186
 exceptions+0.186
 sparing+0.183
Neg logit contributions
naire-0.143
-0.140
naissance-0.139
��-0.136
-0.128
Token is
Token ID318
Feature activation-4.04e-02

Pos logit contributions
naire+0.024
+0.024
naissance+0.023
��+0.023
+0.022
Neg logit contributions
 GOODMAN-0.028
 wip-0.028
inav-0.027
 exceptions-0.027
 sparing-0.027
Token one
Token ID530
Feature activation+2.74e-02

Pos logit contributions
naire+0.038
+0.038
naissance+0.037
��+0.037
+0.035
Neg logit contributions
 GOODMAN-0.026
inav-0.026
 wip-0.025
 exceptions-0.025
 sparing-0.024
Token specific
Token ID2176
Feature activation+9.71e-02

Pos logit contributions
naire+0.240
+0.236
naissance+0.232
��+0.230
+0.221
Neg logit contributions
 GOODMAN-0.178
inav-0.172
 wip-0.172
 exceptions-0.169
 sparing-0.166
Token countries
Token ID2678
Feature activation+1.36e-01

Pos logit contributions
 GOODMAN+0.058
inav+0.056
 wip+0.056
 exceptions+0.055
 sparing+0.053
Neg logit contributions
naire-0.098
-0.096
naissance-0.095
��-0.094
-0.090
Token in
Token ID287
Feature activation+1.37e-01

Pos logit contributions
 GOODMAN+0.106
 wip+0.102
inav+0.102
 exceptions+0.101
 sparing+0.099
Neg logit contributions
naire-0.112
-0.110
naissance-0.108
��-0.107
-0.102
Token the
Token ID262
Feature activation+1.30e-01

Pos logit contributions
 GOODMAN+0.064
 wip+0.061
inav+0.061
 exceptions+0.059
 sparing+0.057
Neg logit contributions
naire-0.155
-0.153
naissance-0.151
��-0.150
-0.146
Token Middle
Token ID6046
Feature activation+2.65e-01

Pos logit contributions
 GOODMAN+0.084
 wip+0.081
inav+0.081
 exceptions+0.080
 sparing+0.078
Neg logit contributions
naire-0.123
-0.121
naissance-0.119
��-0.118
-0.114
Token East
Token ID3687
Feature activation+8.25e-01

Pos logit contributions
 GOODMAN+0.159
inav+0.154
 wip+0.153
 exceptions+0.150
 sparing+0.146
Neg logit contributions
naire-0.265
-0.260
naissance-0.257
��-0.255
-0.246
Token.
Token ID13
Feature activation+1.55e-01

Pos logit contributions
 GOODMAN+0.627
 wip+0.607
inav+0.607
 exceptions+0.598
 sparing+0.587
Neg logit contributions
naire-0.692
-0.681
naissance-0.668
��-0.663
-0.634
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
 GOODMAN+0.126
 wip+0.122
inav+0.122
 exceptions+0.120
 sparing+0.118
Neg logit contributions
naire-0.122
-0.120
naissance-0.118
��-0.117
-0.111
Token
Token ID198
Feature activation+1.24e-01

Pos logit contributions
 GOODMAN+0.109
 wip+0.106
inav+0.105
 exceptions+0.103
 sparing+0.102
Neg logit contributions
naire-0.111
-0.108
naissance-0.106
��-0.105
-0.101
TokenThe
Token ID464
Feature activation+9.58e-03

Pos logit contributions
 GOODMAN+0.095
 wip+0.092
inav+0.092
 exceptions+0.091
 sparing+0.089
Neg logit contributions
naire-0.102
-0.100
naissance-0.099
��-0.098
-0.093
Token author
Token ID1772
Feature activation+7.44e-02

Pos logit contributions
 GOODMAN+0.007
 wip+0.007
inav+0.007
 exceptions+0.007
 sparing+0.007
Neg logit contributions
naire-0.008
-0.008
naissance-0.008
��-0.008
-0.008
Token slain
Token ID27029
Feature activation+4.05e-01

Pos logit contributions
 GOODMAN+0.249
 wip+0.242
inav+0.242
 exceptions+0.238
 sparing+0.234
Neg logit contributions
naire-0.256
-0.252
naissance-0.247
��-0.245
-0.234
Token by
Token ID416
Feature activation+2.08e-01

Pos logit contributions
 GOODMAN+0.337
inav+0.326
 wip+0.326
 exceptions+0.321
 sparing+0.315
Neg logit contributions
naire-0.312
-0.307
naissance-0.300
��-0.297
-0.284
Token a
Token ID257
Feature activation+1.03e-01

Pos logit contributions
 GOODMAN+0.127
 wip+0.122
inav+0.122
 exceptions+0.118
 sparing+0.116
Neg logit contributions
naire-0.205
-0.203
naissance-0.199
��-0.199
-0.191
Token company
Token ID1664
Feature activation+1.84e-01

Pos logit contributions
 GOODMAN+0.084
 wip+0.082
inav+0.082
 exceptions+0.080
 sparing+0.079
Neg logit contributions
naire-0.081
-0.079
naissance-0.078
��-0.077
-0.073
Token of
Token ID286
Feature activation+8.89e-02

Pos logit contributions
 GOODMAN+0.189
 wip+0.185
inav+0.185
 exceptions+0.182
 sparing+0.181
Neg logit contributions
naire-0.105
-0.103
naissance-0.100
��-0.099
-0.093
Token Roh
Token ID32694
Feature activation+8.21e-01

Pos logit contributions
 GOODMAN+0.060
 wip+0.058
inav+0.057
 exceptions+0.056
 sparing+0.055
Neg logit contributions
naire-0.082
-0.081
naissance-0.080
��-0.080
-0.076
Tokenir
Token ID343
Feature activation+5.09e-01

Pos logit contributions
 GOODMAN+0.450
inav+0.430
 wip+0.429
 exceptions+0.419
 sparing+0.409
Neg logit contributions
naire-0.864
-0.853
naissance-0.840
��-0.835
-0.807
Tokenrim
Token ID3036
Feature activation+2.95e-01

Pos logit contributions
 GOODMAN+0.378
 wip+0.367
inav+0.366
 exceptions+0.359
 sparing+0.352
Neg logit contributions
naire-0.436
-0.430
naissance-0.422
��-0.417
-0.402
Token.
Token ID13
Feature activation+2.98e-01

Pos logit contributions
 GOODMAN+0.227
inav+0.219
 wip+0.219
 exceptions+0.215
 sparing+0.211
Neg logit contributions
naire-0.246
-0.242
naissance-0.237
��-0.235
-0.225
Token Merry
Token ID39001
Feature activation+1.09e-01

Pos logit contributions
 GOODMAN+0.246
 wip+0.238
inav+0.238
 exceptions+0.235
 sparing+0.231
Neg logit contributions
naire-0.231
-0.228
naissance-0.223
��-0.221
-0.211
Token and
Token ID290
Feature activation+1.93e-01

Pos logit contributions
 GOODMAN+0.087
 wip+0.084
inav+0.084
 exceptions+0.083
 sparing+0.082
Neg logit contributions
naire-0.087
-0.086
naissance-0.084
��-0.083
-0.080
Token five
Token ID1936
Feature activation+2.74e-01

Pos logit contributions
 GOODMAN+0.136
inav+0.131
 wip+0.131
 exceptions+0.128
 sparing+0.126
Neg logit contributions
naire-0.167
-0.165
naissance-0.162
��-0.161
-0.154
Token Google
Token ID3012
Feature activation+2.29e-02

Pos logit contributions
 GOODMAN+0.191
 wip+0.184
inav+0.184
 exceptions+0.181
 sparing+0.178
Neg logit contributions
naire-0.248
-0.244
naissance-0.240
��-0.238
-0.229
Token Android
Token ID5565
Feature activation+3.83e-01

Pos logit contributions
 GOODMAN+0.013
 wip+0.013
inav+0.013
 exceptions+0.013
 sparing+0.012
Neg logit contributions
naire-0.023
-0.023
naissance-0.023
��-0.022
-0.022
Token Honey
Token ID21788
Feature activation-3.20e-01

Pos logit contributions
 GOODMAN+0.180
 wip+0.171
inav+0.170
 exceptions+0.166
 sparing+0.161
Neg logit contributions
naire-0.433
-0.428
naissance-0.422
��-0.420
-0.406
Tokencomb
Token ID24011
Feature activation-3.61e-01

Pos logit contributions
naire+0.268
+0.264
naissance+0.259
��+0.256
+0.245
Neg logit contributions
 GOODMAN-0.244
 wip-0.236
inav-0.236
 exceptions-0.232
 sparing-0.229
Token tablets
Token ID17255
Feature activation+8.03e-01

Pos logit contributions
naire+0.400
+0.396
naissance+0.390
��+0.387
+0.375
Neg logit contributions
 GOODMAN-0.177
inav-0.168
 wip-0.168
 exceptions-0.164
 sparing-0.159
Token that
Token ID326
Feature activation+1.59e-01

Pos logit contributions
 GOODMAN+0.671
 wip+0.655
inav+0.649
 exceptions+0.645
 sparing+0.635
Neg logit contributions
naire-0.612
-0.603
��-0.590
naissance-0.590
-0.556
Token have
Token ID423
Feature activation-4.73e-03

Pos logit contributions
 GOODMAN+0.133
 wip+0.129
inav+0.129
 exceptions+0.127
 sparing+0.125
Neg logit contributions
naire-0.120
-0.119
naissance-0.116
��-0.115
-0.109
Token come
Token ID1282
Feature activation-1.36e-01

Pos logit contributions
naire+0.003
+0.003
naissance+0.003
��+0.003
+0.003
Neg logit contributions
 GOODMAN-0.004
 wip-0.004
inav-0.004
 exceptions-0.004
 sparing-0.004
Token out
Token ID503
Feature activation-2.48e-02

Pos logit contributions
naire+0.126
+0.125
naissance+0.122
��+0.122
+0.117
Neg logit contributions
 GOODMAN-0.092
 wip-0.089
inav-0.088
 exceptions-0.087
 sparing-0.085
Token since
Token ID1201
Feature activation-1.42e-01

Pos logit contributions
naire+0.022
+0.021
naissance+0.021
��+0.021
+0.020
Neg logit contributions
 GOODMAN-0.018
 wip-0.017
inav-0.017
 exceptions-0.017
 sparing-0.017
Token Senate
Token ID3845
Feature activation+4.86e-01

Pos logit contributions
 GOODMAN+0.128
inav+0.124
 wip+0.123
 exceptions+0.120
 sparing+0.118
Neg logit contributions
naire-0.174
-0.172
naissance-0.169
��-0.168
-0.162
Token floor
Token ID4314
Feature activation+2.32e-01

Pos logit contributions
 GOODMAN+0.378
 wip+0.365
inav+0.364
 exceptions+0.360
 sparing+0.353
Neg logit contributions
naire-0.401
-0.394
naissance-0.386
��-0.384
-0.366
Token last
Token ID938
Feature activation+6.06e-02

Pos logit contributions
 GOODMAN+0.170
 wip+0.164
inav+0.164
 exceptions+0.161
 sparing+0.159
Neg logit contributions
naire-0.201
-0.198
naissance-0.195
��-0.193
-0.185
Token month
Token ID1227
Feature activation-1.47e-02

Pos logit contributions
 GOODMAN+0.045
 wip+0.044
inav+0.044
 exceptions+0.043
 sparing+0.042
Neg logit contributions
naire-0.051
-0.051
naissance-0.050
��-0.049
-0.047
Token,
Token ID11
Feature activation+1.11e-01

Pos logit contributions
naire+0.011
+0.011
naissance+0.011
��+0.011
+0.010
Neg logit contributions
 GOODMAN-0.012
 wip-0.012
inav-0.012
 exceptions-0.012
 sparing-0.012
Token Flake
Token ID39727
Feature activation+8.00e-01

Pos logit contributions
 GOODMAN+0.054
inav+0.052
 wip+0.051
 exceptions+0.050
 sparing+0.048
Neg logit contributions
naire-0.124
-0.123
naissance-0.121
��-0.121
-0.117
Token announced
Token ID3414
Feature activation+1.73e-02

Pos logit contributions
 GOODMAN+0.631
 wip+0.614
inav+0.611
 exceptions+0.605
 sparing+0.596
Neg logit contributions
naire-0.647
-0.637
naissance-0.625
��-0.618
-0.589
Token his
Token ID465
Feature activation-1.69e-02

Pos logit contributions
 GOODMAN+0.013
inav+0.012
 wip+0.012
 exceptions+0.012
 sparing+0.012
Neg logit contributions
naire-0.015
-0.015
naissance-0.014
��-0.014
-0.014
Token plans
Token ID3352
Feature activation+1.28e-01

Pos logit contributions
naire+0.016
+0.016
naissance+0.016
��+0.015
+0.015
Neg logit contributions
 GOODMAN-0.011
inav-0.011
 wip-0.011
 exceptions-0.010
 sparing-0.010
Token to
Token ID284
Feature activation+8.43e-02

Pos logit contributions
 GOODMAN+0.088
inav+0.085
 wip+0.085
 exceptions+0.083
 sparing+0.081
Neg logit contributions
naire-0.117
-0.115
naissance-0.113
��-0.112
-0.108
Token retire
Token ID8058
Feature activation-1.39e-01

Pos logit contributions
 GOODMAN+0.062
 wip+0.060
inav+0.059
 exceptions+0.059
 sparing+0.058
Neg logit contributions
naire-0.073
-0.072
naissance-0.071
��-0.070
-0.067
Token the
Token ID262
Feature activation+1.56e-01

Pos logit contributions
 GOODMAN+0.056
inav+0.053
 wip+0.053
 exceptions+0.052
 sparing+0.050
Neg logit contributions
naire-0.112
-0.111
naissance-0.109
��-0.108
-0.105
Token OG
Token ID34498
Feature activation+1.35e-01

Pos logit contributions
 GOODMAN+0.109
inav+0.105
 wip+0.105
 exceptions+0.103
 sparing+0.101
Neg logit contributions
naire-0.140
-0.138
naissance-0.136
��-0.135
-0.130
Token.
Token ID13
Feature activation+1.67e-03

Pos logit contributions
 GOODMAN+0.119
 wip+0.116
inav+0.116
 exceptions+0.114
 sparing+0.113
Neg logit contributions
naire-0.097
-0.095
naissance-0.093
��-0.092
-0.087
Token Nor
Token ID5414
Feature activation-4.66e-02

Pos logit contributions
 GOODMAN+0.001
 wip+0.001
inav+0.001
 exceptions+0.001
 sparing+0.001
Neg logit contributions
naire-0.001
-0.001
naissance-0.001
��-0.001
-0.001
Token the
Token ID262
Feature activation+9.08e-02

Pos logit contributions
naire+0.039
+0.038
naissance+0.038
��+0.037
+0.036
Neg logit contributions
 GOODMAN-0.036
 wip-0.034
inav-0.034
 exceptions-0.034
 sparing-0.033
Token FG
Token ID25503
Feature activation+7.94e-01

Pos logit contributions
 GOODMAN+0.060
inav+0.058
 wip+0.058
 exceptions+0.057
 sparing+0.056
Neg logit contributions
naire-0.085
-0.084
naissance-0.082
��-0.082
-0.079
Token.
Token ID13
Feature activation+3.77e-02

Pos logit contributions
 GOODMAN+0.634
 wip+0.615
inav+0.615
 exceptions+0.605
 sparing+0.595
Neg logit contributions
naire-0.635
-0.626
naissance-0.613
��-0.608
-0.581
Token However
Token ID2102
Feature activation-4.53e-02

Pos logit contributions
 GOODMAN+0.030
 wip+0.029
inav+0.029
 exceptions+0.028
 sparing+0.028
Neg logit contributions
naire-0.031
-0.030
naissance-0.030
��-0.029
-0.028
Token,
Token ID11
Feature activation-5.12e-03

Pos logit contributions
naire+0.037
+0.036
naissance+0.036
��+0.035
+0.034
Neg logit contributions
 GOODMAN-0.036
 wip-0.034
inav-0.034
 exceptions-0.034
 sparing-0.033
Token if
Token ID611
Feature activation+3.23e-01

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.003
inav-0.003
 wip-0.003
 exceptions-0.003
 sparing-0.003
Token we
Token ID356
Feature activation+1.44e-01

Pos logit contributions
 GOODMAN+0.195
 wip+0.188
inav+0.188
 exceptions+0.184
 sparing+0.180
Neg logit contributions
naire-0.321
-0.317
naissance-0.311
��-0.309
-0.298
Token 1987
Token ID12923
Feature activation-1.09e-01

Pos logit contributions
naire+0.080
+0.079
naissance+0.077
��+0.076
+0.073
Neg logit contributions
 GOODMAN-0.089
 wip-0.087
inav-0.086
 exceptions-0.086
 sparing-0.084
Token-
Token ID12
Feature activation-1.84e-01

Pos logit contributions
naire+0.070
+0.069
naissance+0.067
��+0.066
+0.062
Neg logit contributions
 GOODMAN-0.104
 wip-0.101
inav-0.101
 exceptions-0.100
 sparing-0.099
Token1989
Token ID25475
Feature activation-9.29e-02

Pos logit contributions
naire+0.141
+0.138
naissance+0.136
��+0.135
+0.128
Neg logit contributions
 GOODMAN-0.153
 wip-0.148
inav-0.148
 exceptions-0.146
 sparing-0.144
Token-
Token ID12
Feature activation-2.57e-01

Pos logit contributions
naire+0.060
+0.059
naissance+0.058
��+0.057
+0.054
Neg logit contributions
 GOODMAN-0.088
 wip-0.086
inav-0.086
 exceptions-0.085
 sparing-0.084
Token 4
Token ID604
Feature activation-1.38e-01

Pos logit contributions
naire+0.213
+0.210
naissance+0.206
��+0.204
+0.195
Neg logit contributions
 GOODMAN-0.199
 wip-0.192
inav-0.192
 exceptions-0.189
 sparing-0.186
Token Pierce
Token ID23023
Feature activation-1.00e+00

Pos logit contributions
naire+0.107
+0.105
naissance+0.103
��+0.102
+0.097
Neg logit contributions
 GOODMAN-0.114
 wip-0.110
inav-0.110
 exceptions-0.108
 sparing-0.107
Token Bros
Token ID14266
Feature activation+4.70e-02

Pos logit contributions
naire+0.771
+0.757
naissance+0.741
��+0.734
+0.699
Neg logit contributions
 GOODMAN-0.836
 wip-0.812
inav-0.809
 exceptions-0.801
 sparing-0.788
Tokennan
Token ID12647
Feature activation-6.27e-02

Pos logit contributions
 GOODMAN+0.025
inav+0.024
 wip+0.024
 exceptions+0.023
 sparing+0.022
Neg logit contributions
naire-0.050
-0.049
naissance-0.049
��-0.049
-0.047
Token films
Token ID7328
Feature activation-1.14e-01

Pos logit contributions
naire+0.056
+0.055
naissance+0.055
��+0.054
+0.052
Neg logit contributions
 GOODMAN-0.044
 wip-0.043
inav-0.042
 exceptions-0.042
 sparing-0.041
Token,
Token ID11
Feature activation-1.41e-01

Pos logit contributions
naire+0.087
+0.085
naissance+0.083
��+0.083
+0.079
Neg logit contributions
 GOODMAN-0.096
 wip-0.093
inav-0.093
 exceptions-0.092
 sparing-0.090
Token 1995
Token ID8735
Feature activation-1.50e-01

Pos logit contributions
naire+0.109
+0.107
naissance+0.105
��+0.104
+0.099
Neg logit contributions
 GOODMAN-0.117
 wip-0.114
inav-0.113
 exceptions-0.112
 sparing-0.110
Token for
Token ID329
Feature activation-7.71e-02

Pos logit contributions
naire+0.027
+0.027
naissance+0.026
��+0.026
+0.025
Neg logit contributions
 GOODMAN-0.026
 wip-0.025
inav-0.025
 exceptions-0.025
 sparing-0.024
Token a
Token ID257
Feature activation-8.13e-02

Pos logit contributions
naire+0.072
+0.071
naissance+0.070
��+0.069
+0.067
Neg logit contributions
 GOODMAN-0.051
 wip-0.049
inav-0.049
 exceptions-0.048
 sparing-0.048
Token few
Token ID1178
Feature activation+1.25e-02

Pos logit contributions
naire+0.067
+0.066
naissance+0.065
��+0.065
+0.061
Neg logit contributions
 GOODMAN-0.063
inav-0.061
 wip-0.061
 exceptions-0.060
 sparing-0.059
Token other
Token ID584
Feature activation+6.96e-02

Pos logit contributions
 GOODMAN+0.009
 wip+0.008
inav+0.008
 exceptions+0.008
 sparing+0.008
Neg logit contributions
naire-0.011
-0.011
naissance-0.011
��-0.011
-0.011
Token fr
Token ID1216
Feature activation-4.10e-01

Pos logit contributions
 GOODMAN+0.046
 wip+0.045
inav+0.045
 exceptions+0.044
 sparing+0.043
Neg logit contributions
naire-0.065
-0.064
naissance-0.063
��-0.063
-0.060
Tokenatern
Token ID9205
Feature activation-9.51e-01

Pos logit contributions
naire+0.256
+0.250
naissance+0.243
��+0.241
+0.226
Neg logit contributions
 GOODMAN-0.401
inav-0.390
 wip-0.390
 exceptions-0.386
 sparing-0.380
Tokenities
Token ID871
Feature activation+5.95e-02

Pos logit contributions
naire+0.761
+0.748
naissance+0.734
��+0.728
+0.694
Neg logit contributions
 GOODMAN-0.760
inav-0.737
 wip-0.736
 exceptions-0.726
 sparing-0.713
Token are
Token ID389
Feature activation-3.30e-02

Pos logit contributions
 GOODMAN+0.048
 wip+0.046
inav+0.046
 exceptions+0.046
 sparing+0.045
Neg logit contributions
naire-0.047
-0.046
naissance-0.046
��-0.045
-0.043
Token also
Token ID635
Feature activation-1.56e-01

Pos logit contributions
naire+0.029
+0.028
naissance+0.028
��+0.028
+0.027
Neg logit contributions
 GOODMAN-0.024
inav-0.023
 wip-0.023
 exceptions-0.022
 sparing-0.022
Token in
Token ID287
Feature activation+3.82e-02

Pos logit contributions
naire+0.150
+0.149
naissance+0.146
��+0.145
+0.140
Neg logit contributions
 GOODMAN-0.100
inav-0.096
 wip-0.095
 exceptions-0.093
 sparing-0.091
Token a
Token ID257
Feature activation-1.10e-01

Pos logit contributions
 GOODMAN+0.021
inav+0.020
 wip+0.020
 exceptions+0.019
 sparing+0.019
Neg logit contributions
naire-0.040
-0.040
naissance-0.039
��-0.039
-0.038
Token higher
Token ID2440
Feature activation-5.21e-01

Pos logit contributions
 GOODMAN+0.033
 wip+0.032
inav+0.031
 exceptions+0.031
 sparing+0.030
Neg logit contributions
naire-0.048
-0.047
naissance-0.046
��-0.046
-0.044
Token in
Token ID287
Feature activation-6.49e-03

Pos logit contributions
naire+0.443
+0.435
naissance+0.428
��+0.423
+0.406
Neg logit contributions
 GOODMAN-0.390
 wip-0.378
inav-0.377
 exceptions-0.368
 sparing-0.362
Token charter
Token ID17422
Feature activation-9.38e-01

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.005
 wip-0.005
inav-0.005
 exceptions-0.005
 sparing-0.005
Token schools
Token ID4266
Feature activation-1.56e-01

Pos logit contributions
naire+0.675
+0.662
naissance+0.648
��+0.639
+0.609
Neg logit contributions
 GOODMAN-0.827
 wip-0.803
inav-0.801
 exceptions-0.788
 sparing-0.778
Token because
Token ID780
Feature activation+5.23e-02

Pos logit contributions
naire+0.138
+0.136
naissance+0.134
��+0.133
+0.128
Neg logit contributions
 GOODMAN-0.111
 wip-0.107
inav-0.107
 exceptions-0.105
 sparing-0.103
Token charter
Token ID17422
Feature activation-9.45e-01

Pos logit contributions
 GOODMAN+0.038
 wip+0.037
inav+0.037
 exceptions+0.037
 sparing+0.036
Neg logit contributions
naire-0.045
-0.045
naissance-0.044
��-0.044
-0.042
Token school
Token ID1524
Feature activation-2.47e-01

Pos logit contributions
naire+0.727
+0.714
naissance+0.700
��+0.693
+0.661
Neg logit contributions
 GOODMAN-0.786
 wip-0.763
inav-0.762
 exceptions-0.749
 sparing-0.738
Token teachers
Token ID7799
Feature activation-4.44e-01

Pos logit contributions
naire+0.220
+0.217
naissance+0.213
��+0.212
+0.203
Neg logit contributions
 GOODMAN-0.176
 wip-0.170
inav-0.170
 exceptions-0.167
 sparing-0.164
Token are
Token ID389
Feature activation-5.23e-02

Pos logit contributions
naire+0.351
+0.347
naissance+0.339
��+0.337
+0.321
Neg logit contributions
 GOODMAN-0.358
 wip-0.348
inav-0.348
 exceptions-0.343
 sparing-0.338
Token unhappy
Token ID19283
Feature activation-4.71e-01

Pos logit contributions
naire+0.048
+0.047
naissance+0.046
��+0.046
+0.044
Neg logit contributions
 GOODMAN-0.036
 wip-0.035
inav-0.035
 exceptions-0.034
 sparing-0.034
Token or
Token ID393
Feature activation+4.04e-02

Pos logit contributions
naire+0.376
+0.369
naissance+0.362
��+0.359
+0.343
Neg logit contributions
 GOODMAN-0.378
 wip-0.367
inav-0.366
 exceptions-0.359
 sparing-0.354
Token turnover
Token ID25079
Feature activation-4.90e-01

Pos logit contributions
naire+0.379
+0.374
naissance+0.367
��+0.365
+0.348
Neg logit contributions
 GOODMAN-0.365
inav-0.354
 wip-0.353
 exceptions-0.350
 sparing-0.343
Token may
Token ID743
Feature activation+4.33e-02

Pos logit contributions
naire+0.379
+0.375
naissance+0.368
��+0.364
+0.347
Neg logit contributions
 GOODMAN-0.402
 wip-0.393
inav-0.391
 exceptions-0.388
 sparing-0.381
Token be
Token ID307
Feature activation+5.04e-02

Pos logit contributions
 GOODMAN+0.031
 wip+0.030
inav+0.030
 exceptions+0.030
 sparing+0.029
Neg logit contributions
naire-0.038
-0.038
naissance-0.037
��-0.037
-0.035
Token higher
Token ID2440
Feature activation-5.21e-01

Pos logit contributions
 GOODMAN+0.033
 wip+0.032
inav+0.031
 exceptions+0.031
 sparing+0.030
Neg logit contributions
naire-0.048
-0.047
naissance-0.046
��-0.046
-0.044
Token in
Token ID287
Feature activation-6.49e-03

Pos logit contributions
naire+0.443
+0.435
naissance+0.428
��+0.423
+0.406
Neg logit contributions
 GOODMAN-0.390
 wip-0.378
inav-0.377
 exceptions-0.368
 sparing-0.362
Token charter
Token ID17422
Feature activation-9.38e-01

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.005
 wip-0.005
inav-0.005
 exceptions-0.005
 sparing-0.005
Token schools
Token ID4266
Feature activation-1.56e-01

Pos logit contributions
naire+0.675
+0.662
naissance+0.648
��+0.639
+0.609
Neg logit contributions
 GOODMAN-0.827
 wip-0.803
inav-0.801
 exceptions-0.788
 sparing-0.778
Token because
Token ID780
Feature activation+5.23e-02

Pos logit contributions
naire+0.138
+0.136
naissance+0.134
��+0.133
+0.128
Neg logit contributions
 GOODMAN-0.111
 wip-0.107
inav-0.107
 exceptions-0.105
 sparing-0.103
Token charter
Token ID17422
Feature activation-9.45e-01

Pos logit contributions
 GOODMAN+0.038
 wip+0.037
inav+0.037
 exceptions+0.037
 sparing+0.036
Neg logit contributions
naire-0.045
-0.045
naissance-0.044
��-0.044
-0.042
Token school
Token ID1524
Feature activation-2.47e-01

Pos logit contributions
naire+0.727
+0.714
naissance+0.700
��+0.693
+0.661
Neg logit contributions
 GOODMAN-0.786
 wip-0.763
inav-0.762
 exceptions-0.749
 sparing-0.738
Token teachers
Token ID7799
Feature activation-4.44e-01

Pos logit contributions
naire+0.220
+0.217
naissance+0.213
��+0.212
+0.203
Neg logit contributions
 GOODMAN-0.176
 wip-0.170
inav-0.170
 exceptions-0.167
 sparing-0.164
Token few
Token ID1178
Feature activation-1.34e-01

Pos logit contributions
naire+0.273
+0.270
naissance+0.265
��+0.263
+0.253
Neg logit contributions
 GOODMAN-0.200
 wip-0.193
inav-0.193
 exceptions-0.189
 sparing-0.186
Token that
Token ID326
Feature activation-9.96e-02

Pos logit contributions
naire+0.103
+0.102
naissance+0.099
��+0.098
+0.094
Neg logit contributions
 GOODMAN-0.111
 wip-0.108
inav-0.107
 exceptions-0.106
 sparing-0.104
Token do
Token ID466
Feature activation-5.88e-02

Pos logit contributions
naire+0.080
+0.079
naissance+0.077
��+0.077
+0.073
Neg logit contributions
 GOODMAN-0.079
 wip-0.077
inav-0.077
 exceptions-0.076
 sparing-0.075
Token practice
Token ID3357
Feature activation-2.43e-01

Pos logit contributions
naire+0.054
+0.054
naissance+0.053
��+0.052
+0.050
Neg logit contributions
 GOODMAN-0.040
 wip-0.038
inav-0.038
 exceptions-0.037
 sparing-0.037
Token Lac
Token ID23115
Feature activation-7.47e-03

Pos logit contributions
naire+0.205
+0.202
naissance+0.198
��+0.196
+0.188
Neg logit contributions
 GOODMAN-0.183
 wip-0.177
inav-0.177
 exceptions-0.175
 sparing-0.172
Tokenanian
Token ID38336
Feature activation-9.28e-01

Pos logit contributions
naire+0.004
+0.004
naissance+0.004
��+0.004
+0.004
Neg logit contributions
 GOODMAN-0.008
inav-0.008
 wip-0.008
 exceptions-0.007
 sparing-0.007
Token psycho
Token ID30731
Feature activation-1.57e-01

Pos logit contributions
naire+0.695
+0.684
naissance+0.669
��+0.663
+0.631
Neg logit contributions
 GOODMAN-0.789
 wip-0.767
inav-0.766
 exceptions-0.755
 sparing-0.743
Tokenanalysis
Token ID20930
Feature activation-3.82e-01

Pos logit contributions
naire+0.133
+0.131
naissance+0.128
��+0.127
+0.122
Neg logit contributions
 GOODMAN-0.119
inav-0.115
 wip-0.115
 exceptions-0.113
 sparing-0.111
Token in
Token ID287
Feature activation-8.79e-02

Pos logit contributions
naire+0.315
+0.310
naissance+0.304
��+0.301
+0.288
Neg logit contributions
 GOODMAN-0.296
 wip-0.287
inav-0.287
 exceptions-0.282
 sparing-0.277
Token such
Token ID884
Feature activation-8.30e-02

Pos logit contributions
naire+0.095
+0.094
naissance+0.092
��+0.091
+0.089
Neg logit contributions
 GOODMAN-0.046
 wip-0.044
inav-0.044
 exceptions-0.042
 sparing-0.041
Token settings
Token ID6460
Feature activation-1.13e-01

Pos logit contributions
naire+0.081
+0.080
naissance+0.079
��+0.078
+0.075
Neg logit contributions
 GOODMAN-0.052
 wip-0.050
inav-0.050
 exceptions-0.049
 sparing-0.048
Token was
Token ID373
Feature activation-2.45e-01

Pos logit contributions
naire+0.335
+0.332
naissance+0.324
��+0.321
+0.304
Neg logit contributions
 GOODMAN-0.410
 wip-0.402
inav-0.399
 exceptions-0.397
 sparing-0.391
Token twice
Token ID5403
Feature activation+5.40e-02

Pos logit contributions
naire+0.232
+0.229
naissance+0.225
��+0.223
+0.215
Neg logit contributions
 GOODMAN-0.159
 wip-0.153
inav-0.153
 exceptions-0.150
 sparing-0.148
Token as
Token ID355
Feature activation-5.14e-03

Pos logit contributions
 GOODMAN+0.031
inav+0.030
 wip+0.030
 exceptions+0.029
 sparing+0.028
Neg logit contributions
naire-0.056
-0.055
naissance-0.054
��-0.054
-0.052
Token high
Token ID1029
Feature activation-1.64e-01

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.003
 wip-0.003
inav-0.003
 exceptions-0.003
 sparing-0.003
Token at
Token ID379
Feature activation+3.02e-02

Pos logit contributions
naire+0.139
+0.137
naissance+0.135
��+0.134
+0.128
Neg logit contributions
 GOODMAN-0.123
 wip-0.119
inav-0.119
 exceptions-0.117
 sparing-0.115
Token charter
Token ID17422
Feature activation-9.20e-01

Pos logit contributions
 GOODMAN+0.022
 wip+0.022
inav+0.022
 exceptions+0.021
 sparing+0.021
Neg logit contributions
naire-0.026
-0.025
naissance-0.025
��-0.025
-0.024
Token schools
Token ID4266
Feature activation-2.10e-01

Pos logit contributions
naire+0.666
+0.653
naissance+0.641
��+0.632
+0.602
Neg logit contributions
 GOODMAN-0.806
 wip-0.783
inav-0.781
 exceptions-0.766
 sparing-0.757
Token (
Token ID357
Feature activation-1.67e-01

Pos logit contributions
naire+0.184
+0.181
naissance+0.178
��+0.176
+0.169
Neg logit contributions
 GOODMAN-0.152
 wip-0.147
inav-0.147
 exceptions-0.144
 sparing-0.141
TokenSt
Token ID1273
Feature activation-1.13e-01

Pos logit contributions
naire+0.122
+0.120
naissance+0.118
��+0.117
+0.111
Neg logit contributions
 GOODMAN-0.144
inav-0.140
 wip-0.140
 exceptions-0.138
 sparing-0.136
Tokenuit
Token ID5013
Feature activation-9.12e-02

Pos logit contributions
naire+0.085
+0.084
naissance+0.082
��+0.082
+0.078
Neg logit contributions
 GOODMAN-0.094
inav-0.092
 wip-0.091
 exceptions-0.090
 sparing-0.089
Token and
Token ID290
Feature activation+5.15e-02

Pos logit contributions
naire+0.076
+0.075
naissance+0.074
��+0.073
+0.070
Neg logit contributions
 GOODMAN-0.070
 wip-0.068
inav-0.068
 exceptions-0.067
 sparing-0.066
Token traditional
Token ID4569
Feature activation-2.05e-01

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.003
 wip-0.003
inav-0.003
 exceptions-0.003
 sparing-0.003
Token public
Token ID1171
Feature activation-4.91e-01

Pos logit contributions
naire+0.192
+0.189
naissance+0.186
��+0.185
+0.178
Neg logit contributions
 GOODMAN-0.135
 wip-0.130
inav-0.130
 exceptions-0.127
 sparing-0.125
Token schools
Token ID4266
Feature activation-3.19e-01

Pos logit contributions
naire+0.381
+0.375
naissance+0.368
��+0.363
+0.348
Neg logit contributions
 GOODMAN-0.403
inav-0.392
 wip-0.391
 exceptions-0.383
 sparing-0.378
Token and
Token ID290
Feature activation-1.93e-01

Pos logit contributions
naire+0.272
+0.268
naissance+0.263
��+0.260
+0.250
Neg logit contributions
 GOODMAN-0.239
 wip-0.232
inav-0.231
 exceptions-0.227
 sparing-0.223
Token at
Token ID379
Feature activation+1.82e-03

Pos logit contributions
naire+0.170
+0.168
naissance+0.165
��+0.163
+0.157
Neg logit contributions
 GOODMAN-0.139
 wip-0.134
inav-0.134
 exceptions-0.132
 sparing-0.129
Token charter
Token ID17422
Feature activation-8.80e-01

Pos logit contributions
 GOODMAN+0.002
 wip+0.002
inav+0.002
 exceptions+0.002
 sparing+0.002
Neg logit contributions
naire-0.001
-0.001
naissance-0.001
��-0.001
-0.001
Token schools
Token ID4266
Feature activation-1.81e-01

Pos logit contributions
naire+0.618
+0.605
naissance+0.593
��+0.583
+0.556
Neg logit contributions
 GOODMAN-0.791
 wip-0.769
inav-0.768
 exceptions-0.752
 sparing-0.745
Token.
Token ID13
Feature activation+2.25e-02

Pos logit contributions
naire+0.144
+0.142
naissance+0.139
��+0.138
+0.132
Neg logit contributions
 GOODMAN-0.145
 wip-0.141
inav-0.140
 exceptions-0.138
 sparing-0.136
Token
Token ID198
Feature activation-6.14e-02

Pos logit contributions
 GOODMAN+0.019
 wip+0.018
inav+0.018
 exceptions+0.018
 sparing+0.018
Neg logit contributions
naire-0.017
-0.017
naissance-0.017
��-0.017
-0.016
Token
Token ID198
Feature activation-7.33e-02

Pos logit contributions
naire+0.050
+0.048
naissance+0.047
��+0.047
+0.045
Neg logit contributions
 GOODMAN-0.049
 wip-0.047
inav-0.047
 exceptions-0.046
 sparing-0.046
TokenTe
Token ID6767
Feature activation-5.83e-01

Pos logit contributions
naire+0.054
+0.053
naissance+0.052
��+0.052
+0.049
Neg logit contributions
 GOODMAN-0.062
inav-0.061
 wip-0.061
 exceptions-0.060
 sparing-0.059
Token retailer
Token ID21538
Feature activation-4.36e-02

Pos logit contributions
naire+0.172
+0.171
naissance+0.168
��+0.167
+0.159
Neg logit contributions
 GOODMAN-0.143
 wip-0.138
inav-0.138
 exceptions-0.136
 sparing-0.134
Token?
Token ID30
Feature activation+8.07e-03

Pos logit contributions
naire+0.038
+0.037
naissance+0.036
��+0.036
+0.035
Neg logit contributions
 GOODMAN-0.032
 wip-0.031
inav-0.031
 exceptions-0.030
 sparing-0.030
Token
Token ID198
Feature activation-9.68e-03

Pos logit contributions
 GOODMAN+0.006
 wip+0.006
inav+0.006
 exceptions+0.006
 sparing+0.006
Neg logit contributions
naire-0.007
-0.007
naissance-0.006
��-0.006
-0.006
Token
Token ID198
Feature activation-2.75e-02

Pos logit contributions
naire+0.008
+0.008
naissance+0.007
��+0.007
+0.007
Neg logit contributions
 GOODMAN-0.008
 wip-0.008
inav-0.007
 exceptions-0.007
 sparing-0.007
TokenFred
Token ID30847
Feature activation-2.36e-01

Pos logit contributions
naire+0.021
+0.021
naissance+0.021
��+0.021
+0.020
Neg logit contributions
 GOODMAN-0.023
inav-0.022
 wip-0.022
 exceptions-0.021
 sparing-0.021
Token Pierce
Token ID23023
Feature activation-8.73e-01

Pos logit contributions
naire+0.179
+0.176
naissance+0.173
��+0.171
+0.163
Neg logit contributions
 GOODMAN-0.198
inav-0.191
 wip-0.191
 exceptions-0.189
 sparing-0.185
Token:
Token ID25
Feature activation-4.69e-02

Pos logit contributions
naire+0.703
+0.692
naissance+0.679
��+0.673
+0.642
Neg logit contributions
 GOODMAN-0.694
 wip-0.672
inav-0.671
 exceptions-0.661
 sparing-0.650
Token I
Token ID314
Feature activation-1.35e-01

Pos logit contributions
naire+0.040
+0.040
naissance+0.039
��+0.039
+0.037
Neg logit contributions
 GOODMAN-0.035
 wip-0.033
inav-0.033
 exceptions-0.033
 sparing-0.032
Token'll
Token ID1183
Feature activation+7.97e-02

Pos logit contributions
naire+0.136
+0.134
naissance+0.132
��+0.132
+0.126
Neg logit contributions
 GOODMAN-0.080
 wip-0.077
inav-0.077
 exceptions-0.075
 sparing-0.073
Token tell
Token ID1560
Feature activation-2.76e-02

Pos logit contributions
 GOODMAN+0.055
 wip+0.053
inav+0.053
 exceptions+0.052
 sparing+0.051
Neg logit contributions
naire-0.073
-0.072
naissance-0.071
��-0.070
-0.067
Token what
Token ID644
Feature activation-4.18e-02

Pos logit contributions
naire+0.028
+0.027
naissance+0.027
��+0.027
+0.026
Neg logit contributions
 GOODMAN-0.016
 wip-0.016
inav-0.016
 exceptions-0.015
 sparing-0.015
Token relationship
Token ID2776
Feature activation-4.10e-01

Pos logit contributions
naire+0.067
+0.066
naissance+0.065
��+0.064
+0.062
Neg logit contributions
 GOODMAN-0.055
 wip-0.053
inav-0.053
 exceptions-0.053
 sparing-0.052
Token with
Token ID351
Feature activation-7.37e-02

Pos logit contributions
naire+0.300
+0.294
naissance+0.288
��+0.286
+0.271
Neg logit contributions
 GOODMAN-0.356
 wip-0.347
inav-0.346
 exceptions-0.342
 sparing-0.337
Token the
Token ID262
Feature activation+5.89e-02

Pos logit contributions
naire+0.061
+0.060
naissance+0.059
��+0.058
+0.056
Neg logit contributions
 GOODMAN-0.057
 wip-0.055
inav-0.055
 exceptions-0.054
 sparing-0.054
Token CEO
Token ID6123
Feature activation-2.85e-01

Pos logit contributions
 GOODMAN+0.043
 wip+0.042
inav+0.042
 exceptions+0.041
 sparing+0.040
Neg logit contributions
naire-0.051
-0.050
naissance-0.050
��-0.049
-0.047
Token.
Token ID13
Feature activation+7.84e-02

Pos logit contributions
naire+0.216
+0.212
naissance+0.209
��+0.207
+0.196
Neg logit contributions
 GOODMAN-0.241
 wip-0.234
inav-0.232
 exceptions-0.231
 sparing-0.228
Token Blank
Token ID31990
Feature activation-8.72e-01

Pos logit contributions
 GOODMAN+0.066
 wip+0.064
inav+0.064
 exceptions+0.063
 sparing+0.062
Neg logit contributions
naire-0.059
-0.058
naissance-0.058
��-0.057
-0.054
Tokenfe
Token ID5036
Feature activation+1.59e-01

Pos logit contributions
naire+0.865
+0.852
naissance+0.839
��+0.832
+0.803
Neg logit contributions
 GOODMAN-0.532
 wip-0.509
inav-0.509
 exceptions-0.498
 sparing-0.487
Tokenin
Token ID259
Feature activation+5.79e-02

Pos logit contributions
 GOODMAN+0.094
 wip+0.089
inav+0.088
 exceptions+0.087
 sparing+0.085
Neg logit contributions
naire-0.162
-0.159
naissance-0.157
��-0.155
-0.150
Token and
Token ID290
Feature activation-6.45e-02

Pos logit contributions
 GOODMAN+0.054
 wip+0.053
inav+0.053
 exceptions+0.053
 sparing+0.052
Neg logit contributions
naire-0.038
-0.037
naissance-0.036
��-0.036
-0.034
Token Cohn
Token ID45005
Feature activation-9.80e-02

Pos logit contributions
naire+0.054
+0.053
naissance+0.052
��+0.052
+0.049
Neg logit contributions
 GOODMAN-0.049
 wip-0.048
inav-0.048
 exceptions-0.047
 sparing-0.046
Token vacation
Token ID14600
Feature activation-2.19e-01

Pos logit contributions
naire+0.066
+0.065
naissance+0.064
��+0.064
+0.060
Neg logit contributions
 GOODMAN-0.090
 wip-0.088
inav-0.088
 exceptions-0.086
 sparing-0.086
Token in
Token ID287
Feature activation-6.06e-02

Pos logit contributions
 GOODMAN+0.034
 wip+0.033
inav+0.033
 exceptions+0.033
 sparing+0.032
Neg logit contributions
naire-0.043
-0.042
naissance-0.041
��-0.041
-0.039
Token a
Token ID257
Feature activation-1.66e-01

Pos logit contributions
naire+0.060
+0.059
naissance+0.058
��+0.058
+0.056
Neg logit contributions
 GOODMAN-0.037
 wip-0.036
inav-0.036
 exceptions-0.035
 sparing-0.034
Token time
Token ID640
Feature activation-2.11e-02

Pos logit contributions
naire+0.145
+0.143
naissance+0.141
��+0.140
+0.134
Neg logit contributions
 GOODMAN-0.119
 wip-0.116
inav-0.115
 exceptions-0.114
 sparing-0.112
Token when
Token ID618
Feature activation+2.31e-01

Pos logit contributions
naire+0.021
+0.021
naissance+0.020
��+0.020
+0.019
Neg logit contributions
 GOODMAN-0.013
 wip-0.012
inav-0.012
 exceptions-0.012
 sparing-0.012
Token Lac
Token ID23115
Feature activation-1.83e-02

Pos logit contributions
 GOODMAN+0.146
 wip+0.140
inav+0.140
 exceptions+0.138
 sparing+0.135
Neg logit contributions
naire-0.224
-0.221
naissance-0.218
��-0.216
-0.208
Tokenanian
Token ID38336
Feature activation-8.71e-01

Pos logit contributions
naire+0.015
+0.014
naissance+0.014
��+0.014
+0.013
Neg logit contributions
 GOODMAN-0.015
inav-0.014
 wip-0.014
 exceptions-0.014
 sparing-0.014
Token clinical
Token ID8668
Feature activation-2.56e-01

Pos logit contributions
naire+0.662
+0.652
naissance+0.638
��+0.632
+0.602
Neg logit contributions
 GOODMAN-0.731
 wip-0.710
inav-0.709
 exceptions-0.699
 sparing-0.688
Token practice
Token ID3357
Feature activation-1.92e-01

Pos logit contributions
naire+0.221
+0.218
naissance+0.214
��+0.212
+0.203
Neg logit contributions
 GOODMAN-0.189
 wip-0.183
inav-0.182
 exceptions-0.179
 sparing-0.176
Token is
Token ID318
Feature activation-1.94e-01

Pos logit contributions
naire+0.119
+0.117
naissance+0.114
��+0.113
+0.106
Neg logit contributions
 GOODMAN-0.188
 wip-0.184
inav-0.184
 exceptions-0.183
 sparing-0.180
Token not
Token ID407
Feature activation-3.68e-02

Pos logit contributions
naire+0.177
+0.174
naissance+0.171
��+0.170
+0.163
Neg logit contributions
 GOODMAN-0.133
 wip-0.129
inav-0.128
 exceptions-0.127
 sparing-0.125
Token even
Token ID772
Feature activation-1.84e-01

Pos logit contributions
naire+0.035
+0.035
naissance+0.034
��+0.034
+0.032
Neg logit contributions
 GOODMAN-0.024
 wip-0.023
inav-0.023
 exceptions-0.022
 sparing-0.022
Token it
Token ID340
Feature activation-3.20e-01

Pos logit contributions
naire+0.022
+0.021
naissance+0.021
��+0.021
+0.020
Neg logit contributions
 GOODMAN-0.023
 wip-0.022
inav-0.022
 exceptions-0.022
 sparing-0.021
Token means
Token ID1724
Feature activation+1.02e-01

Pos logit contributions
naire+0.255
+0.251
naissance+0.246
��+0.244
+0.233
Neg logit contributions
 GOODMAN-0.257
 wip-0.250
inav-0.249
 exceptions-0.246
 sparing-0.242
Token to
Token ID284
Feature activation-8.33e-02

Pos logit contributions
 GOODMAN+0.068
 wip+0.066
inav+0.066
 exceptions+0.065
 sparing+0.063
Neg logit contributions
naire-0.094
-0.093
naissance-0.091
��-0.091
-0.087
Token practice
Token ID3357
Feature activation-2.54e-01

Pos logit contributions
naire+0.073
+0.072
naissance+0.071
��+0.071
+0.067
Neg logit contributions
 GOODMAN-0.060
 wip-0.058
inav-0.058
 exceptions-0.057
 sparing-0.056
Token Lac
Token ID23115
Feature activation-1.49e-01

Pos logit contributions
naire+0.202
+0.199
naissance+0.195
��+0.193
+0.185
Neg logit contributions
 GOODMAN-0.203
 wip-0.197
inav-0.197
 exceptions-0.194
 sparing-0.192
Tokenanian
Token ID38336
Feature activation-8.69e-01

Pos logit contributions
naire+0.104
+0.102
naissance+0.100
��+0.099
+0.094
Neg logit contributions
 GOODMAN-0.134
inav-0.131
 wip-0.130
 exceptions-0.129
 sparing-0.127
Token psycho
Token ID30731
Feature activation-2.33e-01

Pos logit contributions
naire+0.636
+0.624
naissance+0.611
��+0.606
+0.575
Neg logit contributions
 GOODMAN-0.753
 wip-0.733
inav-0.732
 exceptions-0.723
 sparing-0.712
Tokenanalysis
Token ID20930
Feature activation-3.41e-01

Pos logit contributions
naire+0.197
+0.194
naissance+0.190
��+0.189
+0.181
Neg logit contributions
 GOODMAN-0.175
inav-0.170
 wip-0.170
 exceptions-0.167
 sparing-0.164
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
naire+0.278
+0.273
naissance+0.268
��+0.265
+0.254
Neg logit contributions
 GOODMAN-0.268
 wip-0.259
inav-0.259
 exceptions-0.255
 sparing-0.250
Token This
Token ID770
Feature activation-3.98e-01

Pos logit contributions
naire+0.108
+0.107
naissance+0.105
��+0.104
+0.099
Neg logit contributions
 GOODMAN-0.107
inav-0.103
 wip-0.103
 exceptions-0.102
 sparing-0.100
Token is
Token ID318
Feature activation-2.01e-01

Pos logit contributions
naire+0.273
+0.267
naissance+0.262
��+0.259
+0.245
Neg logit contributions
 GOODMAN-0.363
 wip-0.354
inav-0.353
 exceptions-0.350
 sparing-0.345
Token Exc
Token ID25268
Feature activation+6.48e-03

Pos logit contributions
naire+0.351
+0.345
naissance+0.338
��+0.335
+0.319
Neg logit contributions
 GOODMAN-0.388
inav-0.376
 wip-0.376
 exceptions-0.371
 sparing-0.365
Tokeniting
Token ID1780
Feature activation+2.24e-01

Pos logit contributions
 GOODMAN+0.006
 wip+0.006
inav+0.006
 exceptions+0.006
 sparing+0.006
Neg logit contributions
naire-0.004
-0.004
naissance-0.004
��-0.004
-0.004
Token
Token ID50169
Feature activation-1.31e-01

Pos logit contributions
 GOODMAN+0.159
 wip+0.154
inav+0.154
 exceptions+0.151
 sparing+0.148
Neg logit contributions
naire-0.199
-0.196
naissance-0.193
��-0.191
-0.184
Token
Token ID235
Feature activation-3.39e-01

Pos logit contributions
naire+0.050
naissance+0.046
+0.046
��+0.044
 dominates+0.039
Neg logit contributions
 GOODMAN-0.159
 wip-0.156
inav-0.155
 exceptions-0.155
 sparing-0.153
Token
Token ID8582
Feature activation-3.64e-01

Pos logit contributions
naire+0.236
+0.232
naissance+0.227
��+0.224
+0.213
Neg logit contributions
 GOODMAN-0.306
 wip-0.297
inav-0.297
 exceptions-0.293
 sparing-0.289
Token
Token ID229
Feature activation-8.50e-01

Pos logit contributions
naire+0.091
+0.085
naissance+0.081
��+0.078
+0.065
Neg logit contributions
 GOODMAN-0.490
 wip-0.481
inav-0.480
 exceptions-0.477
 sparing-0.472
Token
Token ID118
Feature activation-1.62e-01

Pos logit contributions
naire+0.454
+0.443
naissance+0.430
��+0.424
+0.394
Neg logit contributions
 GOODMAN-0.906
 wip-0.886
inav-0.885
 exceptions-0.874
 sparing-0.864
Token
Token ID8582
Feature activation-3.49e-01

Pos logit contributions
naire+0.099
+0.097
naissance+0.095
��+0.093
+0.088
Neg logit contributions
 GOODMAN-0.160
 wip-0.156
inav-0.156
 exceptions-0.154
 sparing-0.152
Token
Token ID229
Feature activation-8.30e-01

Pos logit contributions
naire+0.092
+0.083
naissance+0.083
��+0.077
 dominates+0.065
Neg logit contributions
 GOODMAN-0.466
 wip-0.458
inav-0.457
 exceptions-0.454
 sparing-0.449
Token
Token ID116
Feature activation-1.83e-01

Pos logit contributions
naire+0.462
+0.450
naissance+0.438
��+0.432
+0.403
Neg logit contributions
 GOODMAN-0.864
 wip-0.845
inav-0.844
 exceptions-0.834
 sparing-0.824
Token
Token ID8582
Feature activation-2.91e-01

Pos logit contributions
naire+0.132
+0.130
naissance+0.127
��+0.126
+0.119
Neg logit contributions
 GOODMAN-0.160
 wip-0.155
inav-0.155
 exceptions-0.153
 sparing-0.151
Token scope
Token ID8354
Feature activation-2.34e-01

Pos logit contributions
naire+0.072
+0.071
naissance+0.069
��+0.069
+0.066
Neg logit contributions
 GOODMAN-0.068
 wip-0.066
inav-0.066
 exceptions-0.065
 sparing-0.064
Token,
Token ID11
Feature activation-1.76e-01

Pos logit contributions
naire+0.141
+0.138
naissance+0.134
��+0.133
+0.124
Neg logit contributions
 GOODMAN-0.233
 wip-0.227
inav-0.227
 exceptions-0.225
 sparing-0.222
Token and
Token ID290
Feature activation-1.01e-01

Pos logit contributions
naire+0.158
+0.155
naissance+0.153
��+0.151
+0.146
Neg logit contributions
 GOODMAN-0.124
inav-0.120
 wip-0.120
 exceptions-0.117
 sparing-0.115
Token practice
Token ID3357
Feature activation-2.61e-01

Pos logit contributions
naire+0.089
+0.088
naissance+0.086
��+0.086
+0.082
Neg logit contributions
 GOODMAN-0.072
inav-0.070
 wip-0.070
 exceptions-0.068
 sparing-0.067
Token Lac
Token ID23115
Feature activation-1.06e-01

Pos logit contributions
naire+0.247
+0.243
naissance+0.240
��+0.238
+0.229
Neg logit contributions
 GOODMAN-0.170
 wip-0.164
inav-0.164
 exceptions-0.161
 sparing-0.158
Tokenanian
Token ID38336
Feature activation-8.46e-01

Pos logit contributions
naire+0.059
+0.058
naissance+0.056
��+0.056
+0.052
Neg logit contributions
 GOODMAN-0.110
inav-0.108
 wip-0.107
 exceptions-0.106
 sparing-0.105
Token psycho
Token ID30731
Feature activation-2.06e-01

Pos logit contributions
naire+0.638
+0.628
naissance+0.614
��+0.608
+0.579
Neg logit contributions
 GOODMAN-0.715
 wip-0.695
inav-0.694
 exceptions-0.684
 sparing-0.673
Tokenanalysis
Token ID20930
Feature activation-3.81e-01

Pos logit contributions
naire+0.175
+0.172
naissance+0.168
��+0.167
+0.160
Neg logit contributions
 GOODMAN-0.155
inav-0.151
 wip-0.150
 exceptions-0.148
 sparing-0.145
Token every
Token ID790
Feature activation-1.76e-01

Pos logit contributions
naire+0.329
+0.324
naissance+0.318
��+0.315
+0.302
Neg logit contributions
 GOODMAN-0.280
inav-0.271
 wip-0.271
 exceptions-0.266
 sparing-0.260
Token day
Token ID1110
Feature activation+1.05e-01

Pos logit contributions
naire+0.167
+0.165
naissance+0.163
��+0.161
+0.155
Neg logit contributions
 GOODMAN-0.115
 wip-0.110
inav-0.110
 exceptions-0.108
 sparing-0.106
Token.
Token ID13
Feature activation-6.90e-02

Pos logit contributions
 GOODMAN+0.083
 wip+0.081
inav+0.080
 exceptions+0.079
 sparing+0.078
Neg logit contributions
naire-0.085
-0.084
naissance-0.082
��-0.082
-0.078
Token.
Token ID13
Feature activation+2.11e-02

Pos logit contributions
 GOODMAN+0.039
 wip+0.038
inav+0.037
 exceptions+0.037
 sparing+0.036
Neg logit contributions
naire-0.038
-0.037
naissance-0.037
��-0.036
-0.034
Token Wells
Token ID18292
Feature activation+7.90e-02

Pos logit contributions
 GOODMAN+0.017
 wip+0.016
inav+0.016
 exceptions+0.016
 sparing+0.016
Neg logit contributions
naire-0.017
-0.017
naissance-0.016
��-0.016
-0.015
Token Fargo
Token ID28125
Feature activation-6.07e-02

Pos logit contributions
 GOODMAN+0.071
 wip+0.069
inav+0.069
 exceptions+0.069
 sparing+0.067
Neg logit contributions
naire-0.055
-0.055
naissance-0.054
��-0.053
-0.050
Token,
Token ID11
Feature activation-6.24e-02

Pos logit contributions
naire+0.041
+0.041
naissance+0.040
��+0.040
+0.037
Neg logit contributions
 GOODMAN-0.056
 wip-0.055
inav-0.054
 exceptions-0.054
 sparing-0.053
Token JPMorgan
Token ID43318
Feature activation-3.64e-01

Pos logit contributions
naire+0.061
+0.060
naissance+0.059
��+0.059
+0.057
Neg logit contributions
 GOODMAN-0.039
 wip-0.037
inav-0.037
 exceptions-0.036
 sparing-0.036
Token Chase
Token ID16346
Feature activation-8.45e-01

Pos logit contributions
naire+0.179
+0.175
naissance+0.171
��+0.168
+0.154
Neg logit contributions
 GOODMAN-0.404
 wip-0.394
inav-0.393
 exceptions-0.390
 sparing-0.385
Token,
Token ID11
Feature activation-1.59e-01

Pos logit contributions
naire+0.646
+0.636
naissance+0.623
��+0.617
+0.588
Neg logit contributions
 GOODMAN-0.705
 wip-0.685
inav-0.684
 exceptions-0.674
 sparing-0.663
Token and
Token ID290
Feature activation-8.25e-02

Pos logit contributions
naire+0.132
+0.130
naissance+0.127
��+0.126
+0.121
Neg logit contributions
 GOODMAN-0.122
 wip-0.118
inav-0.118
 exceptions-0.116
 sparing-0.114
Token Cit
Token ID15792
Feature activation-1.62e-01

Pos logit contributions
naire+0.069
+0.068
naissance+0.067
��+0.067
+0.064
Neg logit contributions
 GOODMAN-0.062
 wip-0.060
inav-0.060
 exceptions-0.059
 sparing-0.058
Tokenib
Token ID571
Feature activation+1.92e-01

Pos logit contributions
naire+0.108
+0.106
naissance+0.103
��+0.102
+0.097
Neg logit contributions
 GOODMAN-0.150
 wip-0.147
inav-0.146
 exceptions-0.144
 sparing-0.142
Tokenank
Token ID962
Feature activation+2.36e-02

Pos logit contributions
 GOODMAN+0.169
 wip+0.165
inav+0.165
 exceptions+0.162
 sparing+0.160
Neg logit contributions
naire-0.137
-0.134
naissance-0.132
��-0.130
-0.123
Token of
Token ID286
Feature activation-1.36e-01

Pos logit contributions
naire+0.046
+0.045
naissance+0.044
��+0.043
+0.040
Neg logit contributions
 GOODMAN-0.082
 wip-0.080
inav-0.079
 exceptions-0.079
 sparing-0.078
Token the
Token ID262
Feature activation+1.44e-01

Pos logit contributions
naire+0.154
+0.152
naissance+0.150
��+0.149
+0.145
Neg logit contributions
 GOODMAN-0.064
inav-0.060
 wip-0.060
 exceptions-0.058
 sparing-0.057
Token bank
Token ID3331
Feature activation+3.77e-02

Pos logit contributions
 GOODMAN+0.102
 wip+0.098
inav+0.098
 exceptions+0.097
 sparing+0.095
Neg logit contributions
naire-0.129
-0.128
naissance-0.125
��-0.124
-0.119
Token.
Token ID13
Feature activation+9.39e-02

Pos logit contributions
 GOODMAN+0.034
 wip+0.033
inav+0.033
 exceptions+0.032
 sparing+0.032
Neg logit contributions
naire-0.027
-0.026
naissance-0.025
��-0.025
-0.024
Token JPMorgan
Token ID43318
Feature activation-4.56e-01

Pos logit contributions
 GOODMAN+0.079
 wip+0.076
inav+0.076
 exceptions+0.075
 sparing+0.073
Neg logit contributions
naire-0.072
-0.071
naissance-0.070
��-0.069
-0.065
Token Chase
Token ID16346
Feature activation-8.38e-01

Pos logit contributions
naire+0.277
+0.275
naissance+0.269
��+0.266
+0.248
Neg logit contributions
 GOODMAN-0.451
 wip-0.441
 exceptions-0.437
inav-0.436
 sparing-0.429
Token,
Token ID11
Feature activation-2.26e-01

Pos logit contributions
naire+0.552
+0.545
naissance+0.532
��+0.527
+0.496
Neg logit contributions
 GOODMAN-0.785
 wip-0.769
inav-0.763
 exceptions-0.759
 sparing-0.747
Token Bank
Token ID5018
Feature activation-2.57e-01

Pos logit contributions
naire+0.196
+0.194
naissance+0.190
��+0.189
+0.181
Neg logit contributions
 GOODMAN-0.166
 wip-0.160
inav-0.160
 exceptions-0.158
 sparing-0.155
Token of
Token ID286
Feature activation-2.33e-01

Pos logit contributions
naire+0.145
+0.144
naissance+0.141
��+0.139
+0.129
Neg logit contributions
 GOODMAN-0.265
inav-0.258
 wip-0.258
 exceptions-0.256
 sparing-0.251
Token America
Token ID2253
Feature activation-2.62e-03

Pos logit contributions
naire+0.236
+0.233
naissance+0.228
��+0.226
+0.219
Neg logit contributions
 GOODMAN-0.138
 wip-0.132
inav-0.131
 exceptions-0.128
 sparing-0.126
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
naire+0.002
+0.002
naissance+0.002
��+0.002
+0.002
Neg logit contributions
 GOODMAN-0.002
 wip-0.002
inav-0.002
 exceptions-0.002
 sparing-0.002
Token.
Token ID13
Feature activation+9.33e-02

Pos logit contributions
 GOODMAN+0.037
 wip+0.036
inav+0.036
 exceptions+0.036
 sparing+0.035
Neg logit contributions
naire-0.039
-0.039
naissance-0.038
��-0.038
-0.036
Token Lines
Token ID26299
Feature activation-3.72e-02

Pos logit contributions
 GOODMAN+0.079
 wip+0.076
inav+0.076
 exceptions+0.075
 sparing+0.073
Neg logit contributions
naire-0.070
-0.070
naissance-0.069
��-0.068
-0.064
Token are
Token ID389
Feature activation+9.47e-02

Pos logit contributions
naire+0.031
+0.030
naissance+0.030
��+0.030
+0.028
Neg logit contributions
 GOODMAN-0.029
 wip-0.028
inav-0.028
 exceptions-0.027
 sparing-0.027
Token going
Token ID1016
Feature activation+1.32e-01

Pos logit contributions
 GOODMAN+0.063
 wip+0.061
 exceptions+0.060
inav+0.060
 sparing+0.059
Neg logit contributions
naire-0.088
-0.087
naissance-0.086
��-0.085
-0.082
Token to
Token ID284
Feature activation+7.92e-02

Pos logit contributions
 GOODMAN+0.085
 wip+0.082
inav+0.080
 exceptions+0.080
 sparing+0.079
Neg logit contributions
naire-0.127
-0.125
naissance-0.124
��-0.123
-0.117
Token pile
Token ID14540
Feature activation-8.34e-01

Pos logit contributions
 GOODMAN+0.057
 wip+0.056
inav+0.055
 exceptions+0.055
 sparing+0.054
Neg logit contributions
naire-0.069
-0.068
naissance-0.067
��-0.067
-0.063
Token on
Token ID319
Feature activation-1.13e-01

Pos logit contributions
naire+0.805
+0.796
naissance+0.784
��+0.780
+0.748
Neg logit contributions
 GOODMAN-0.528
 wip-0.509
inav-0.506
 exceptions-0.499
 sparing-0.489
Token for
Token ID329
Feature activation-3.07e-02

Pos logit contributions
naire+0.097
+0.096
naissance+0.094
��+0.093
+0.089
Neg logit contributions
 GOODMAN-0.084
 wip-0.081
inav-0.081
 exceptions-0.080
 sparing-0.078
Token AAA
Token ID25734
Feature activation+4.24e-01

Pos logit contributions
naire+0.031
+0.030
naissance+0.030
��+0.029
+0.028
Neg logit contributions
 GOODMAN-0.018
inav-0.018
 wip-0.018
 exceptions-0.017
 sparing-0.017
Token games
Token ID1830
Feature activation+2.85e-02

Pos logit contributions
 GOODMAN+0.311
 wip+0.302
inav+0.301
 exceptions+0.298
 sparing+0.291
Neg logit contributions
naire-0.366
-0.361
naissance-0.354
��-0.351
-0.336
Token,
Token ID11
Feature activation-1.63e-02

Pos logit contributions
 GOODMAN+0.022
 wip+0.022
inav+0.022
 exceptions+0.021
 sparing+0.021
Neg logit contributions
naire-0.023
-0.023
naissance-0.022
��-0.022
-0.021
Token losing
Token ID6078
Feature activation-6.99e-02

Pos logit contributions
naire+0.160
+0.157
naissance+0.153
��+0.152
+0.144
Neg logit contributions
 GOODMAN-0.207
 wip-0.201
inav-0.201
 exceptions-0.199
 sparing-0.196
Token ground
Token ID2323
Feature activation+9.74e-02

Pos logit contributions
naire+0.065
+0.064
naissance+0.063
��+0.063
+0.060
Neg logit contributions
 GOODMAN-0.047
 wip-0.045
inav-0.045
 exceptions-0.044
 sparing-0.043
Token to
Token ID284
Feature activation-2.75e-02

Pos logit contributions
 GOODMAN+0.069
 wip+0.066
inav+0.066
 exceptions+0.065
 sparing+0.064
Neg logit contributions
naire-0.087
-0.086
naissance-0.084
��-0.084
-0.080
Token rivals
Token ID14987
Feature activation-3.59e-02

Pos logit contributions
naire+0.027
+0.026
naissance+0.026
��+0.026
+0.025
Neg logit contributions
 GOODMAN-0.017
 wip-0.017
inav-0.017
 exceptions-0.016
 sparing-0.016
Token like
Token ID588
Feature activation+3.01e-02

Pos logit contributions
naire+0.035
+0.035
naissance+0.034
��+0.034
+0.033
Neg logit contributions
 GOODMAN-0.022
 wip-0.021
inav-0.021
 exceptions-0.021
 sparing-0.020
Token Dom
Token ID9666
Feature activation-8.30e-01

Pos logit contributions
 GOODMAN+0.026
 wip+0.025
inav+0.025
 exceptions+0.025
 sparing+0.024
Neg logit contributions
naire-0.022
-0.022
naissance-0.021
��-0.021
-0.020
Tokenino
Token ID2879
Feature activation-2.45e-01

Pos logit contributions
naire+0.651
+0.641
naissance+0.627
��+0.621
+0.593
Neg logit contributions
 GOODMAN-0.676
 wip-0.657
inav-0.655
 exceptions-0.645
 sparing-0.635
Token's
Token ID338
Feature activation-3.05e-01

Pos logit contributions
naire+0.114
+0.112
naissance+0.108
��+0.107
+0.097
Neg logit contributions
 GOODMAN-0.277
 wip-0.271
inav-0.270
 exceptions-0.269
 sparing-0.265
Token Pizza
Token ID20952
Feature activation-5.20e-01

Pos logit contributions
naire+0.203
+0.199
naissance+0.194
��+0.192
+0.182
Neg logit contributions
 GOODMAN-0.285
 wip-0.277
inav-0.277
 exceptions-0.273
 sparing-0.269
Token.
Token ID13
Feature activation+7.46e-04

Pos logit contributions
naire+0.427
+0.421
naissance+0.414
��+0.411
+0.391
Neg logit contributions
 GOODMAN-0.403
 wip-0.392
inav-0.390
 exceptions-0.386
 sparing-0.379
Token
Token ID198
Feature activation-9.97e-02

Pos logit contributions
 GOODMAN+0.001
inav+0.001
 wip+0.001
 exceptions+0.001
 sparing+0.001
Neg logit contributions
naire-0.001
-0.001
naissance-0.001
��-0.001
-0.001
Token
Token ID235
Feature activation-3.39e-01

Pos logit contributions
naire+0.050
naissance+0.046
+0.046
��+0.044
 dominates+0.039
Neg logit contributions
 GOODMAN-0.159
 wip-0.156
inav-0.155
 exceptions-0.155
 sparing-0.153
Token
Token ID8582
Feature activation-3.64e-01

Pos logit contributions
naire+0.236
+0.232
naissance+0.227
��+0.224
+0.213
Neg logit contributions
 GOODMAN-0.306
 wip-0.297
inav-0.297
 exceptions-0.293
 sparing-0.289
Token
Token ID229
Feature activation-8.50e-01

Pos logit contributions
naire+0.091
+0.085
naissance+0.081
��+0.078
+0.065
Neg logit contributions
 GOODMAN-0.490
 wip-0.481
inav-0.480
 exceptions-0.477
 sparing-0.472
Token
Token ID118
Feature activation-1.62e-01

Pos logit contributions
naire+0.454
+0.443
naissance+0.430
��+0.424
+0.394
Neg logit contributions
 GOODMAN-0.906
 wip-0.886
inav-0.885
 exceptions-0.874
 sparing-0.864
Token
Token ID8582
Feature activation-3.49e-01

Pos logit contributions
naire+0.099
+0.097
naissance+0.095
��+0.093
+0.088
Neg logit contributions
 GOODMAN-0.160
 wip-0.156
inav-0.156
 exceptions-0.154
 sparing-0.152
Token
Token ID229
Feature activation-8.30e-01

Pos logit contributions
naire+0.092
+0.083
naissance+0.083
��+0.077
 dominates+0.065
Neg logit contributions
 GOODMAN-0.466
 wip-0.458
inav-0.457
 exceptions-0.454
 sparing-0.449
Token
Token ID116
Feature activation-1.83e-01

Pos logit contributions
naire+0.462
+0.450
naissance+0.438
��+0.432
+0.403
Neg logit contributions
 GOODMAN-0.864
 wip-0.845
inav-0.844
 exceptions-0.834
 sparing-0.824
Token
Token ID8582
Feature activation-2.91e-01

Pos logit contributions
naire+0.132
+0.130
naissance+0.127
��+0.126
+0.119
Neg logit contributions
 GOODMAN-0.160
 wip-0.155
inav-0.155
 exceptions-0.153
 sparing-0.151
Token
Token ID235
Feature activation-4.11e-01

Pos logit contributions
naire+0.079
+0.072
naissance+0.071
��+0.067
 dominates+0.056
Neg logit contributions
 GOODMAN-0.386
 wip-0.380
inav-0.379
 exceptions-0.376
 sparing-0.372
Token
Token ID222
Feature activation-4.36e-01

Pos logit contributions
naire+0.167
naissance+0.154
+0.153
��+0.146
 dominates+0.135
Neg logit contributions
 GOODMAN-0.490
 wip-0.480
inav-0.479
 exceptions-0.476
 sparing-0.470
Token https
Token ID3740
Feature activation-2.78e-01

Pos logit contributions
naire+0.310
+0.304
naissance+0.298
��+0.295
+0.280
Neg logit contributions
 GOODMAN-0.388
 wip-0.378
inav-0.377
 exceptions-0.372
 sparing-0.366
Token Choice
Token ID18502
Feature activation-9.17e-02

Pos logit contributions
naire+0.367
+0.360
naissance+0.353
��+0.350
+0.336
Neg logit contributions
 GOODMAN-0.346
inav-0.333
 wip-0.332
 exceptions-0.328
 sparing-0.322
Token at
Token ID379
Feature activation+9.40e-02

Pos logit contributions
naire+0.069
+0.069
naissance+0.067
��+0.067
+0.063
Neg logit contributions
 GOODMAN-0.077
 wip-0.074
inav-0.074
 exceptions-0.074
 sparing-0.072
Token Vanderbilt
Token ID38684
Feature activation+2.05e-01

Pos logit contributions
 GOODMAN+0.061
 wip+0.058
inav+0.058
 exceptions+0.056
 sparing+0.056
Neg logit contributions
naire-0.090
-0.089
naissance-0.087
��-0.087
-0.083
Token University
Token ID2059
Feature activation-3.74e-01

Pos logit contributions
 GOODMAN+0.197
 wip+0.192
inav+0.192
 exceptions+0.190
 sparing+0.187
Neg logit contributions
naire-0.131
-0.129
naissance-0.126
��-0.125
-0.116
Token compared
Token ID3688
Feature activation-1.11e-01

Pos logit contributions
naire+0.266
+0.263
naissance+0.257
��+0.255
+0.240
Neg logit contributions
 GOODMAN-0.332
 wip-0.322
inav-0.322
 exceptions-0.318
 sparing-0.313
Token charter
Token ID17422
Feature activation-8.21e-01

Pos logit contributions
naire+0.101
+0.100
naissance+0.098
��+0.098
+0.094
Neg logit contributions
 GOODMAN-0.077
 wip-0.074
inav-0.074
 exceptions-0.073
 sparing-0.071
Token schools
Token ID4266
Feature activation-1.14e-01

Pos logit contributions
naire+0.554
+0.542
naissance+0.530
��+0.522
+0.496
Neg logit contributions
 GOODMAN-0.761
 wip-0.740
inav-0.739
 exceptions-0.728
 sparing-0.719
Token with
Token ID351
Feature activation-1.18e-01

Pos logit contributions
naire+0.094
+0.093
naissance+0.091
��+0.090
+0.086
Neg logit contributions
 GOODMAN-0.087
 wip-0.085
inav-0.085
 exceptions-0.083
 sparing-0.082
Token traditional
Token ID4569
Feature activation-2.29e-01

Pos logit contributions
naire+0.114
+0.113
naissance+0.111
��+0.110
+0.106
Neg logit contributions
 GOODMAN-0.074
 wip-0.071
inav-0.071
 exceptions-0.069
 sparing-0.068
Token public
Token ID1171
Feature activation-3.93e-01

Pos logit contributions
naire+0.229
+0.226
naissance+0.223
��+0.221
+0.213
Neg logit contributions
 GOODMAN-0.137
 wip-0.131
inav-0.131
 exceptions-0.128
 sparing-0.125
Token schools
Token ID4266
Feature activation-2.60e-01

Pos logit contributions
naire+0.269
+0.263
naissance+0.258
��+0.255
+0.243
Neg logit contributions
 GOODMAN-0.359
inav-0.350
 wip-0.349
 exceptions-0.342
 sparing-0.339
Token the
Token ID262
Feature activation+2.07e-01

Pos logit contributions
 GOODMAN+0.133
 wip+0.128
inav+0.128
 exceptions+0.126
 sparing+0.123
Neg logit contributions
naire-0.161
-0.159
naissance-0.155
��-0.154
-0.148
Token person
Token ID1048
Feature activation-1.15e-01

Pos logit contributions
 GOODMAN+0.153
 wip+0.148
inav+0.147
 exceptions+0.145
 sparing+0.143
Neg logit contributions
naire-0.178
-0.175
naissance-0.172
��-0.170
-0.163
Token typically
Token ID6032
Feature activation+1.33e-02

Pos logit contributions
naire+0.089
+0.087
naissance+0.085
��+0.085
+0.081
Neg logit contributions
 GOODMAN-0.096
 wip-0.093
inav-0.093
 exceptions-0.092
 sparing-0.090
Token enjoys
Token ID20393
Feature activation-2.90e-01

Pos logit contributions
 GOODMAN+0.012
inav+0.012
 wip+0.012
 exceptions+0.012
 sparing+0.012
Neg logit contributions
naire-0.009
-0.009
naissance-0.008
��-0.008
-0.008
Token.
Token ID13
Feature activation+1.39e-01

Pos logit contributions
naire+0.239
+0.235
naissance+0.230
��+0.228
+0.219
Neg logit contributions
 GOODMAN-0.225
 wip-0.219
inav-0.218
 exceptions-0.213
 iod-0.210
Token Blank
Token ID31990
Feature activation-8.19e-01

Pos logit contributions
 GOODMAN+0.112
 wip+0.109
inav+0.109
 exceptions+0.107
 sparing+0.105
Neg logit contributions
naire-0.109
-0.108
naissance-0.106
��-0.105
-0.100
Tokenet
Token ID316
Feature activation-4.57e-02

Pos logit contributions
naire+0.794
+0.783
naissance+0.769
��+0.763
+0.737
Neg logit contributions
 GOODMAN-0.517
inav-0.496
 wip-0.496
 exceptions-0.485
 sparing-0.474
Token for
Token ID329
Feature activation+6.50e-03

Pos logit contributions
naire+0.041
+0.040
naissance+0.039
��+0.039
+0.037
Neg logit contributions
 GOODMAN-0.032
 wip-0.032
inav-0.031
 exceptions-0.031
 sparing-0.030
Tokents
Token ID912
Feature activation-1.18e-02

Pos logit contributions
 GOODMAN+0.004
inav+0.004
 wip+0.004
 exceptions+0.004
 sparing+0.004
Neg logit contributions
naire-0.006
-0.006
naissance-0.006
��-0.006
-0.006
Token are
Token ID389
Feature activation+1.56e-01

Pos logit contributions
naire+0.010
+0.010
naissance+0.010
��+0.009
+0.009
Neg logit contributions
 GOODMAN-0.009
 wip-0.009
inav-0.009
 exceptions-0.009
 sparing-0.008
Token good
Token ID922
Feature activation+1.54e-01

Pos logit contributions
 GOODMAN+0.103
 wip+0.099
inav+0.099
 exceptions+0.097
 sparing+0.095
Neg logit contributions
naire-0.147
-0.145
naissance-0.142
��-0.141
-0.136
TokenNS
Token ID8035
Feature activation+3.22e-01

Pos logit contributions
naire+0.177
+0.174
naissance+0.171
��+0.170
+0.164
Neg logit contributions
 GOODMAN-0.127
 wip-0.122
inav-0.121
 exceptions-0.119
 sparing-0.117
Token via
Token ID2884
Feature activation-8.97e-02

Pos logit contributions
 GOODMAN+0.257
 wip+0.249
inav+0.248
 exceptions+0.245
 sparing+0.240
Neg logit contributions
naire-0.259
-0.255
naissance-0.250
��-0.248
-0.237
Token Getty
Token ID7136
Feature activation+4.11e-01

Pos logit contributions
naire+0.094
+0.093
naissance+0.091
��+0.091
+0.088
Neg logit contributions
 GOODMAN-0.049
inav-0.047
 wip-0.047
 exceptions-0.046
 sparing-0.045
Token Images
Token ID5382
Feature activation+4.34e-01

Pos logit contributions
 GOODMAN+0.274
inav+0.264
 wip+0.264
 exceptions+0.259
 sparing+0.254
Neg logit contributions
naire-0.382
-0.378
naissance-0.371
��-0.368
-0.354
Token)
Token ID8
Feature activation+3.17e-01

Pos logit contributions
 GOODMAN+0.284
 wip+0.273
inav+0.273
 exceptions+0.268
 sparing+0.262
Neg logit contributions
naire-0.410
-0.405
naissance-0.398
��-0.395
-0.380
Token Indiana
Token ID10278
Feature activation+5.67e-01

Pos logit contributions
 GOODMAN+0.240
 wip+0.232
inav+0.231
 exceptions+0.228
 sparing+0.223
Neg logit contributions
naire-0.267
-0.264
naissance-0.260
��-0.257
-0.245
Token Gov
Token ID10964
Feature activation+4.06e-01

Pos logit contributions
 GOODMAN+0.286
 wip+0.272
inav+0.268
 exceptions+0.267
 sparing+0.262
Neg logit contributions
naire-0.620
-0.612
naissance-0.608
��-0.600
-0.579
Token.
Token ID13
Feature activation+3.08e-02

Pos logit contributions
 GOODMAN+0.318
 wip+0.309
inav+0.308
 exceptions+0.303
 sparing+0.298
Neg logit contributions
naire-0.330
-0.326
naissance-0.319
��-0.316
-0.302
Token Mike
Token ID4995
Feature activation-2.89e-01

Pos logit contributions
 GOODMAN+0.027
 wip+0.026
 exceptions+0.026
 sparing+0.026
inav+0.026
Neg logit contributions
naire-0.022
-0.022
naissance-0.022
��-0.021
-0.020
Token Pence
Token ID17339
Feature activation+1.69e-01

Pos logit contributions
naire+0.294
+0.293
naissance+0.290
��+0.287
+0.277
Neg logit contributions
 GOODMAN-0.167
 wip-0.158
 exceptions-0.157
inav-0.155
 sparing-0.152
Token Pence
Token ID17339
Feature activation+1.18e-01

Pos logit contributions
 GOODMAN+0.138
 wip+0.134
inav+0.133
 exceptions+0.133
 sparing+0.131
Neg logit contributions
naire-0.132
-0.130
naissance-0.128
��-0.127
-0.120
Token Arabs
Token ID22457
Feature activation+4.53e-01

Pos logit contributions
 GOODMAN+0.036
inav+0.034
 wip+0.034
 exceptions+0.033
 sparing+0.033
Neg logit contributions
naire-0.046
-0.045
naissance-0.044
��-0.044
-0.042
Token or
Token ID393
Feature activation+2.66e-01

Pos logit contributions
 GOODMAN+0.300
 wip+0.289
inav+0.289
 exceptions+0.284
 sparing+0.278
Neg logit contributions
naire-0.423
-0.418
naissance-0.411
��-0.407
-0.392
Token Muslims
Token ID7045
Feature activation+1.32e-01

Pos logit contributions
 GOODMAN+0.167
 wip+0.161
inav+0.161
 exceptions+0.157
 sparing+0.154
Neg logit contributions
naire-0.258
-0.255
naissance-0.251
��-0.249
-0.240
Token
Token ID564
Feature activation+1.27e-01

Pos logit contributions
 GOODMAN+0.086
inav+0.082
 wip+0.082
 exceptions+0.080
 sparing+0.079
Neg logit contributions
naire-0.126
-0.124
naissance-0.122
��-0.121
-0.116
Token
Token ID250
Feature activation+7.01e-02

Pos logit contributions
 GOODMAN+0.157
 wip+0.154
inav+0.154
 exceptions+0.153
 sparing+0.151
Neg logit contributions
naire-0.045
-0.043
naissance-0.042
��-0.040
 dominates-0.036
Tokensav
Token ID39308
Feature activation+5.93e-01

Pos logit contributions
 GOODMAN+0.034
 wip+0.032
inav+0.032
 exceptions+0.031
 sparing+0.030
Neg logit contributions
naire-0.079
-0.078
naissance-0.077
��-0.076
-0.074
Tokenages
Token ID1095
Feature activation+9.78e-02

Pos logit contributions
 GOODMAN+0.434
inav+0.422
 wip+0.421
 exceptions+0.414
 sparing+0.406
Neg logit contributions
naire-0.512
-0.505
naissance-0.495
��-0.492
-0.471
Token,
Token ID11
Feature activation+3.46e-02

Pos logit contributions
 GOODMAN+0.079
inav+0.077
 wip+0.077
 exceptions+0.076
 sparing+0.075
Neg logit contributions
naire-0.077
-0.076
naissance-0.074
��-0.073
-0.070
Token
Token ID447
Feature activation+8.61e-02

Pos logit contributions
 GOODMAN+0.022
inav+0.021
 wip+0.021
 exceptions+0.021
 sparing+0.020
Neg logit contributions
naire-0.033
-0.033
naissance-0.032
��-0.032
-0.031
Token
Token ID251
Feature activation-2.28e-01

Pos logit contributions
 GOODMAN+0.106
 wip+0.104
inav+0.104
 exceptions+0.103
 sparing+0.102
Neg logit contributions
naire-0.032
-0.031
naissance-0.029
��-0.029
-0.026
Token nor
Token ID4249
Feature activation+3.24e-01

Pos logit contributions
naire+0.219
+0.216
naissance+0.211
��+0.211
+0.203
Neg logit contributions
 GOODMAN-0.146
inav-0.141
 wip-0.140
 exceptions-0.135
 iod-0.134
Token financial
Token ID3176
Feature activation-7.18e-02

Pos logit contributions
naire+0.085
+0.084
naissance+0.082
��+0.082
+0.079
Neg logit contributions
 GOODMAN-0.060
 wip-0.058
inav-0.057
 exceptions-0.057
 sparing-0.055
Token results
Token ID2482
Feature activation-1.28e-01

Pos logit contributions
naire+0.073
+0.071
naissance+0.070
��+0.070
+0.067
Neg logit contributions
 GOODMAN-0.042
inav-0.041
 wip-0.040
 exceptions-0.039
 sparing-0.038
Token in
Token ID287
Feature activation+6.20e-02

Pos logit contributions
naire+0.110
+0.108
naissance+0.106
��+0.105
+0.101
Neg logit contributions
 GOODMAN-0.095
inav-0.092
 wip-0.092
 exceptions-0.090
 sparing-0.088
Token conjunction
Token ID17856
Feature activation-1.77e-01

Pos logit contributions
 GOODMAN+0.038
inav+0.037
 wip+0.037
 exceptions+0.036
 sparing+0.035
Neg logit contributions
naire-0.061
-0.060
naissance-0.059
��-0.058
-0.056
Token with
Token ID351
Feature activation-7.76e-03

Pos logit contributions
naire+0.126
+0.124
naissance+0.121
��+0.120
+0.114
Neg logit contributions
 GOODMAN-0.157
 wip-0.153
inav-0.153
 exceptions-0.151
 sparing-0.148
Token tax
Token ID1687
Feature activation+4.84e-01

Pos logit contributions
naire+0.007
+0.007
naissance+0.007
��+0.007
+0.007
Neg logit contributions
 GOODMAN-0.005
inav-0.005
 wip-0.005
 exceptions-0.005
 sparing-0.005
Token filings
Token ID28058
Feature activation+3.55e-01

Pos logit contributions
 GOODMAN+0.296
inav+0.284
 wip+0.284
 exceptions+0.277
 sparing+0.272
Neg logit contributions
naire-0.478
-0.472
naissance-0.464
��-0.461
-0.445
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
 GOODMAN+0.271
 wip+0.263
inav+0.262
 exceptions+0.259
 sparing+0.254
Neg logit contributions
naire-0.296
-0.292
naissance-0.286
��-0.284
-0.271
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
 GOODMAN+0.126
 wip+0.122
inav+0.122
 exceptions+0.120
 sparing+0.118
Neg logit contributions
naire-0.131
-0.129
naissance-0.127
��-0.126
-0.120
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
 GOODMAN+0.102
 wip+0.099
inav+0.099
 exceptions+0.097
 sparing+0.095
Neg logit contributions
naire-0.104
-0.102
naissance-0.099
��-0.099
-0.094
TokenStephen
Token ID24920
Feature activation+7.96e-02

Pos logit contributions
 GOODMAN+0.088
inav+0.086
 wip+0.086
 exceptions+0.085
 sparing+0.082
Neg logit contributions
naire-0.088
-0.087
naissance-0.085
��-0.085
-0.081
Token have
Token ID423
Feature activation-4.27e-02

Pos logit contributions
 GOODMAN+0.185
 wip+0.180
inav+0.179
 exceptions+0.177
 sparing+0.174
Neg logit contributions
naire-0.193
-0.190
naissance-0.186
��-0.185
-0.176
Token changed
Token ID3421
Feature activation-8.98e-02

Pos logit contributions
naire+0.037
+0.036
naissance+0.036
��+0.035
+0.034
Neg logit contributions
 GOODMAN-0.031
 wip-0.030
inav-0.030
 exceptions-0.030
 sparing-0.029
Token.
Token ID13
Feature activation+6.80e-02

Pos logit contributions
naire+0.077
+0.076
naissance+0.074
��+0.073
+0.071
Neg logit contributions
 GOODMAN-0.067
inav-0.065
 wip-0.065
 exceptions-0.063
 sparing-0.062
Token So
Token ID1406
Feature activation-9.95e-02

Pos logit contributions
 GOODMAN+0.056
 wip+0.055
inav+0.055
 exceptions+0.054
 sparing+0.053
Neg logit contributions
naire-0.052
-0.052
naissance-0.051
��-0.050
-0.048
Token checks
Token ID8794
Feature activation+1.22e-01

Pos logit contributions
naire+0.094
+0.093
naissance+0.091
��+0.091
+0.088
Neg logit contributions
 GOODMAN-0.065
inav-0.062
 wip-0.062
 exceptions-0.061
 sparing-0.059
Tokenum
Token ID388
Feature activation+5.26e-01

Pos logit contributions
 GOODMAN+0.084
inav+0.081
 wip+0.081
 exceptions+0.079
 sparing+0.077
Neg logit contributions
naire-0.112
-0.110
naissance-0.108
��-0.107
-0.104
Token everything
Token ID2279
Feature activation-6.20e-02

Pos logit contributions
 GOODMAN+0.417
 wip+0.406
inav+0.405
 exceptions+0.399
 sparing+0.392
Neg logit contributions
naire-0.423
-0.417
naissance-0.409
��-0.405
-0.387
Token and
Token ID290
Feature activation+6.10e-03

Pos logit contributions
naire+0.053
+0.052
naissance+0.051
��+0.051
+0.049
Neg logit contributions
 GOODMAN-0.046
inav-0.045
 wip-0.044
 exceptions-0.044
 sparing-0.043
Token compare
Token ID8996
Feature activation+8.71e-02

Pos logit contributions
 GOODMAN+0.004
inav+0.004
 wip+0.004
 exceptions+0.004
 sparing+0.004
Neg logit contributions
naire-0.005
-0.005
naissance-0.005
��-0.005
-0.005
Token the
Token ID262
Feature activation+6.17e-02

Pos logit contributions
 GOODMAN+0.057
inav+0.055
 wip+0.055
 exceptions+0.053
 sparing+0.052
Neg logit contributions
naire-0.082
-0.081
naissance-0.080
��-0.079
-0.076
Token checks
Token ID8794
Feature activation+1.48e-01

Pos logit contributions
 GOODMAN+0.038
inav+0.036
 wip+0.036
 exceptions+0.035
 sparing+0.035
Neg logit contributions
naire-0.061
-0.060
naissance-0.059
��-0.059
-0.057
Token good
Token ID922
Feature activation+2.09e-01

Pos logit contributions
 GOODMAN+0.259
inav+0.249
 wip+0.249
 exceptions+0.243
 sparing+0.238
Neg logit contributions
naire-0.400
-0.395
naissance-0.388
��-0.385
-0.371
Token launch
Token ID4219
Feature activation+3.68e-01

Pos logit contributions
 GOODMAN+0.131
inav+0.126
 wip+0.125
 exceptions+0.122
 sparing+0.120
Neg logit contributions
naire-0.203
-0.201
naissance-0.197
��-0.196
-0.189
Token conditions
Token ID3403
Feature activation-2.68e-02

Pos logit contributions
 GOODMAN+0.249
 wip+0.241
inav+0.240
 exceptions+0.236
 sparing+0.232
Neg logit contributions
naire-0.339
-0.334
naissance-0.328
��-0.326
-0.313
Token.
Token ID13
Feature activation+2.11e-01

Pos logit contributions
naire+0.022
+0.021
naissance+0.021
��+0.021
+0.020
Neg logit contributions
 GOODMAN-0.021
inav-0.020
 wip-0.020
 exceptions-0.020
 sparing-0.020
Token The
Token ID383
Feature activation-3.25e-02

Pos logit contributions
 GOODMAN+0.182
 wip+0.177
inav+0.176
 exceptions+0.174
 sparing+0.171
Neg logit contributions
naire-0.155
-0.153
naissance-0.150
��-0.148
-0.140
Token sun
Token ID4252
Feature activation+5.04e-01

Pos logit contributions
naire+0.030
+0.029
naissance+0.029
��+0.028
+0.027
Neg logit contributions
 GOODMAN-0.022
inav-0.021
 wip-0.021
 exceptions-0.021
 sparing-0.021
Token was
Token ID373
Feature activation+6.36e-02

Pos logit contributions
 GOODMAN+0.503
 wip+0.498
inav+0.492
 exceptions+0.487
 sparing+0.483
Neg logit contributions
naire-0.299
-0.296
naissance-0.286
��-0.285
-0.264
Token setting
Token ID4634
Feature activation+1.32e-01

Pos logit contributions
 GOODMAN+0.040
inav+0.038
 wip+0.038
 exceptions+0.037
 sparing+0.036
Neg logit contributions
naire-0.062
-0.061
naissance-0.060
��-0.060
-0.058
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
 GOODMAN+0.098
 wip+0.095
inav+0.095
 exceptions+0.093
 sparing+0.092
Neg logit contributions
naire-0.113
-0.112
naissance-0.110
��-0.109
-0.104
Token The
Token ID383
Feature activation+1.11e-02

Pos logit contributions
 GOODMAN+0.186
 wip+0.181
inav+0.180
 exceptions+0.178
 sparing+0.174
Neg logit contributions
naire-0.159
-0.157
naissance-0.154
��-0.152
-0.144
Token king
Token ID5822
Feature activation+3.57e-01

Pos logit contributions
 GOODMAN+0.008
inav+0.007
 wip+0.007
 exceptions+0.007
 sparing+0.007
Neg logit contributions
naire-0.010
-0.010
naissance-0.010
��-0.010
-0.009
Token try
Token ID1949
Feature activation+1.28e-01

Pos logit contributions
 GOODMAN+0.087
 wip+0.085
inav+0.085
 exceptions+0.084
 sparing+0.083
Neg logit contributions
naire-0.104
-0.103
��-0.101
naissance-0.101
-0.096
Token to
Token ID284
Feature activation+2.63e-02

Pos logit contributions
 GOODMAN+0.086
inav+0.083
 wip+0.082
 exceptions+0.080
 sparing+0.078
Neg logit contributions
naire-0.120
-0.118
naissance-0.116
��-0.115
-0.111
Token attack
Token ID1368
Feature activation+1.49e-02

Pos logit contributions
 GOODMAN+0.019
 wip+0.019
inav+0.019
 exceptions+0.018
 sparing+0.018
Neg logit contributions
naire-0.023
-0.023
naissance-0.022
��-0.022
-0.021
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
 GOODMAN+0.010
inav+0.009
 wip+0.009
 exceptions+0.009
 sparing+0.009
Neg logit contributions
naire-0.014
-0.014
naissance-0.014
��-0.014
-0.013
Token I
Token ID314
Feature activation+1.54e-01

Pos logit contributions
 GOODMAN+0.095
 wip+0.093
inav+0.093
 exceptions+0.091
 sparing+0.090
Neg logit contributions
naire-0.096
-0.094
naissance-0.092
��-0.091
-0.087
Token think
Token ID892
Feature activation+2.32e-01

Pos logit contributions
 GOODMAN+0.115
 wip+0.111
inav+0.111
 exceptions+0.109
 sparing+0.107
Neg logit contributions
naire-0.132
-0.130
naissance-0.127
��-0.127
-0.121
Token tomorrow
Token ID9439
Feature activation+1.63e-01

Pos logit contributions
 GOODMAN+0.147
 wip+0.142
inav+0.142
 exceptions+0.139
 sparing+0.136
Neg logit contributions
naire-0.224
-0.221
naissance-0.217
��-0.216
-0.208
Token is
Token ID318
Feature activation-8.30e-02

Pos logit contributions
 GOODMAN+0.136
 wip+0.132
inav+0.132
 exceptions+0.130
 sparing+0.128
Neg logit contributions
naire-0.124
-0.122
naissance-0.119
��-0.118
-0.113
Token the
Token ID262
Feature activation+1.75e-01

Pos logit contributions
naire+0.085
+0.084
naissance+0.083
��+0.082
+0.079
Neg logit contributions
 GOODMAN-0.048
inav-0.046
 wip-0.046
 exceptions-0.044
 sparing-0.044
Token best
Token ID1266
Feature activation+1.60e-01

Pos logit contributions
 GOODMAN+0.117
 wip+0.113
inav+0.113
 exceptions+0.111
 sparing+0.109
Neg logit contributions
naire-0.163
-0.161
naissance-0.158
��-0.157
-0.151
Token for
Token ID329
Feature activation+5.79e-02

Pos logit contributions
 GOODMAN+0.110
 wip+0.106
inav+0.106
 exceptions+0.104
 sparing+0.102
Neg logit contributions
naire-0.147
-0.145
naissance-0.142
��-0.141
-0.136
Token after
Token ID706
Feature activation-6.39e-02

Pos logit contributions
naire+0.130
+0.128
naissance+0.125
��+0.125
+0.120
Neg logit contributions
 GOODMAN-0.100
 wip-0.096
inav-0.096
 exceptions-0.094
 sparing-0.092
Token
Token ID564
Feature activation-2.31e-01

Pos logit contributions
naire+0.059
+0.058
naissance+0.057
��+0.057
+0.055
Neg logit contributions
 GOODMAN-0.043
 wip-0.041
inav-0.041
 exceptions-0.040
 sparing-0.040
Token
Token ID250
Feature activation-1.59e-01

Pos logit contributions
naire+0.084
+0.079
naissance+0.079
��+0.074
 dominates+0.066
Neg logit contributions
 GOODMAN-0.285
 wip-0.280
inav-0.280
 exceptions-0.278
 sparing-0.274
Tokenthe
Token ID1169
Feature activation-2.36e-01

Pos logit contributions
naire+0.090
+0.088
naissance+0.085
��+0.084
+0.079
Neg logit contributions
 GOODMAN-0.165
 wip-0.161
inav-0.161
 exceptions-0.159
 sparing-0.157
Token bigger
Token ID5749
Feature activation-2.77e-01

Pos logit contributions
naire+0.203
+0.200
naissance+0.196
��+0.195
+0.186
Neg logit contributions
 GOODMAN-0.175
 wip-0.169
inav-0.169
 exceptions-0.166
 sparing-0.163
Token fish
Token ID5916
Feature activation+3.58e-01

Pos logit contributions
naire+0.256
+0.254
naissance+0.250
��+0.247
+0.238
Neg logit contributions
 GOODMAN-0.186
 wip-0.180
inav-0.179
 exceptions-0.177
 sparing-0.173
Token
Token ID447
Feature activation-1.88e-01

Pos logit contributions
 GOODMAN+0.279
inav+0.271
 wip+0.271
 exceptions+0.265
 sparing+0.261
Neg logit contributions
naire-0.295
-0.290
naissance-0.284
��-0.281
-0.269
Token
Token ID251
Feature activation-4.63e-01

Pos logit contributions
naire+0.051
naissance+0.046
+0.046
��+0.042
 dominates+0.036
Neg logit contributions
 GOODMAN-0.250
 wip-0.245
inav-0.244
 exceptions-0.243
 sparing-0.240
Token at
Token ID379
Feature activation-1.54e-02

Pos logit contributions
naire+0.395
+0.388
naissance+0.381
��+0.377
+0.362
Neg logit contributions
 GOODMAN-0.346
inav-0.336
 wip-0.335
 exceptions-0.328
 sparing-0.323
Token Sea
Token ID6896
Feature activation-2.47e-01

Pos logit contributions
naire+0.014
+0.014
naissance+0.014
��+0.014
+0.013
Neg logit contributions
 GOODMAN-0.010
inav-0.010
 wip-0.010
 exceptions-0.010
 sparing-0.009
TokenWorld
Token ID10603
Feature activation+2.32e-01

Pos logit contributions
naire+0.212
+0.209
naissance+0.205
��+0.204
+0.195
Neg logit contributions
 GOODMAN-0.182
 wip-0.177
inav-0.176
 exceptions-0.173
 sparing-0.170
Token is
Token ID318
Feature activation-6.25e-02

Pos logit contributions
 GOODMAN+0.248
 wip+0.242
inav+0.241
 exceptions+0.239
 sparing+0.235
Neg logit contributions
naire-0.205
-0.202
naissance-0.199
��-0.196
-0.186
Token simply
Token ID2391
Feature activation-5.12e-02

Pos logit contributions
naire+0.064
+0.064
naissance+0.063
��+0.062
+0.060
Neg logit contributions
 GOODMAN-0.035
inav-0.034
 wip-0.034
 exceptions-0.033
 sparing-0.032
Token not
Token ID407
Feature activation+1.31e-01

Pos logit contributions
naire+0.052
+0.052
naissance+0.051
��+0.050
+0.049
Neg logit contributions
 GOODMAN-0.030
inav-0.029
 wip-0.028
 exceptions-0.028
 sparing-0.027
Token worth
Token ID2861
Feature activation+2.20e-01

Pos logit contributions
 GOODMAN+0.072
inav+0.070
 wip+0.069
 exceptions+0.067
 sparing+0.065
Neg logit contributions
naire-0.137
-0.136
naissance-0.133
��-0.133
-0.129
Token it
Token ID340
Feature activation-1.04e-01

Pos logit contributions
 GOODMAN+0.116
inav+0.110
 wip+0.110
 exceptions+0.105
 sparing+0.101
Neg logit contributions
naire-0.235
-0.234
��-0.229
naissance-0.228
-0.222
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
naire+0.083
+0.082
naissance+0.080
��+0.079
+0.076
Neg logit contributions
 GOODMAN-0.083
inav-0.081
 wip-0.080
 exceptions-0.078
 sparing-0.077
Token
Token ID198
Feature activation+8.30e-02

Pos logit contributions
 GOODMAN+0.092
 wip+0.089
inav+0.089
 exceptions+0.087
 sparing+0.086
Neg logit contributions
naire-0.096
-0.094
naissance-0.093
��-0.092
-0.088
Token
Token ID198
Feature activation+6.53e-02

Pos logit contributions
 GOODMAN+0.066
 wip+0.064
inav+0.064
 exceptions+0.063
 sparing+0.062
Neg logit contributions
naire-0.067
-0.065
naissance-0.064
��-0.063
-0.061
Token
Token ID447
Feature activation-6.65e-03

Pos logit contributions
 GOODMAN+0.053
 wip+0.051
inav+0.051
 exceptions+0.050
 sparing+0.049
Neg logit contributions
naire-0.052
-0.051
naissance-0.050
��-0.050
-0.047
Token
Token ID250
Feature activation+2.15e-02

Pos logit contributions
naire+0.002
+0.002
naissance+0.002
��+0.002
 dominates+0.002
Neg logit contributions
 GOODMAN-0.008
 wip-0.008
inav-0.008
 exceptions-0.008
 sparing-0.008
TokenWhat
Token ID2061
Feature activation-9.96e-02

Pos logit contributions
 GOODMAN+0.017
 wip+0.017
inav+0.017
 exceptions+0.016
 sparing+0.016
Neg logit contributions
naire-0.017
-0.017
naissance-0.017
��-0.016
-0.016
Token Trump
Token ID1301
Feature activation-5.81e-02

Pos logit contributions
naire+0.026
+0.026
naissance+0.025
��+0.025
+0.024
Neg logit contributions
 GOODMAN-0.019
 wip-0.019
inav-0.019
 exceptions-0.018
 sparing-0.018
Token closing
Token ID9605
Feature activation+1.95e-02

Pos logit contributions
naire+0.054
+0.053
naissance+0.052
��+0.052
+0.050
Neg logit contributions
 GOODMAN-0.039
inav-0.038
 wip-0.038
 exceptions-0.037
 sparing-0.036
Token the
Token ID262
Feature activation+6.36e-02

Pos logit contributions
 GOODMAN+0.013
inav+0.012
 wip+0.012
 exceptions+0.012
 sparing+0.012
Neg logit contributions
naire-0.018
-0.018
naissance-0.018
��-0.018
-0.017
Token gap
Token ID7625
Feature activation-5.31e-01

Pos logit contributions
 GOODMAN+0.065
 wip+0.064
inav+0.064
 exceptions+0.063
 sparing+0.062
Neg logit contributions
naire-0.037
-0.036
naissance-0.035
��-0.034
-0.032
Token with
Token ID351
Feature activation-6.59e-02

Pos logit contributions
naire+0.431
+0.424
naissance+0.416
��+0.413
+0.394
Neg logit contributions
 GOODMAN-0.417
 wip-0.405
inav-0.404
 exceptions-0.398
 sparing-0.392
Token Mrs
Token ID9074
Feature activation+6.28e-03

Pos logit contributions
naire+0.062
+0.061
naissance+0.060
��+0.060
+0.058
Neg logit contributions
 GOODMAN-0.043
 wip-0.042
inav-0.042
 exceptions-0.041
 sparing-0.040
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
 GOODMAN+0.005
 wip+0.005
inav+0.005
 exceptions+0.005
 sparing+0.005
Neg logit contributions
naire-0.005
-0.005
naissance-0.005
��-0.005
-0.005
Token Clinton
Token ID2605
Feature activation-1.68e-01

Pos logit contributions
 GOODMAN+0.018
 wip+0.017
inav+0.017
 exceptions+0.017
 sparing+0.017
Neg logit contributions
naire-0.019
-0.019
naissance-0.019
��-0.018
-0.018
Token
Token ID851
Feature activation-1.55e-01

Pos logit contributions
naire+0.137
+0.135
naissance+0.132
��+0.131
+0.125
Neg logit contributions
 GOODMAN-0.131
 wip-0.127
inav-0.127
 exceptions-0.125
 sparing-0.123
Token largely
Token ID5688
Feature activation-2.75e-01

Pos logit contributions
naire+0.142
+0.140
naissance+0.138
��+0.137
+0.131
Neg logit contributions
 GOODMAN-0.106
 wip-0.103
inav-0.102
 exceptions-0.101
 sparing-0.099
Token because
Token ID780
Feature activation-3.11e-02

Pos logit contributions
naire+0.253
+0.250
naissance+0.245
��+0.244
+0.234
Neg logit contributions
 GOODMAN-0.186
 wip-0.180
inav-0.180
 exceptions-0.176
 sparing-0.173
Tokenills
Token ID2171
Feature activation+4.51e-01

Pos logit contributions
 GOODMAN+0.116
 wip+0.111
inav+0.111
 exceptions+0.109
 sparing+0.107
Neg logit contributions
naire-0.169
-0.167
naissance-0.164
��-0.162
-0.157
Token and
Token ID290
Feature activation+8.28e-02

Pos logit contributions
 GOODMAN+0.333
 wip+0.322
inav+0.322
 exceptions+0.318
 sparing+0.312
Neg logit contributions
naire-0.387
-0.381
naissance-0.375
��-0.372
-0.356
Token talents
Token ID18054
Feature activation+1.45e-01

Pos logit contributions
 GOODMAN+0.060
 wip+0.058
inav+0.058
 exceptions+0.057
 sparing+0.056
Neg logit contributions
naire-0.072
-0.071
naissance-0.070
��-0.069
-0.067
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
 GOODMAN+0.111
 wip+0.108
inav+0.108
 exceptions+0.106
 sparing+0.104
Neg logit contributions
naire-0.120
-0.119
naissance-0.116
��-0.115
-0.110
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
 GOODMAN+0.110
 wip+0.107
inav+0.106
 exceptions+0.104
 sparing+0.103
Neg logit contributions
naire-0.114
-0.111
naissance-0.109
��-0.108
-0.104
TokenSecondly
Token ID44276
Feature activation+1.63e-01

Pos logit contributions
 GOODMAN+0.089
inav+0.087
 wip+0.087
 exceptions+0.085
 sparing+0.084
Neg logit contributions
naire-0.087
-0.086
naissance-0.084
��-0.084
-0.080
Token,
Token ID11
Feature activation-2.36e-02

Pos logit contributions
 GOODMAN+0.138
 wip+0.134
inav+0.134
 exceptions+0.132
 sparing+0.130
Neg logit contributions
naire-0.123
-0.121
naissance-0.119
��-0.117
-0.112
Token the
Token ID262
Feature activation+1.36e-01

Pos logit contributions
naire+0.024
+0.023
naissance+0.023
��+0.023
+0.022
Neg logit contributions
 GOODMAN-0.014
inav-0.014
 wip-0.014
 exceptions-0.013
 sparing-0.013
Token content
Token ID2695
Feature activation-4.20e-02

Pos logit contributions
 GOODMAN+0.102
 wip+0.098
inav+0.098
 exceptions+0.097
 sparing+0.095
Neg logit contributions
naire-0.115
-0.114
naissance-0.112
��-0.111
-0.106
Token gives
Token ID3607
Feature activation-1.31e-01

Pos logit contributions
naire+0.028
+0.027
naissance+0.027
��+0.026
+0.025
Neg logit contributions
 GOODMAN-0.039
 wip-0.038
inav-0.038
 exceptions-0.038
 sparing-0.037
Token some
Token ID617
Feature activation-5.25e-02

Pos logit contributions
naire+0.134
+0.133
naissance+0.131
��+0.130
+0.126
Neg logit contributions
 GOODMAN-0.075
inav-0.072
 wip-0.072
 exceptions-0.070
 sparing-0.069
Token.
Token ID13
Feature activation+2.18e-02

Pos logit contributions
 GOODMAN+0.047
inav+0.045
 wip+0.045
 exceptions+0.045
 sparing+0.044
Neg logit contributions
naire-0.049
-0.048
naissance-0.047
��-0.047
-0.045
Token
Token ID198
Feature activation-1.42e-02

Pos logit contributions
 GOODMAN+0.018
 wip+0.017
inav+0.017
 exceptions+0.017
 sparing+0.017
Neg logit contributions
naire-0.017
-0.017
naissance-0.017
��-0.016
-0.016
Token
Token ID198
Feature activation-3.87e-02

Pos logit contributions
naire+0.011
+0.011
naissance+0.011
��+0.011
+0.010
Neg logit contributions
 GOODMAN-0.011
 wip-0.011
inav-0.011
 exceptions-0.011
 sparing-0.011
TokenCand
Token ID41572
Feature activation-9.77e-02

Pos logit contributions
naire+0.030
+0.029
naissance+0.029
��+0.029
+0.027
Neg logit contributions
 GOODMAN-0.032
 wip-0.031
inav-0.031
 exceptions-0.031
 sparing-0.030
Tokenace
Token ID558
Feature activation-1.54e-01

Pos logit contributions
naire+0.080
+0.079
naissance+0.078
��+0.077
+0.074
Neg logit contributions
 GOODMAN-0.076
inav-0.074
 wip-0.073
 exceptions-0.072
 sparing-0.071
Token Hilton
Token ID31248
Feature activation-3.42e-01

Pos logit contributions
naire+0.115
+0.113
naissance+0.111
��+0.110
+0.104
Neg logit contributions
 GOODMAN-0.131
inav-0.127
 wip-0.127
 exceptions-0.125
 sparing-0.123
Token said
Token ID531
Feature activation+8.25e-02

Pos logit contributions
naire+0.253
+0.249
naissance+0.245
��+0.243
+0.230
Neg logit contributions
 GOODMAN-0.293
 wip-0.284
inav-0.283
 exceptions-0.281
 sparing-0.275
Token she
Token ID673
Feature activation-1.61e-01

Pos logit contributions
 GOODMAN+0.060
 wip+0.058
inav+0.058
 exceptions+0.057
 sparing+0.056
Neg logit contributions
naire-0.072
-0.071
naissance-0.070
��-0.069
-0.066
Token
Token ID447
Feature activation-9.61e-02

Pos logit contributions
naire+0.112
+0.110
naissance+0.108
��+0.107
+0.101
Neg logit contributions
 GOODMAN-0.145
 wip-0.142
inav-0.140
 exceptions-0.139
 sparing-0.137
Token
Token ID247
Feature activation-4.32e-02

Pos logit contributions
naire+0.063
+0.061
naissance+0.060
��+0.059
 dominates+0.055
Neg logit contributions
 GOODMAN-0.090
 wip-0.088
inav-0.088
 exceptions-0.087
 sparing-0.086
Tokens
Token ID82
Feature activation+4.49e-02

Pos logit contributions
naire+0.045
+0.045
naissance+0.044
��+0.044
+0.042
Neg logit contributions
 GOODMAN-0.024
inav-0.023
 wip-0.023
 exceptions-0.022
 sparing-0.022
Token.
Token ID13
Feature activation-2.62e-02

Pos logit contributions
naire+0.240
+0.237
naissance+0.232
��+0.230
+0.220
Neg logit contributions
 GOODMAN-0.212
inav-0.205
 wip-0.205
 exceptions-0.201
 sparing-0.197
Token
Token ID198
Feature activation-5.94e-02

Pos logit contributions
naire+0.020
+0.020
naissance+0.020
��+0.020
+0.019
Neg logit contributions
 GOODMAN-0.021
 wip-0.021
inav-0.021
 exceptions-0.020
 sparing-0.020
Token
Token ID198
Feature activation-7.24e-02

Pos logit contributions
naire+0.048
+0.047
naissance+0.046
��+0.046
+0.044
Neg logit contributions
 GOODMAN-0.047
 wip-0.046
inav-0.046
 exceptions-0.045
 sparing-0.044
TokenThe
Token ID464
Feature activation-1.69e-01

Pos logit contributions
naire+0.057
+0.056
naissance+0.055
��+0.055
+0.052
Neg logit contributions
 GOODMAN-0.059
inav-0.057
 wip-0.057
 exceptions-0.056
 sparing-0.055
Token risk
Token ID2526
Feature activation-2.67e-01

Pos logit contributions
naire+0.155
+0.153
naissance+0.150
��+0.149
+0.144
Neg logit contributions
 GOODMAN-0.116
 wip-0.111
inav-0.111
 exceptions-0.109
 sparing-0.107
Token comes
Token ID2058
Feature activation-1.98e-01

Pos logit contributions
naire+0.189
+0.186
naissance+0.183
��+0.180
+0.170
Neg logit contributions
 GOODMAN-0.238
 wip-0.232
inav-0.231
 exceptions-0.229
 sparing-0.226
Token after
Token ID706
Feature activation+4.27e-02

Pos logit contributions
naire+0.157
+0.155
naissance+0.151
��+0.150
+0.144
Neg logit contributions
 GOODMAN-0.159
inav-0.155
 wip-0.154
 exceptions-0.151
 sparing-0.149
Token the
Token ID262
Feature activation-2.29e-02

Pos logit contributions
 GOODMAN+0.024
 wip+0.023
inav+0.023
 exceptions+0.023
 sparing+0.022
Neg logit contributions
naire-0.044
-0.043
naissance-0.043
��-0.042
-0.041
Token rule
Token ID3896
Feature activation-1.70e-01

Pos logit contributions
naire+0.021
+0.020
naissance+0.020
��+0.020
+0.019
Neg logit contributions
 GOODMAN-0.016
 wip-0.015
inav-0.015
 exceptions-0.015
 sparing-0.015
Token change
Token ID1487
Feature activation-1.58e-01

Pos logit contributions
naire+0.145
+0.143
naissance+0.141
��+0.140
+0.134
Neg logit contributions
 GOODMAN-0.126
 wip-0.122
inav-0.121
 exceptions-0.121
 sparing-0.118
Token when
Token ID618
Feature activation+2.08e-01

Pos logit contributions
naire+0.110
+0.108
naissance+0.106
��+0.105
+0.100
Neg logit contributions
 GOODMAN-0.142
 wip-0.139
inav-0.138
 exceptions-0.137
 sparing-0.135
Token or
Token ID393
Feature activation+1.38e-01

Pos logit contributions
naire+0.080
+0.079
naissance+0.077
��+0.077
+0.073
Neg logit contributions
 GOODMAN-0.077
 wip-0.075
inav-0.074
 exceptions-0.074
 sparing-0.072
Token Twitter
Token ID3009
Feature activation+1.13e-01

Pos logit contributions
 GOODMAN+0.085
 wip+0.082
inav+0.082
 exceptions+0.080
 sparing+0.079
Neg logit contributions
naire-0.135
-0.133
naissance-0.131
��-0.130
-0.125
Token,
Token ID11
Feature activation-3.95e-03

Pos logit contributions
 GOODMAN+0.088
 wip+0.086
inav+0.086
 exceptions+0.084
 sparing+0.083
Neg logit contributions
naire-0.092
-0.091
naissance-0.089
��-0.088
-0.085
Token Lawrence
Token ID13914
Feature activation+7.11e-02

Pos logit contributions
naire+0.004
+0.004
naissance+0.004
��+0.004
+0.003
Neg logit contributions
 GOODMAN-0.003
 wip-0.003
inav-0.003
 exceptions-0.002
 sparing-0.002
Token lashed
Token ID44416
Feature activation-2.03e-01

Pos logit contributions
 GOODMAN+0.065
 wip+0.063
 exceptions+0.062
inav+0.062
 sparing+0.062
Neg logit contributions
naire-0.049
-0.049
naissance-0.047
��-0.047
-0.044
Token out
Token ID503
Feature activation-1.04e-01

Pos logit contributions
naire+0.191
+0.189
naissance+0.186
��+0.184
+0.178
Neg logit contributions
 GOODMAN-0.134
 wip-0.129
inav-0.128
 exceptions-0.127
 sparing-0.124
Token at
Token ID379
Feature activation+1.19e-01

Pos logit contributions
naire+0.088
+0.087
naissance+0.085
��+0.085
+0.081
Neg logit contributions
 GOODMAN-0.079
 wip-0.076
inav-0.076
 exceptions-0.075
 sparing-0.074
Token the
Token ID262
Feature activation+8.68e-02

Pos logit contributions
 GOODMAN+0.073
 wip+0.070
inav+0.070
 exceptions+0.068
 sparing+0.067
Neg logit contributions
naire-0.118
-0.117
naissance-0.115
��-0.114
-0.110
Token sites
Token ID5043
Feature activation-6.69e-02

Pos logit contributions
 GOODMAN+0.065
inav+0.063
 wip+0.063
 exceptions+0.062
 sparing+0.061
Neg logit contributions
naire-0.073
-0.072
naissance-0.071
��-0.070
-0.067
Token that
Token ID326
Feature activation+6.61e-02

Pos logit contributions
naire+0.059
+0.058
naissance+0.057
��+0.056
+0.054
Neg logit contributions
 GOODMAN-0.049
 wip-0.047
inav-0.047
 exceptions-0.046
 sparing-0.045
Token permitted
Token ID10431
Feature activation-1.74e-01

Pos logit contributions
 GOODMAN+0.056
 wip+0.055
inav+0.054
 exceptions+0.054
 sparing+0.053
Neg logit contributions
naire-0.049
-0.049
naissance-0.048
��-0.047
-0.045
Token 2013
Token ID2211
Feature activation-1.18e-01

Pos logit contributions
 GOODMAN+0.177
 wip+0.172
inav+0.171
 exceptions+0.169
 sparing+0.166
Neg logit contributions
naire-0.170
-0.168
naissance-0.165
��-0.163
-0.155
Token
Token ID198
Feature activation-8.20e-02

Pos logit contributions
naire+0.096
+0.095
naissance+0.093
��+0.093
+0.088
Neg logit contributions
 GOODMAN-0.093
 wip-0.090
inav-0.089
 exceptions-0.089
 sparing-0.087
Token
Token ID198
Feature activation-7.86e-02

Pos logit contributions
naire+0.066
+0.064
naissance+0.063
��+0.062
+0.060
Neg logit contributions
 GOODMAN-0.065
 wip-0.063
inav-0.063
 exceptions-0.062
 sparing-0.061
TokenStarting
Token ID22851
Feature activation-4.02e-01

Pos logit contributions
naire+0.062
+0.061
naissance+0.059
��+0.059
+0.056
Neg logit contributions
 GOODMAN-0.064
inav-0.062
 wip-0.062
 exceptions-0.061
 sparing-0.060
Token in
Token ID287
Feature activation+5.00e-02

Pos logit contributions
naire+0.333
+0.328
naissance+0.322
��+0.319
+0.305
Neg logit contributions
 GOODMAN-0.309
 wip-0.299
inav-0.299
 exceptions-0.294
 sparing-0.289
Token 2013
Token ID2211
Feature activation-8.71e-02

Pos logit contributions
 GOODMAN+0.040
 wip+0.039
inav+0.039
 exceptions+0.038
 sparing+0.037
Neg logit contributions
naire-0.040
-0.039
naissance-0.039
��-0.038
-0.037
Token,
Token ID11
Feature activation-1.59e-01

Pos logit contributions
naire+0.068
+0.067
naissance+0.066
��+0.065
+0.062
Neg logit contributions
 GOODMAN-0.071
 wip-0.069
inav-0.069
 exceptions-0.068
 sparing-0.067
Token some
Token ID617
Feature activation-5.30e-02

Pos logit contributions
naire+0.155
+0.153
naissance+0.151
��+0.149
+0.145
Neg logit contributions
 GOODMAN-0.099
inav-0.095
 wip-0.095
 exceptions-0.092
 sparing-0.091
Token EC
Token ID13182
Feature activation-1.64e-01

Pos logit contributions
naire+0.045
+0.044
naissance+0.044
��+0.043
+0.041
Neg logit contributions
 GOODMAN-0.040
 wip-0.039
inav-0.038
 exceptions-0.038
 sparing-0.037
Token2
Token ID17
Feature activation-5.84e-02

Pos logit contributions
naire+0.112
+0.111
naissance+0.107
��+0.106
+0.101
Neg logit contributions
 GOODMAN-0.149
inav-0.145
 wip-0.145
 exceptions-0.142
 sparing-0.141
Token instance
Token ID4554
Feature activation+6.15e-02

Pos logit contributions
naire+0.064
+0.064
naissance+0.063
��+0.062
+0.060
Neg logit contributions
 GOODMAN-0.029
 wip-0.028
inav-0.028
 exceptions-0.027
 sparing-0.026
Token with
Token ID351
Feature activation-7.42e-02

Pos logit contributions
 GOODMAN+0.025
inav+0.024
 wip+0.024
 exceptions+0.023
 sparing+0.023
Neg logit contributions
naire-0.034
-0.033
naissance-0.033
��-0.032
-0.031
Token Red
Token ID2297
Feature activation-1.44e-01

Pos logit contributions
naire+0.073
+0.072
naissance+0.071
��+0.071
+0.068
Neg logit contributions
 GOODMAN-0.045
inav-0.043
 wip-0.043
 exceptions-0.042
 sparing-0.041
Tokenfer
Token ID2232
Feature activation-1.83e-03

Pos logit contributions
naire+0.110
+0.109
naissance+0.106
��+0.105
+0.100
Neg logit contributions
 GOODMAN-0.121
inav-0.117
 wip-0.117
 exceptions-0.115
 sparing-0.114
Tokenne
Token ID710
Feature activation-1.16e-01

Pos logit contributions
naire+0.001
+0.001
naissance+0.001
��+0.001
+0.001
Neg logit contributions
 GOODMAN-0.001
 wip-0.001
inav-0.001
 exceptions-0.001
 sparing-0.001
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
naire+0.094
+0.093
naissance+0.091
��+0.090
+0.086
Neg logit contributions
 GOODMAN-0.091
 wip-0.088
inav-0.088
 exceptions-0.087
 sparing-0.085
Token who
Token ID508
Feature activation-8.72e-02

Pos logit contributions
naire+0.104
+0.103
naissance+0.101
��+0.100
+0.096
Neg logit contributions
 GOODMAN-0.082
 wip-0.080
inav-0.079
 exceptions-0.078
 sparing-0.077
Token reports
Token ID3136
Feature activation+1.59e-01

Pos logit contributions
naire+0.060
+0.059
naissance+0.057
��+0.057
+0.054
Neg logit contributions
 GOODMAN-0.080
 wip-0.078
inav-0.078
 exceptions-0.077
 sparing-0.076
Token seeing
Token ID4379
Feature activation+6.98e-02

Pos logit contributions
 GOODMAN+0.090
 wip+0.087
inav+0.086
 exceptions+0.085
 sparing+0.083
Neg logit contributions
naire-0.163
-0.162
naissance-0.159
��-0.158
-0.152
Token a
Token ID257
Feature activation-1.03e-01

Pos logit contributions
 GOODMAN+0.047
 wip+0.046
inav+0.046
 exceptions+0.045
 sparing+0.044
Neg logit contributions
naire-0.064
-0.064
naissance-0.062
��-0.062
-0.059
Token party
Token ID2151
Feature activation-6.48e-03

Pos logit contributions
naire+0.091
+0.090
naissance+0.089
��+0.088
+0.084
Neg logit contributions
 GOODMAN-0.073
 wip-0.071
inav-0.071
 exceptions-0.069
 sparing-0.068
Token of
Token ID286
Feature activation-1.73e-01

Pos logit contributions
naire+0.004
+0.004
naissance+0.004
��+0.004
+0.004
Neg logit contributions
 GOODMAN-0.006
 wip-0.006
inav-0.006
 exceptions-0.006
 sparing-0.006
Token
Token ID447
Feature activation-6.19e-02

Pos logit contributions
naire+0.101
+0.099
naissance+0.097
��+0.095
+0.090
Neg logit contributions
 GOODMAN-0.164
 wip-0.161
inav-0.160
 exceptions-0.159
 sparing-0.157
Token
Token ID247
Feature activation-1.08e-02

Pos logit contributions
naire+0.043
naissance+0.041
+0.041
��+0.040
 dominates+0.038
Neg logit contributions
 GOODMAN-0.056
 wip-0.055
inav-0.055
 exceptions-0.054
 sparing-0.053
Tokens
Token ID82
Feature activation+6.55e-02

Pos logit contributions
naire+0.012
+0.012
naissance+0.011
��+0.011
+0.011
Neg logit contributions
 GOODMAN-0.006
 wip-0.005
inav-0.005
 exceptions-0.005
 sparing-0.005
Token making
Token ID1642
Feature activation+1.62e-01

Pos logit contributions
 GOODMAN+0.048
 wip+0.047
 exceptions+0.046
inav+0.046
 sparing+0.046
Neg logit contributions
naire-0.056
-0.056
naissance-0.055
��-0.054
-0.052
Token in
Token ID287
Feature activation+1.12e-01

Pos logit contributions
 GOODMAN+0.108
 wip+0.104
inav+0.104
 exceptions+0.103
 sparing+0.101
Neg logit contributions
naire-0.151
-0.149
naissance-0.147
��-0.145
-0.140
Token Miami
Token ID8437
Feature activation-5.23e-01

Pos logit contributions
 GOODMAN+0.075
 wip+0.073
inav+0.073
 exceptions+0.071
 sparing+0.070
Neg logit contributions
naire-0.103
-0.102
naissance-0.100
��-0.099
-0.095
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
naire+0.429
+0.423
naissance+0.414
��+0.411
+0.393
Neg logit contributions
 GOODMAN-0.408
 wip-0.395
inav-0.395
 exceptions-0.389
 sparing-0.382
Token He
Token ID679
Feature activation-1.39e-01

Pos logit contributions
 GOODMAN+0.091
 wip+0.088
inav+0.087
 exceptions+0.086
 sparing+0.084
Neg logit contributions
naire-0.094
-0.093
naissance-0.092
��-0.091
-0.086
Token
Token ID447
Feature activation-4.93e-02

Pos logit contributions
naire+0.089
+0.088
naissance+0.086
��+0.085
+0.080
Neg logit contributions
 GOODMAN-0.132
 wip-0.129
inav-0.128
 exceptions-0.128
 sparing-0.126
Token
Token ID247
Feature activation+2.39e-03

Pos logit contributions
naire+0.033
+0.032
naissance+0.032
��+0.031
 dominates+0.029
Neg logit contributions
 GOODMAN-0.045
 wip-0.044
inav-0.044
 exceptions-0.044
 sparing-0.043
Tokens
Token ID82
Feature activation+7.62e-02

Pos logit contributions
 GOODMAN+0.001
 wip+0.001
inav+0.001
 exceptions+0.001
 sparing+0.001
Neg logit contributions
naire-0.003
-0.003
naissance-0.002
��-0.002
-0.002
Token manager
Token ID4706
Feature activation-2.51e-01

Pos logit contributions
 GOODMAN+0.088
 wip+0.086
inav+0.085
 exceptions+0.084
 sparing+0.083
Neg logit contributions
naire-0.109
-0.108
naissance-0.106
��-0.105
-0.101
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
naire+0.203
+0.200
naissance+0.196
��+0.195
+0.186
Neg logit contributions
 GOODMAN-0.198
 wip-0.193
inav-0.192
 exceptions-0.189
 sparing-0.187
Token He
Token ID679
Feature activation-4.20e-02

Pos logit contributions
 GOODMAN+0.089
 wip+0.086
inav+0.086
 exceptions+0.085
 sparing+0.083
Neg logit contributions
naire-0.091
-0.090
naissance-0.088
��-0.087
-0.083
Token had
Token ID550
Feature activation-1.07e-01

Pos logit contributions
naire+0.027
+0.027
naissance+0.026
��+0.026
+0.025
Neg logit contributions
 GOODMAN-0.040
 wip-0.039
inav-0.039
 exceptions-0.038
 sparing-0.038
Token an
Token ID281
Feature activation-4.28e-02

Pos logit contributions
naire+0.081
+0.080
naissance+0.078
��+0.077
+0.073
Neg logit contributions
 GOODMAN-0.090
 wip-0.089
inav-0.088
 exceptions-0.087
 sparing-0.086
Token aura
Token ID22491
Feature activation-5.62e-01

Pos logit contributions
naire+0.040
+0.040
naissance+0.039
��+0.039
+0.037
Neg logit contributions
 GOODMAN-0.028
 wip-0.027
inav-0.027
 exceptions-0.027
 sparing-0.026
Token,
Token ID11
Feature activation-1.11e-01

Pos logit contributions
naire+0.383
+0.377
naissance+0.368
��+0.365
+0.345
Neg logit contributions
 GOODMAN-0.515
 wip-0.503
inav-0.500
 exceptions-0.496
 sparing-0.489
Token as
Token ID355
Feature activation+8.54e-02

Pos logit contributions
naire+0.107
+0.106
naissance+0.104
��+0.104
+0.100
Neg logit contributions
 GOODMAN-0.070
 wip-0.068
inav-0.067
 exceptions-0.067
 sparing-0.065
Token did
Token ID750
Feature activation-4.74e-02

Pos logit contributions
 GOODMAN+0.055
 wip+0.053
inav+0.053
 exceptions+0.052
 sparing+0.051
Neg logit contributions
naire-0.082
-0.080
naissance-0.079
��-0.078
-0.076
Token his
Token ID465
Feature activation-4.21e-03

Pos logit contributions
naire+0.045
+0.045
naissance+0.044
��+0.043
+0.042
Neg logit contributions
 GOODMAN-0.031
inav-0.030
 wip-0.030
 exceptions-0.029
 sparing-0.028
Token assistant
Token ID8796
Feature activation-1.14e-01

Pos logit contributions
naire+0.003
+0.003
naissance+0.003
��+0.003
+0.003
Neg logit contributions
 GOODMAN-0.003
inav-0.003
 wip-0.003
 exceptions-0.003
 sparing-0.003
Token
Token ID198
Feature activation-6.31e-03

Pos logit contributions
 GOODMAN+0.010
 wip+0.009
inav+0.009
 exceptions+0.009
 sparing+0.009
Neg logit contributions
naire-0.010
-0.010
naissance-0.010
��-0.010
-0.009
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
naire+0.005
+0.005
naissance+0.005
��+0.005
+0.005
Neg logit contributions
 GOODMAN-0.005
 wip-0.005
inav-0.005
 exceptions-0.005
 sparing-0.005
TokenYour
Token ID7120
Feature activation+2.00e-01

Pos logit contributions
naire+0.013
+0.013
naissance+0.012
��+0.012
+0.012
Neg logit contributions
 GOODMAN-0.012
inav-0.012
 wip-0.012
 exceptions-0.012
 sparing-0.011
Token Inner
Token ID24877
Feature activation-1.74e-01

Pos logit contributions
 GOODMAN+0.156
 wip+0.152
 exceptions+0.151
inav+0.151
 sparing+0.148
Neg logit contributions
naire-0.163
-0.160
naissance-0.158
��-0.156
-0.149
Token Ass
Token ID2195
Feature activation-2.33e-02

Pos logit contributions
naire+0.125
+0.122
naissance+0.119
��+0.118
+0.112
Neg logit contributions
 GOODMAN-0.154
inav-0.149
 wip-0.149
 exceptions-0.148
 sparing-0.145
Tokenhole
Token ID13207
Feature activation-5.60e-01

Pos logit contributions
naire+0.008
+0.008
naissance+0.008
��+0.007
+0.007
Neg logit contributions
 GOODMAN-0.029
inav-0.028
 wip-0.028
 exceptions-0.028
 sparing-0.028
Token is
Token ID318
Feature activation-1.53e-01

Pos logit contributions
naire+0.408
+0.403
naissance+0.396
��+0.391
+0.372
Neg logit contributions
 GOODMAN-0.485
 wip-0.475
inav-0.471
 exceptions-0.469
 sparing-0.463
Token never
Token ID1239
Feature activation-1.30e-01

Pos logit contributions
naire+0.142
+0.140
naissance+0.138
��+0.136
+0.131
Neg logit contributions
 GOODMAN-0.103
 wip-0.100
inav-0.099
 exceptions-0.098
 sparing-0.097
Token off
Token ID572
Feature activation+2.86e-01

Pos logit contributions
naire+0.127
+0.125
naissance+0.123
��+0.122
+0.117
Neg logit contributions
 GOODMAN-0.081
 wip-0.079
inav-0.078
 exceptions-0.077
 sparing-0.076
Token the
Token ID262
Feature activation+3.95e-02

Pos logit contributions
 GOODMAN+0.188
 wip+0.180
inav+0.180
 exceptions+0.178
 sparing+0.174
Neg logit contributions
naire-0.270
-0.266
naissance-0.263
��-0.261
-0.250
Token alert
Token ID7995
Feature activation+3.14e-02

Pos logit contributions
 GOODMAN+0.027
 wip+0.026
inav+0.026
 exceptions+0.026
 sparing+0.025
Neg logit contributions
naire-0.036
-0.036
naissance-0.035
��-0.035
-0.034
Token retailer
Token ID21538
Feature activation-4.36e-02

Pos logit contributions
naire+0.172
+0.171
naissance+0.168
��+0.167
+0.159
Neg logit contributions
 GOODMAN-0.143
 wip-0.138
inav-0.138
 exceptions-0.136
 sparing-0.134
Token?
Token ID30
Feature activation+8.07e-03

Pos logit contributions
naire+0.038
+0.037
naissance+0.036
��+0.036
+0.035
Neg logit contributions
 GOODMAN-0.032
 wip-0.031
inav-0.031
 exceptions-0.030
 sparing-0.030
Token
Token ID198
Feature activation-9.68e-03

Pos logit contributions
 GOODMAN+0.006
 wip+0.006
inav+0.006
 exceptions+0.006
 sparing+0.006
Neg logit contributions
naire-0.007
-0.007
naissance-0.006
��-0.006
-0.006
Token
Token ID198
Feature activation-2.75e-02

Pos logit contributions
naire+0.008
+0.008
naissance+0.007
��+0.007
+0.007
Neg logit contributions
 GOODMAN-0.008
 wip-0.008
inav-0.007
 exceptions-0.007
 sparing-0.007
TokenFred
Token ID30847
Feature activation-2.36e-01

Pos logit contributions
naire+0.021
+0.021
naissance+0.021
��+0.021
+0.020
Neg logit contributions
 GOODMAN-0.023
inav-0.022
 wip-0.022
 exceptions-0.021
 sparing-0.021
Token Pierce
Token ID23023
Feature activation-8.73e-01

Pos logit contributions
naire+0.179
+0.176
naissance+0.173
��+0.171
+0.163
Neg logit contributions
 GOODMAN-0.198
inav-0.191
 wip-0.191
 exceptions-0.189
 sparing-0.185
Token:
Token ID25
Feature activation-4.69e-02

Pos logit contributions
naire+0.703
+0.692
naissance+0.679
��+0.673
+0.642
Neg logit contributions
 GOODMAN-0.694
 wip-0.672
inav-0.671
 exceptions-0.661
 sparing-0.650
Token I
Token ID314
Feature activation-1.35e-01

Pos logit contributions
naire+0.040
+0.040
naissance+0.039
��+0.039
+0.037
Neg logit contributions
 GOODMAN-0.035
 wip-0.033
inav-0.033
 exceptions-0.033
 sparing-0.032
Token'll
Token ID1183
Feature activation+7.97e-02

Pos logit contributions
naire+0.136
+0.134
naissance+0.132
��+0.132
+0.126
Neg logit contributions
 GOODMAN-0.080
 wip-0.077
inav-0.077
 exceptions-0.075
 sparing-0.073
Token tell
Token ID1560
Feature activation-2.76e-02

Pos logit contributions
 GOODMAN+0.055
 wip+0.053
inav+0.053
 exceptions+0.052
 sparing+0.051
Neg logit contributions
naire-0.073
-0.072
naissance-0.071
��-0.070
-0.067
Token what
Token ID644
Feature activation-4.18e-02

Pos logit contributions
naire+0.028
+0.027
naissance+0.027
��+0.027
+0.026
Neg logit contributions
 GOODMAN-0.016
 wip-0.016
inav-0.016
 exceptions-0.015
 sparing-0.015
Token {
Token ID1391
Feature activation-2.40e-01

Pos logit contributions
naire+0.107
+0.105
naissance+0.104
��+0.103
+0.098
Neg logit contributions
 GOODMAN-0.097
 wip-0.094
inav-0.093
 exceptions-0.093
 sparing-0.091
Token(
Token ID7
Feature activation-4.64e-01

Pos logit contributions
naire+0.129
+0.126
naissance+0.123
��+0.121
+0.112
Neg logit contributions
 GOODMAN-0.255
 wip-0.249
inav-0.249
 exceptions-0.246
 sparing-0.243
Token6
Token ID21
Feature activation-1.01e-01

Pos logit contributions
naire+0.349
+0.343
naissance+0.336
��+0.333
+0.317
Neg logit contributions
 GOODMAN-0.393
 wip-0.381
inav-0.381
 exceptions-0.375
 sparing-0.369
Tokens
Token ID82
Feature activation-9.15e-03

Pos logit contributions
naire+0.075
+0.074
naissance+0.073
��+0.072
+0.068
Neg logit contributions
 GOODMAN-0.085
 wip-0.083
inav-0.083
 exceptions-0.082
 sparing-0.080
Token)}
Token ID38165
Feature activation-7.52e-02

Pos logit contributions
naire+0.009
+0.009
naissance+0.009
��+0.009
+0.009
Neg logit contributions
 GOODMAN-0.005
inav-0.005
 wip-0.005
 exceptions-0.005
 sparing-0.005
Token Ng
Token ID34786
Feature activation-5.25e-01

Pos logit contributions
naire+0.056
+0.055
naissance+0.054
��+0.053
+0.050
Neg logit contributions
 GOODMAN-0.064
 wip-0.063
inav-0.062
 exceptions-0.062
 sparing-0.061
Token6
Token ID21
Feature activation-7.92e-02

Pos logit contributions
naire+0.395
+0.388
naissance+0.381
��+0.377
+0.358
Neg logit contributions
 GOODMAN-0.443
inav-0.432
 wip-0.431
 exceptions-0.425
 sparing-0.419
Token {
Token ID1391
Feature activation-2.25e-01

Pos logit contributions
naire+0.066
+0.065
naissance+0.065
��+0.064
+0.061
Neg logit contributions
 GOODMAN-0.060
 wip-0.058
inav-0.058
 exceptions-0.057
 sparing-0.056
Token(
Token ID7
Feature activation-4.46e-01

Pos logit contributions
naire+0.120
+0.118
naissance+0.115
��+0.113
+0.105
Neg logit contributions
 GOODMAN-0.239
 wip-0.233
inav-0.233
 exceptions-0.231
 sparing-0.228
Token7
Token ID22
Feature activation+1.98e-03

Pos logit contributions
naire+0.334
+0.329
naissance+0.322
��+0.319
+0.303
Neg logit contributions
 GOODMAN-0.379
 wip-0.368
inav-0.368
 exceptions-0.363
 sparing-0.357
Tokens
Token ID82
Feature activation+9.16e-03

Pos logit contributions
 GOODMAN+0.002
 wip+0.002
inav+0.002
 exceptions+0.002
 sparing+0.002
Neg logit contributions
naire-0.001
-0.001
naissance-0.001
��-0.001
-0.001