TOP ACTIVATIONS
MAX = 1.088

The T iki Tw irl thrill ride at California 's
More Advanced Ruby Method Arg uments H ashes And Block
and Gen ç ler b irl i ğ i .
generic equivalents at treating hyp othy roid ism .
icide pre vention / doc uments / older adult / plan
War call er vs Sem blance An vil V
secretary Fer id un Sin irl i oglu , the official
acknowledged . Mon uments raised in recent years better
ton , Sam P anche vre ( Sam s
headed chance and forcing Gu iller mo O cho a into
s o eu vre , Manhattan d ut ifully
expansion of an o eu vre that mixes discomfort and que
breakers and a nuclear fre ighter , has increased Arctic navigation
s o eu vre . It feels nothing like
Col onel David L apan , a Pentagon spokesman ,
re ) led by Aless andro Pav olini and the Dec
kind of f iller between moves ,
he makes , Mid n ighter 's going to know it
: What made Mid n ighter initially come to mind ?
run - off between Gu iller mo L asso and Lenin

MIN ACTIVATIONS
MIN = -1.009

BS , Food Network , HG TV , Cartoon Network ,
Ramadan argues that Muhammad dev iated from his earlier , more
said . Sm oke Music manager Mark de Jong
Pride he sought to st oke through Pad m av ati
, they in ­ v oke him . I
be b esp oke rather like
a team in - j oke from down the years ?
or may perhaps be allev iated or designed out of the
subway station in Et obic oke . Police have
identified as Joshua E ern isse and Beau Sch oen hard
( 1979 ) Grade : A +
Ver h ä lt n isse " because of refugees or
( 1978 ) Grade : A In
Ken ichi Shin oda , the boss of Japan
Rd . in Et obic oke s Mark land
rid of its Communist y oke . For conservatives , libertarians
Ver h ä lt n isse " is just another way
a crust y old bl oke on a stool , ask
areas might be off - limits . La ure
. im aging . image format ] :: B mp );

INTERVAL 0.564 - 1.088
CONTAINS 0.155%

That never changes for me anyway . I d
1992 Jerry Se infeld 1993 Ted D anson
said Owen Do herty , climate model er and
, Gand hin agar , Gujarat 38 2020 , India
) - Latin American and Caribbean leaders converge on Cuba this

INTERVAL 0.039 - 0.564
CONTAINS 28.819%

Dev ial ets st up end ous imaging ,
9 2007 6 0 2008 15 4 2009 10 2 2010
we 've all agreed that maybe that episode was a little
if it 's answered Golden State War riors (@ war
. Sun an Abu Daw ud 14 : 26 65

INTERVAL -0.485 - 0.039
CONTAINS 70.723%

Last year at this time , the folks from Boise
over step the bounds in peaceful protests ? WASHINGTON
rea bought cocaine from Gal ar za 's co - worker
. However he has no links with Pakistan and worked in
" Some may qu ibble that this doesn 't take

INTERVAL -1.009 - -0.485
CONTAINS 0.303%

lez al slide on the Cait lyn Jenner comparisons and
of animal care . Experimental procedures were performed in accordance with
is composed of the Un locked BIOS , Digital P WM
, drew just eight b idd ers when auction ed by
ced : S chie ff elin , B .
Token
Token ID198
Feature activation+5.24e-02

Pos logit contributions
blance+0.022
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.016
 Debor-0.015
BUR-0.015
osit-0.014
 supervision-0.014
TokenThe
Token ID464
Feature activation+7.87e-02

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.014
osit-0.014
 supervision-0.013
Token T
Token ID309
Feature activation+3.22e-01

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.024
 Debor-0.022
BUR-0.022
osit-0.021
 supervision-0.021
Tokeniki
Token ID5580
Feature activation-2.00e-01

Pos logit contributions
blance+0.122
uments+0.115
arthed+0.113
ondon+0.108
nesota+0.102
Neg logit contributions
ogens-0.097
 Debor-0.091
BUR-0.088
osit-0.086
 supervision-0.084
Token Tw
Token ID1815
Feature activation+3.27e-01

Pos logit contributions
ogens+0.063
 Debor+0.059
BUR+0.057
osit+0.056
 supervision+0.055
Neg logit contributions
blance-0.074
uments-0.069
arthed-0.068
ondon-0.065
nesota-0.062
Tokenirl
Token ID1901
Feature activation+1.09e+00

Pos logit contributions
blance+0.102
arthed+0.094
uments+0.094
ondon+0.087
nesota+0.082
Neg logit contributions
ogens-0.122
 Debor-0.113
BUR-0.111
osit-0.111
iated-0.108
Token thrill
Token ID28576
Feature activation+2.06e-01

Pos logit contributions
blance+0.417
uments+0.392
arthed+0.388
ondon+0.370
nesota+0.352
Neg logit contributions
ogens-0.326
 Debor-0.302
BUR-0.294
osit-0.286
 supervision-0.281
Token ride
Token ID6594
Feature activation+2.22e-02

Pos logit contributions
blance+0.087
uments+0.083
arthed+0.082
ondon+0.078
nesota+0.075
Neg logit contributions
ogens-0.053
 Debor-0.049
BUR-0.048
osit-0.046
 supervision-0.045
Token at
Token ID379
Feature activation+3.55e-02

Pos logit contributions
blance+0.009
uments+0.008
arthed+0.008
ondon+0.008
nesota+0.007
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token California
Token ID3442
Feature activation+1.80e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.011
nesota+0.011
Neg logit contributions
ogens-0.011
 Debor-0.011
BUR-0.010
osit-0.010
 supervision-0.010
Token's
Token ID338
Feature activation-5.48e-03

Pos logit contributions
blance+0.061
uments+0.057
arthed+0.056
ondon+0.053
nesota+0.050
Neg logit contributions
ogens-0.062
 Debor-0.059
BUR-0.057
osit-0.056
 supervision-0.055
Token More
Token ID3125
Feature activation+8.07e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token Advanced
Token ID13435
Feature activation+4.43e-01

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.025
 Debor-0.024
BUR-0.023
osit-0.022
 supervision-0.022
Token Ruby
Token ID10888
Feature activation+9.68e-02

Pos logit contributions
blance+0.159
uments+0.149
arthed+0.148
ondon+0.140
nesota+0.133
Neg logit contributions
ogens-0.143
 Debor-0.134
BUR-0.131
osit-0.127
 supervision-0.125
Token Method
Token ID11789
Feature activation+2.27e-01

Pos logit contributions
blance+0.036
uments+0.033
arthed+0.033
ondon+0.031
nesota+0.030
Neg logit contributions
ogens-0.031
 Debor-0.029
BUR-0.028
osit-0.027
 supervision-0.027
Token Arg
Token ID20559
Feature activation+1.08e-01

Pos logit contributions
blance+0.077
uments+0.071
arthed+0.071
ondon+0.067
nesota+0.063
Neg logit contributions
ogens-0.078
 Debor-0.073
BUR-0.071
osit-0.070
 supervision-0.068
Tokenuments
Token ID2886
Feature activation+1.08e+00

Pos logit contributions
blance+0.005
arthed+0.002
uments+0.000
ondon-0.000
nesota-0.002
Neg logit contributions
ogens-0.070
 Debor-0.067
BUR-0.066
osit-0.066
 supervision-0.065
Token
Token ID784
Feature activation+6.59e-02

Pos logit contributions
blance+0.414
uments+0.388
arthed+0.386
ondon+0.367
nesota+0.350
Neg logit contributions
ogens-0.325
 Debor-0.303
BUR-0.293
osit-0.285
 supervision-0.280
Token H
Token ID367
Feature activation-2.21e-01

Pos logit contributions
blance+0.024
uments+0.023
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.021
 Debor-0.020
BUR-0.019
osit-0.018
 supervision-0.018
Tokenashes
Token ID7465
Feature activation+2.36e-01

Pos logit contributions
ogens+0.073
 Debor+0.068
BUR+0.066
osit+0.065
 supervision+0.064
Neg logit contributions
blance-0.078
uments-0.073
arthed-0.072
ondon-0.068
nesota-0.065
Token And
Token ID843
Feature activation+1.03e-01

Pos logit contributions
blance+0.091
uments+0.086
arthed+0.085
ondon+0.081
nesota+0.078
Neg logit contributions
ogens-0.070
 Debor-0.065
BUR-0.063
osit-0.061
 supervision-0.060
Token Block
Token ID9726
Feature activation+1.40e-01

Pos logit contributions
blance+0.037
uments+0.035
arthed+0.035
ondon+0.033
nesota+0.031
Neg logit contributions
ogens-0.033
 Debor-0.031
BUR-0.030
osit-0.030
 supervision-0.029
Token and
Token ID290
Feature activation+4.50e-02

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.000
nesota+0.000
Neg logit contributions
ogens-0.000
 Debor-0.000
BUR-0.000
osit-0.000
 supervision-0.000
Token Gen
Token ID5215
Feature activation-5.49e-02

Pos logit contributions
blance+0.017
uments+0.016
arthed+0.016
ondon+0.015
nesota+0.014
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.012
 supervision-0.012
Tokenç
Token ID16175
Feature activation+3.24e-02

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.019
osit+0.018
 supervision+0.018
Neg logit contributions
blance-0.017
uments-0.016
arthed-0.016
ondon-0.015
nesota-0.014
Tokenler
Token ID1754
Feature activation+2.65e-01

Pos logit contributions
blance+0.012
uments+0.011
arthed+0.011
ondon+0.010
nesota+0.010
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.009
 supervision-0.009
Tokenb
Token ID65
Feature activation+1.82e-01

Pos logit contributions
blance+0.098
uments+0.092
arthed+0.091
ondon+0.087
nesota+0.083
Neg logit contributions
ogens-0.083
 Debor-0.077
BUR-0.075
osit-0.073
 supervision-0.071
Tokenirl
Token ID1901
Feature activation+1.08e+00

Pos logit contributions
blance+0.066
uments+0.062
arthed+0.062
ondon+0.058
nesota+0.056
Neg logit contributions
ogens-0.058
 Debor-0.053
BUR-0.052
osit-0.051
 supervision-0.050
Tokeni
Token ID72
Feature activation+2.70e-01

Pos logit contributions
blance+0.478
uments+0.452
arthed+0.447
ondon+0.435
aiden+0.413
Neg logit contributions
ogens-0.254
 Debor-0.238
BUR-0.227
osit-0.214
 supervision-0.212
Tokenğ
Token ID33133
Feature activation+9.48e-02

Pos logit contributions
blance+0.102
uments+0.096
arthed+0.095
ondon+0.091
nesota+0.086
Neg logit contributions
ogens-0.082
 Debor-0.076
BUR-0.074
osit-0.072
 supervision-0.070
Tokeni
Token ID72
Feature activation+2.36e-01

Pos logit contributions
blance+0.035
uments+0.033
arthed+0.032
ondon+0.031
nesota+0.029
Neg logit contributions
ogens-0.030
 Debor-0.028
BUR-0.027
osit-0.027
 supervision-0.026
Token.
Token ID13
Feature activation+2.22e-02

Pos logit contributions
blance+0.090
uments+0.084
arthed+0.083
ondon+0.079
nesota+0.075
Neg logit contributions
ogens-0.071
 Debor-0.067
BUR-0.065
osit-0.063
 supervision-0.062
Token
Token ID447
Feature activation+4.80e-03

Pos logit contributions
blance+0.009
uments+0.008
arthed+0.008
ondon+0.008
nesota+0.007
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token generic
Token ID14276
Feature activation+6.86e-02

Pos logit contributions
blance+0.052
uments+0.049
arthed+0.049
ondon+0.047
nesota+0.045
Neg logit contributions
ogens-0.037
 Debor-0.035
BUR-0.033
osit-0.033
 supervision-0.032
Token equivalents
Token ID40255
Feature activation+9.66e-02

Pos logit contributions
blance+0.027
uments+0.026
arthed+0.025
ondon+0.024
nesota+0.023
Neg logit contributions
ogens-0.020
 Debor-0.018
BUR-0.018
osit-0.017
 supervision-0.017
Token at
Token ID379
Feature activation+2.22e-02

Pos logit contributions
blance+0.037
uments+0.034
arthed+0.034
ondon+0.032
nesota+0.031
Neg logit contributions
ogens-0.029
 Debor-0.027
BUR-0.027
osit-0.026
 supervision-0.025
Token treating
Token ID13622
Feature activation+5.22e-02

Pos logit contributions
blance+0.009
uments+0.008
arthed+0.008
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.005
 supervision-0.005
Token hyp
Token ID5328
Feature activation+3.58e-01

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.014
osit-0.013
 supervision-0.013
Tokenothy
Token ID14863
Feature activation+1.06e+00

Pos logit contributions
blance+0.089
uments+0.081
arthed+0.080
ondon+0.074
nesota+0.068
Neg logit contributions
ogens-0.156
 Debor-0.146
BUR-0.144
osit-0.143
iated-0.140
Tokenroid
Token ID3882
Feature activation+3.39e-01

Pos logit contributions
blance+0.263
uments+0.241
arthed+0.236
ondon+0.218
aiden+0.200
Neg logit contributions
ogens-0.457
 Debor-0.441
BUR-0.430
 supervision-0.417
osit-0.417
Tokenism
Token ID1042
Feature activation-3.22e-01

Pos logit contributions
blance+0.174
uments+0.167
arthed+0.164
ondon+0.159
nesota+0.154
Neg logit contributions
ogens-0.056
 Debor-0.050
BUR-0.047
osit-0.044
 supervision-0.042
Token.
Token ID13
Feature activation+1.59e-02

Pos logit contributions
ogens+0.098
 Debor+0.091
BUR+0.088
osit+0.086
 supervision+0.084
Neg logit contributions
blance-0.122
uments-0.115
arthed-0.114
ondon-0.108
nesota-0.103
Token
Token ID198
Feature activation-5.56e-03

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.004
osit-0.004
 supervision-0.004
Token
Token ID198
Feature activation+1.22e-02

Pos logit contributions
ogens+0.002
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Tokenicide
Token ID5285
Feature activation+4.05e-01

Pos logit contributions
blance+0.064
uments+0.058
arthed+0.057
ondon+0.053
nesota+0.048
Neg logit contributions
ogens-0.110
 Debor-0.104
BUR-0.102
osit-0.101
 supervision-0.099
Tokenpre
Token ID3866
Feature activation-3.81e-02

Pos logit contributions
blance+0.152
uments+0.143
arthed+0.141
ondon+0.134
nesota+0.128
Neg logit contributions
ogens-0.124
 Debor-0.115
BUR-0.112
osit-0.110
 supervision-0.107
Tokenvention
Token ID4018
Feature activation-1.41e-01

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.011
 supervision+0.011
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Token/
Token ID14
Feature activation-4.10e-02

Pos logit contributions
ogens+0.044
 Debor+0.041
BUR+0.040
osit+0.039
 supervision+0.038
Neg logit contributions
blance-0.052
uments-0.049
arthed-0.049
ondon-0.046
nesota-0.044
Tokendoc
Token ID15390
Feature activation+3.39e-02

Pos logit contributions
ogens+0.014
 Debor+0.013
BUR+0.013
osit+0.012
 supervision+0.012
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Tokenuments
Token ID2886
Feature activation+1.06e+00

Pos logit contributions
blance+0.003
arthed+0.002
uments+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.021
 Debor-0.020
BUR-0.020
osit-0.020
iated-0.019
Token/
Token ID14
Feature activation-5.34e-02

Pos logit contributions
blance+0.405
uments+0.380
arthed+0.377
ondon+0.359
nesota+0.342
Neg logit contributions
ogens-0.319
 Debor-0.296
BUR-0.288
osit-0.280
 supervision-0.274
Tokenolder
Token ID19892
Feature activation+3.97e-01

Pos logit contributions
ogens+0.018
 Debor+0.016
BUR+0.016
osit+0.016
 supervision+0.015
Neg logit contributions
blance-0.019
uments-0.017
arthed-0.017
ondon-0.016
nesota-0.016
Tokenadult
Token ID49922
Feature activation+1.49e-01

Pos logit contributions
blance+0.147
uments+0.137
arthed+0.136
ondon+0.129
nesota+0.123
Neg logit contributions
ogens-0.125
 Debor-0.116
BUR-0.113
osit-0.110
 supervision-0.108
Token/
Token ID14
Feature activation-5.63e-02

Pos logit contributions
blance+0.050
uments+0.046
arthed+0.046
ondon+0.043
nesota+0.041
Neg logit contributions
ogens-0.052
 Debor-0.049
BUR-0.048
osit-0.047
 supervision-0.046
Tokenplan
Token ID11578
Feature activation+2.27e-01

Pos logit contributions
ogens+0.020
 Debor+0.018
BUR+0.018
osit+0.018
 supervision+0.017
Neg logit contributions
blance-0.019
uments-0.017
arthed-0.017
ondon-0.016
nesota-0.015
Token War
Token ID1810
Feature activation-2.07e-01

Pos logit contributions
blance+0.129
uments+0.121
arthed+0.120
ondon+0.114
nesota+0.108
Neg logit contributions
ogens-0.112
 Debor-0.105
BUR-0.102
osit-0.099
 supervision-0.098
Tokencall
Token ID13345
Feature activation+1.91e-01

Pos logit contributions
ogens+0.070
 Debor+0.065
BUR+0.064
osit+0.062
 supervision+0.061
Neg logit contributions
blance-0.072
uments-0.067
arthed-0.066
ondon-0.063
nesota-0.060
Tokener
Token ID263
Feature activation+8.97e-02

Pos logit contributions
blance+0.068
uments+0.063
arthed+0.062
ondon+0.059
nesota+0.058
Neg logit contributions
ogens-0.062
 Debor-0.058
BUR-0.057
osit-0.056
 supervision-0.055
Token vs
Token ID3691
Feature activation-1.77e-01

Pos logit contributions
blance+0.036
uments+0.034
arthed+0.034
ondon+0.032
nesota+0.031
Neg logit contributions
ogens-0.025
 Debor-0.023
BUR-0.022
osit-0.022
 supervision-0.021
Token Sem
Token ID12449
Feature activation-1.42e-01

Pos logit contributions
ogens+0.057
 Debor+0.053
BUR+0.052
osit+0.050
 supervision+0.049
Neg logit contributions
blance-0.064
uments-0.060
arthed-0.059
ondon-0.056
nesota-0.053
Tokenblance
Token ID42757
Feature activation+1.06e+00

Pos logit contributions
ogens+0.071
 Debor+0.067
BUR+0.066
osit+0.065
iated+0.065
Neg logit contributions
blance-0.025
uments-0.023
arthed-0.023
ondon-0.020
nesota-0.018
Token An
Token ID1052
Feature activation+2.11e-01

Pos logit contributions
blance+0.386
uments+0.363
arthed+0.359
ondon+0.342
nesota+0.324
Neg logit contributions
ogens-0.334
 Debor-0.312
BUR-0.303
osit-0.295
 supervision-0.289
Tokenvil
Token ID2991
Feature activation-5.61e-02

Pos logit contributions
blance+0.078
uments+0.073
arthed+0.072
ondon+0.069
nesota+0.065
Neg logit contributions
ogens-0.066
 Debor-0.062
BUR-0.060
osit-0.059
 supervision-0.058
Token
Token ID198
Feature activation-1.13e-03

Pos logit contributions
ogens+0.017
 Debor+0.016
BUR+0.015
osit+0.015
 supervision+0.015
Neg logit contributions
blance-0.021
uments-0.020
arthed-0.020
ondon-0.019
nesota-0.018
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
ogens+0.000
 Debor+0.000
BUR+0.000
osit+0.000
 supervision+0.000
Neg logit contributions
blance-0.000
uments-0.000
arthed-0.000
ondon-0.000
nesota-0.000
TokenV
Token ID53
Feature activation+2.42e-02

Pos logit contributions
blance+0.007
uments+0.007
arthed+0.007
ondon+0.006
nesota+0.006
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.005
Token secretary
Token ID7705
Feature activation-2.24e-01

Pos logit contributions
ogens+0.006
 Debor+0.006
BUR+0.005
osit+0.005
iated+0.005
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.007
aiden-0.006
Token Fer
Token ID12880
Feature activation-2.82e-01

Pos logit contributions
ogens+0.067
 Debor+0.062
BUR+0.061
osit+0.059
iated+0.057
Neg logit contributions
blance-0.086
uments-0.081
arthed-0.080
ondon-0.076
aiden-0.072
Tokenid
Token ID312
Feature activation-1.39e-01

Pos logit contributions
ogens+0.092
 Debor+0.086
BUR+0.084
osit+0.082
 supervision+0.080
Neg logit contributions
blance-0.101
uments-0.094
arthed-0.094
ondon-0.088
nesota-0.084
Tokenun
Token ID403
Feature activation-1.31e-01

Pos logit contributions
ogens+0.046
 Debor+0.043
BUR+0.042
osit+0.040
 supervision+0.040
Neg logit contributions
blance-0.049
uments-0.046
arthed-0.046
ondon-0.043
nesota-0.041
Token Sin
Token ID10884
Feature activation-1.15e-01

Pos logit contributions
ogens+0.042
 Debor+0.039
BUR+0.038
osit+0.037
 supervision+0.036
Neg logit contributions
blance-0.048
uments-0.045
arthed-0.044
ondon-0.042
nesota-0.040
Tokenirl
Token ID1901
Feature activation+1.04e+00

Pos logit contributions
ogens+0.054
 Debor+0.052
BUR+0.051
osit+0.050
 supervision+0.050
Neg logit contributions
blance-0.024
uments-0.022
arthed-0.021
ondon-0.019
nesota-0.017
Tokeni
Token ID72
Feature activation+2.21e-01

Pos logit contributions
blance+0.323
uments+0.300
arthed+0.296
ondon+0.280
nesota+0.261
Neg logit contributions
ogens-0.385
 Debor-0.364
BUR-0.356
osit-0.347
 supervision-0.342
Tokenoglu
Token ID49006
Feature activation-5.59e-02

Pos logit contributions
blance+0.086
uments+0.081
arthed+0.080
ondon+0.077
aiden+0.073
Neg logit contributions
ogens-0.064
 Debor-0.060
BUR-0.058
osit-0.056
iated-0.055
Token,
Token ID11
Feature activation-4.59e-02

Pos logit contributions
ogens+0.017
 Debor+0.016
BUR+0.015
osit+0.015
 supervision+0.014
Neg logit contributions
blance-0.021
uments-0.020
arthed-0.020
ondon-0.019
nesota-0.018
Token the
Token ID262
Feature activation-8.02e-03

Pos logit contributions
ogens+0.014
 Debor+0.013
BUR+0.013
osit+0.012
 supervision+0.012
Neg logit contributions
blance-0.017
uments-0.016
arthed-0.016
ondon-0.015
nesota-0.015
Token official
Token ID1743
Feature activation+1.11e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token acknowledged
Token ID10810
Feature activation-1.11e-01

Pos logit contributions
ogens+0.016
 Debor+0.015
BUR+0.014
osit+0.014
 supervision+0.014
Neg logit contributions
blance-0.018
uments-0.017
arthed-0.017
ondon-0.016
nesota-0.015
Token.
Token ID13
Feature activation-3.63e-02

Pos logit contributions
ogens+0.034
 Debor+0.032
BUR+0.031
osit+0.030
 supervision+0.030
Neg logit contributions
blance-0.041
uments-0.039
arthed-0.038
ondon-0.037
nesota-0.035
Token
Token ID198
Feature activation-4.11e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.010
 supervision+0.009
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Token
Token ID198
Feature activation-4.15e-02

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.010
 supervision+0.010
Neg logit contributions
blance-0.016
uments-0.015
arthed-0.015
ondon-0.014
nesota-0.014
TokenMon
Token ID9069
Feature activation+3.37e-02

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.010
 supervision+0.010
Neg logit contributions
blance-0.016
uments-0.016
arthed-0.015
ondon-0.015
nesota-0.014
Tokenuments
Token ID2886
Feature activation+1.02e+00

Pos logit contributions
blance+0.002
arthed+0.001
uments+0.001
ondon+0.000
nesota-0.000
Neg logit contributions
ogens-0.021
 Debor-0.021
BUR-0.020
osit-0.020
iated-0.020
Token raised
Token ID4376
Feature activation+7.60e-02

Pos logit contributions
blance+0.381
uments+0.359
arthed+0.354
ondon+0.338
nesota+0.320
Neg logit contributions
ogens-0.313
 Debor-0.292
BUR-0.284
osit-0.277
 supervision-0.270
Token in
Token ID287
Feature activation-2.79e-02

Pos logit contributions
blance+0.027
uments+0.025
arthed+0.025
ondon+0.024
nesota+0.023
Neg logit contributions
ogens-0.025
 Debor-0.023
BUR-0.023
osit-0.022
 supervision-0.022
Token recent
Token ID2274
Feature activation+1.66e-02

Pos logit contributions
ogens+0.008
 Debor+0.008
BUR+0.008
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.010
ondon-0.009
nesota-0.009
Token years
Token ID812
Feature activation-2.52e-02

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.005
 supervision-0.004
Token better
Token ID1365
Feature activation-2.37e-01

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.009
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.008
Tokenton
Token ID1122
Feature activation-4.06e-01

Pos logit contributions
ogens+0.048
 Debor+0.043
BUR+0.041
osit+0.039
 supervision+0.037
Neg logit contributions
blance-0.132
uments-0.126
arthed-0.125
ondon-0.120
nesota-0.116
Token,
Token ID11
Feature activation+8.19e-03

Pos logit contributions
ogens+0.121
 Debor+0.112
BUR+0.109
osit+0.106
 supervision+0.104
Neg logit contributions
blance-0.156
uments-0.147
arthed-0.146
ondon-0.139
nesota-0.132
Token Sam
Token ID3409
Feature activation+8.70e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token P
Token ID350
Feature activation+3.28e-02

Pos logit contributions
blance+0.033
uments+0.031
arthed+0.030
ondon+0.029
nesota+0.027
Neg logit contributions
ogens-0.027
 Debor-0.025
BUR-0.024
osit-0.024
 supervision-0.023
Tokenanche
Token ID6362
Feature activation+3.42e-01

Pos logit contributions
blance+0.011
uments+0.010
arthed+0.010
ondon+0.010
nesota+0.009
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.010
 supervision-0.010
Tokenvre
Token ID43933
Feature activation+9.69e-01

Pos logit contributions
blance+0.111
uments+0.104
arthed+0.103
ondon+0.097
nesota+0.091
Neg logit contributions
ogens-0.122
 Debor-0.114
BUR-0.112
osit-0.109
iated-0.107
Token (
Token ID357
Feature activation+4.34e-02

Pos logit contributions
blance+0.373
uments+0.351
arthed+0.348
ondon+0.332
nesota+0.315
Neg logit contributions
ogens-0.288
 Debor-0.267
BUR-0.260
osit-0.252
 supervision-0.247
TokenSam
Token ID16305
Feature activation+3.61e-01

Pos logit contributions
blance+0.016
uments+0.015
arthed+0.015
ondon+0.014
nesota+0.013
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.012
osit-0.012
 supervision-0.012
Token
Token ID447
Feature activation+2.00e-02

Pos logit contributions
blance+0.135
uments+0.127
arthed+0.126
ondon+0.119
nesota+0.114
Neg logit contributions
ogens-0.111
 Debor-0.103
BUR-0.101
osit-0.098
 supervision-0.096
Token
Token ID247
Feature activation+1.48e-02

Pos logit contributions
blance+0.007
uments+0.007
arthed+0.007
ondon+0.006
nesota+0.006
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Tokens
Token ID82
Feature activation+4.83e-02

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token headed
Token ID9153
Feature activation+5.16e-02

Pos logit contributions
blance+0.025
uments+0.024
arthed+0.024
ondon+0.023
nesota+0.021
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.017
osit-0.017
 supervision-0.017
Token chance
Token ID2863
Feature activation+4.66e-02

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.014
osit-0.013
 supervision-0.013
Token and
Token ID290
Feature activation+2.43e-02

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.015
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.012
 supervision-0.012
Token forcing
Token ID10833
Feature activation+6.97e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.007
 Debor-0.007
BUR-0.007
osit-0.006
 supervision-0.006
Token Gu
Token ID1962
Feature activation+1.66e-01

Pos logit contributions
blance+0.026
uments+0.024
arthed+0.024
ondon+0.023
nesota+0.022
Neg logit contributions
ogens-0.022
 Debor-0.020
BUR-0.020
osit-0.019
 supervision-0.019
Tokeniller
Token ID4665
Feature activation+9.56e-01

Pos logit contributions
blance+0.026
uments+0.022
arthed+0.022
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.087
 Debor-0.083
BUR-0.082
osit-0.081
iated-0.081
Tokenmo
Token ID5908
Feature activation+6.03e-01

Pos logit contributions
blance+0.233
uments+0.211
arthed+0.208
ondon+0.192
nesota+0.176
Neg logit contributions
ogens-0.419
 Debor-0.399
BUR-0.392
osit-0.384
 supervision-0.379
Token O
Token ID440
Feature activation+1.85e-01

Pos logit contributions
blance+0.217
uments+0.203
arthed+0.202
ondon+0.191
nesota+0.182
Neg logit contributions
ogens-0.194
 Debor-0.182
BUR-0.177
osit-0.173
 supervision-0.169
Tokencho
Token ID6679
Feature activation-1.24e-01

Pos logit contributions
blance+0.084
uments+0.080
arthed+0.079
ondon+0.076
nesota+0.073
Neg logit contributions
ogens-0.043
 Debor-0.039
BUR-0.037
osit-0.035
 supervision-0.035
Tokena
Token ID64
Feature activation+5.95e-02

Pos logit contributions
ogens+0.043
 Debor+0.040
BUR+0.039
osit+0.039
 supervision+0.038
Neg logit contributions
blance-0.041
uments-0.039
arthed-0.038
ondon-0.036
nesota-0.034
Token into
Token ID656
Feature activation-2.07e-02

Pos logit contributions
blance+0.022
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.017
osit-0.017
 supervision-0.016
Token
Token ID447
Feature activation+6.49e-03

Pos logit contributions
blance+0.043
uments+0.041
arthed+0.041
ondon+0.039
nesota+0.037
Neg logit contributions
ogens-0.025
 Debor-0.023
BUR-0.022
osit-0.021
 supervision-0.021
Token
Token ID247
Feature activation-1.70e-03

Pos logit contributions
blance+0.002
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Tokens
Token ID82
Feature activation+1.24e-02

Pos logit contributions
ogens+0.001
 Debor+0.000
BUR+0.000
osit+0.000
 supervision+0.000
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token o
Token ID267
Feature activation+4.20e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.004
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
Tokeneu
Token ID12496
Feature activation-8.38e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.013
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.013
 supervision-0.012
Tokenvre
Token ID43933
Feature activation+9.50e-01

Pos logit contributions
ogens+0.047
 Debor+0.045
BUR+0.044
osit+0.044
 supervision+0.043
Neg logit contributions
blance-0.010
uments-0.008
arthed-0.008
ondon-0.007
nesota-0.006
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
blance+0.358
uments+0.337
arthed+0.333
ondon+0.318
nesota+0.301
Neg logit contributions
ogens-0.290
 Debor-0.270
BUR-0.263
osit-0.255
 supervision-0.250
Token Manhattan
Token ID13458
Feature activation-3.69e-01

Pos logit contributions
blance+0.007
uments+0.006
arthed+0.006
ondon+0.006
nesota+0.006
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.004
 supervision-0.004
Token d
Token ID288
Feature activation+4.29e-02

Pos logit contributions
ogens+0.107
 Debor+0.099
BUR+0.096
osit+0.093
 supervision+0.091
Neg logit contributions
blance-0.145
uments-0.137
arthed-0.136
ondon-0.129
nesota-0.124
Tokenut
Token ID315
Feature activation-1.42e-01

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.014
 Debor-0.014
BUR-0.013
osit-0.013
iated-0.013
Tokenifully
Token ID17049
Feature activation+1.59e-01

Pos logit contributions
ogens+0.046
 Debor+0.043
BUR+0.042
osit+0.040
 supervision+0.040
Neg logit contributions
blance-0.051
uments-0.048
arthed-0.048
ondon-0.045
nesota-0.043
Token expansion
Token ID7118
Feature activation+3.38e-01

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
 supervision+0.007
Neg logit contributions
blance-0.011
uments-0.011
arthed-0.011
ondon-0.010
nesota-0.010
Token of
Token ID286
Feature activation+8.69e-03

Pos logit contributions
blance+0.125
uments+0.118
arthed+0.116
ondon+0.111
nesota+0.105
Neg logit contributions
ogens-0.105
 Debor-0.098
BUR-0.096
osit-0.092
 supervision-0.091
Token an
Token ID281
Feature activation-2.46e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.002
Token o
Token ID267
Feature activation+3.94e-02

Pos logit contributions
ogens+0.007
 Debor+0.007
BUR+0.007
osit+0.006
 supervision+0.006
Neg logit contributions
blance-0.009
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.008
Tokeneu
Token ID12496
Feature activation-8.60e-02

Pos logit contributions
blance+0.011
uments+0.010
arthed+0.010
ondon+0.009
nesota+0.009
Neg logit contributions
ogens-0.016
 Debor-0.015
BUR-0.015
osit-0.015
 supervision-0.014
Tokenvre
Token ID43933
Feature activation+9.49e-01

Pos logit contributions
ogens+0.046
 Debor+0.045
BUR+0.044
osit+0.044
 supervision+0.043
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.009
ondon-0.008
nesota-0.007
Token that
Token ID326
Feature activation-1.45e-02

Pos logit contributions
blance+0.370
uments+0.349
arthed+0.346
ondon+0.330
nesota+0.314
Neg logit contributions
ogens-0.277
 Debor-0.256
BUR-0.249
osit-0.242
 supervision-0.236
Token mixes
Token ID33237
Feature activation+3.70e-02

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token discomfort
Token ID23597
Feature activation-1.64e-01

Pos logit contributions
blance+0.014
uments+0.014
arthed+0.013
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.009
 supervision-0.009
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
ogens+0.052
 Debor+0.049
BUR+0.047
osit+0.046
 supervision+0.045
Neg logit contributions
blance-0.060
uments-0.056
arthed-0.055
ondon-0.053
nesota-0.050
Token que
Token ID8358
Feature activation-1.86e-03

Pos logit contributions
ogens+0.005
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.006
Tokenbreakers
Token ID49295
Feature activation-1.18e-02

Pos logit contributions
ogens+0.053
 Debor+0.048
BUR+0.047
osit+0.045
 supervision+0.044
Neg logit contributions
blance-0.083
uments-0.079
arthed-0.078
ondon-0.075
nesota-0.072
Token and
Token ID290
Feature activation+9.09e-03

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Token a
Token ID257
Feature activation+4.04e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
Token nuclear
Token ID4523
Feature activation+2.83e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.013
Neg logit contributions
ogens-0.012
 Debor-0.012
BUR-0.011
osit-0.011
 supervision-0.011
Token fre
Token ID2030
Feature activation+6.24e-02

Pos logit contributions
blance+0.011
uments+0.011
arthed+0.010
ondon+0.010
nesota+0.009
Neg logit contributions
ogens-0.008
 Debor-0.008
BUR-0.007
osit-0.007
 supervision-0.007
Tokenighter
Token ID4799
Feature activation+9.22e-01

Pos logit contributions
blance+0.008
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.004
Neg logit contributions
ogens-0.035
 Debor-0.033
BUR-0.033
osit-0.033
 supervision-0.032
Token,
Token ID11
Feature activation+2.49e-02

Pos logit contributions
blance+0.351
uments+0.330
arthed+0.327
ondon+0.311
nesota+0.296
Neg logit contributions
ogens-0.278
 Debor-0.259
BUR-0.252
osit-0.245
 supervision-0.240
Token has
Token ID468
Feature activation+6.42e-02

Pos logit contributions
blance+0.010
uments+0.009
arthed+0.009
ondon+0.009
nesota+0.008
Neg logit contributions
ogens-0.007
 Debor-0.007
BUR-0.007
osit-0.006
 supervision-0.006
Token increased
Token ID3220
Feature activation+2.09e-02

Pos logit contributions
blance+0.024
uments+0.022
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.020
 Debor-0.019
BUR-0.018
osit-0.018
 supervision-0.017
Token Arctic
Token ID15723
Feature activation+5.46e-01

Pos logit contributions
blance+0.008
uments+0.007
arthed+0.007
ondon+0.007
nesota+0.006
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token navigation
Token ID16408
Feature activation+6.89e-03

Pos logit contributions
blance+0.216
uments+0.204
arthed+0.202
ondon+0.193
nesota+0.184
Neg logit contributions
ogens-0.156
 Debor-0.145
BUR-0.140
osit-0.136
 supervision-0.133
Token
Token ID447
Feature activation-1.88e-03

Pos logit contributions
blance+0.004
uments+0.004
arthed+0.004
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.002
 supervision-0.002
Token
Token ID247
Feature activation-1.71e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
aiden-0.001
Tokens
Token ID82
Feature activation-4.74e-03

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.006
Token o
Token ID267
Feature activation+1.96e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Tokeneu
Token ID12496
Feature activation-1.06e-01

Pos logit contributions
blance+0.007
uments+0.006
arthed+0.006
ondon+0.006
nesota+0.006
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Tokenvre
Token ID43933
Feature activation+9.21e-01

Pos logit contributions
ogens+0.057
 Debor+0.055
BUR+0.055
osit+0.054
 supervision+0.054
Neg logit contributions
blance-0.014
uments-0.011
arthed-0.011
ondon-0.010
nesota-0.009
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
blance+0.351
uments+0.332
arthed+0.329
ondon+0.312
nesota+0.298
Neg logit contributions
ogens-0.276
 Debor-0.257
BUR-0.250
osit-0.243
 supervision-0.239
Token It
Token ID632
Feature activation-7.83e-02

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Token feels
Token ID5300
Feature activation+6.83e-02

Pos logit contributions
ogens+0.022
 Debor+0.021
BUR+0.020
osit+0.020
 supervision+0.019
Neg logit contributions
blance-0.031
uments-0.029
arthed-0.029
ondon-0.027
nesota-0.026
Token nothing
Token ID2147
Feature activation-2.50e-01

Pos logit contributions
blance+0.024
uments+0.023
arthed+0.023
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.022
 Debor-0.021
BUR-0.020
osit-0.020
 supervision-0.020
Token like
Token ID588
Feature activation+1.76e-02

Pos logit contributions
ogens+0.086
 Debor+0.081
BUR+0.079
osit+0.077
 supervision+0.076
Neg logit contributions
blance-0.084
uments-0.079
arthed-0.078
ondon-0.073
nesota-0.070
Token
Token ID198
Feature activation+1.56e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.004
nesota+0.004
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.003
osit-0.003
 supervision-0.003
TokenCol
Token ID5216
Feature activation-1.09e-01

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.005
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Tokenonel
Token ID26261
Feature activation+4.59e-02

Pos logit contributions
ogens+0.031
 Debor+0.029
BUR+0.028
osit+0.027
 supervision+0.027
Neg logit contributions
blance-0.043
uments-0.040
arthed-0.040
ondon-0.038
nesota-0.037
Token David
Token ID3271
Feature activation-1.60e-01

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.015
Neg logit contributions
ogens-0.013
 Debor-0.012
BUR-0.012
osit-0.012
 supervision-0.011
Token L
Token ID406
Feature activation-2.32e-01

Pos logit contributions
ogens+0.050
 Debor+0.047
BUR+0.046
osit+0.045
 supervision+0.043
Neg logit contributions
blance-0.059
uments-0.055
arthed-0.055
ondon-0.052
nesota-0.050
Tokenapan
Token ID2674
Feature activation+9.21e-01

Pos logit contributions
ogens+0.079
 Debor+0.073
BUR+0.071
osit+0.070
 supervision+0.069
Neg logit contributions
blance-0.080
uments-0.074
arthed-0.074
ondon-0.069
nesota-0.066
Token,
Token ID11
Feature activation+9.28e-03

Pos logit contributions
blance+0.350
uments+0.330
arthed+0.326
ondon+0.310
nesota+0.295
Neg logit contributions
ogens-0.277
 Debor-0.258
BUR-0.251
osit-0.244
 supervision-0.240
Token a
Token ID257
Feature activation+2.72e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.002
Token Pentagon
Token ID12651
Feature activation+2.72e-02

Pos logit contributions
blance+0.011
uments+0.010
arthed+0.010
ondon+0.010
nesota+0.009
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Token spokesman
Token ID6523
Feature activation-6.80e-02

Pos logit contributions
blance+0.012
uments+0.011
arthed+0.011
ondon+0.011
nesota+0.010
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token,
Token ID11
Feature activation+3.99e-02

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.019
osit+0.018
 supervision+0.018
Neg logit contributions
blance-0.026
uments-0.024
arthed-0.024
ondon-0.023
nesota-0.022
Tokenre
Token ID260
Feature activation-3.04e-02

Pos logit contributions
blance+0.043
uments+0.040
arthed+0.040
ondon+0.038
nesota+0.036
Neg logit contributions
ogens-0.037
 Debor-0.035
BUR-0.034
osit-0.033
 supervision-0.032
Token)
Token ID8
Feature activation-5.03e-03

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.010
ondon-0.010
nesota-0.009
Token led
Token ID2957
Feature activation+1.55e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token by
Token ID416
Feature activation+6.78e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.004
ondon+0.004
nesota+0.004
Neg logit contributions
ogens-0.006
 Debor-0.005
BUR-0.005
osit-0.005
 supervision-0.005
Token Aless
Token ID47319
Feature activation-4.74e-02

Pos logit contributions
blance+0.026
uments+0.024
arthed+0.024
ondon+0.023
nesota+0.022
Neg logit contributions
ogens-0.021
 Debor-0.019
BUR-0.019
osit-0.018
 supervision-0.018
Tokenandro
Token ID28092
Feature activation+9.12e-01

Pos logit contributions
ogens+0.022
 Debor+0.021
BUR+0.021
osit+0.021
 supervision+0.020
Neg logit contributions
blance-0.010
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.007
Token Pav
Token ID24081
Feature activation+1.31e-01

Pos logit contributions
blance+0.331
uments+0.311
arthed+0.308
ondon+0.293
nesota+0.277
Neg logit contributions
ogens-0.290
 Debor-0.271
BUR-0.264
osit-0.257
 supervision-0.252
Tokenolini
Token ID43232
Feature activation-1.94e-01

Pos logit contributions
blance+0.050
uments+0.047
arthed+0.047
ondon+0.045
nesota+0.042
Neg logit contributions
ogens-0.039
 Debor-0.037
BUR-0.036
osit-0.034
 supervision-0.034
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
ogens+0.058
 Debor+0.054
BUR+0.053
osit+0.051
 supervision+0.050
Neg logit contributions
blance-0.074
uments-0.070
arthed-0.069
ondon-0.066
nesota-0.063
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.004
Token Dec
Token ID4280
Feature activation-1.33e-01

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.006
arthed-0.006
ondon-0.005
nesota-0.005
Token kind
Token ID1611
Feature activation+9.87e-02

Pos logit contributions
ogens+0.004
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token of
Token ID286
Feature activation-1.75e-02

Pos logit contributions
blance+0.038
uments+0.036
arthed+0.036
ondon+0.034
nesota+0.032
Neg logit contributions
ogens-0.029
 Debor-0.027
BUR-0.026
osit-0.025
 supervision-0.025
Token
Token ID564
Feature activation-1.50e-02

Pos logit contributions
ogens+0.005
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.006
nesota-0.006
Token
Token ID250
Feature activation+2.34e-02

Pos logit contributions
ogens+0.006
 Debor+0.005
BUR+0.005
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Tokenf
Token ID69
Feature activation-2.39e-02

Pos logit contributions
blance+0.009
uments+0.008
arthed+0.008
ondon+0.008
nesota+0.007
Neg logit contributions
ogens-0.007
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.006
Tokeniller
Token ID4665
Feature activation+9.08e-01

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.008
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.006
Token
Token ID447
Feature activation-2.18e-02

Pos logit contributions
blance+0.355
uments+0.335
arthed+0.332
ondon+0.317
nesota+0.301
Neg logit contributions
ogens-0.264
 Debor-0.245
BUR-0.238
osit-0.231
 supervision-0.226
Token
Token ID251
Feature activation-3.34e-02

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.006
nesota-0.006
Token between
Token ID1022
Feature activation-2.73e-01

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Token moves
Token ID6100
Feature activation+7.53e-02

Pos logit contributions
ogens+0.081
 Debor+0.075
BUR+0.073
osit+0.071
 supervision+0.070
Neg logit contributions
blance-0.105
uments-0.099
arthed-0.098
ondon-0.094
nesota-0.089
Token,
Token ID11
Feature activation-1.09e-02

Pos logit contributions
blance+0.029
uments+0.027
arthed+0.027
ondon+0.025
nesota+0.024
Neg logit contributions
ogens-0.023
 Debor-0.021
BUR-0.021
osit-0.020
 supervision-0.020
Token he
Token ID339
Feature activation-3.30e-02

Pos logit contributions
ogens+0.002
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.003
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token makes
Token ID1838
Feature activation-1.91e-02

Pos logit contributions
ogens+0.009
 Debor+0.009
BUR+0.008
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.012
nesota-0.011
Token,
Token ID11
Feature activation+2.29e-02

Pos logit contributions
ogens+0.006
 Debor+0.005
BUR+0.005
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.006
Token Mid
Token ID7215
Feature activation-6.53e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.005
 supervision-0.005
Tokenn
Token ID77
Feature activation-3.45e-02

Pos logit contributions
ogens+0.018
 Debor+0.017
BUR+0.016
osit+0.016
iated+0.015
Neg logit contributions
blance-0.026
uments-0.025
arthed-0.025
ondon-0.023
nesota-0.023
Tokenighter
Token ID4799
Feature activation+9.03e-01

Pos logit contributions
ogens+0.019
 Debor+0.018
BUR+0.018
osit+0.018
iated+0.017
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.003
nesota-0.003
Token's
Token ID338
Feature activation-7.89e-03

Pos logit contributions
blance+0.354
uments+0.334
arthed+0.333
ondon+0.315
nesota+0.301
Neg logit contributions
ogens-0.261
 Debor-0.244
BUR-0.237
osit-0.229
 supervision-0.225
Token going
Token ID1016
Feature activation+2.01e-02

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
 supervision+0.002
osit+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token to
Token ID284
Feature activation-1.04e-02

Pos logit contributions
blance+0.007
uments+0.007
arthed+0.007
ondon+0.006
nesota+0.006
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token know
Token ID760
Feature activation-3.49e-03

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
arthed-0.004
uments-0.004
ondon-0.004
nesota-0.003
Token it
Token ID340
Feature activation+4.85e-03

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token:
Token ID25
Feature activation+3.46e-02

Pos logit contributions
blance+0.143
uments+0.135
arthed+0.133
ondon+0.127
aiden+0.119
Neg logit contributions
ogens-0.125
 Debor-0.118
BUR-0.114
osit-0.111
 supervision-0.109
Token What
Token ID1867
Feature activation+1.19e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.011
nesota+0.011
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.010
 supervision-0.009
Token made
Token ID925
Feature activation-9.54e-02

Pos logit contributions
blance+0.047
uments+0.044
arthed+0.043
ondon+0.041
nesota+0.039
Neg logit contributions
ogens-0.035
 Debor-0.032
BUR-0.031
osit-0.030
 supervision-0.030
Token Mid
Token ID7215
Feature activation-4.70e-02

Pos logit contributions
ogens+0.030
 Debor+0.029
BUR+0.028
osit+0.027
 supervision+0.027
Neg logit contributions
blance-0.035
uments-0.033
arthed-0.032
ondon-0.031
nesota-0.029
Tokenn
Token ID77
Feature activation-3.56e-02

Pos logit contributions
ogens+0.013
 Debor+0.012
BUR+0.012
osit+0.012
iated+0.011
Neg logit contributions
blance-0.019
uments-0.018
arthed-0.018
ondon-0.017
nesota-0.016
Tokenighter
Token ID4799
Feature activation+9.02e-01

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.019
osit+0.018
iated+0.018
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.003
nesota-0.002
Token initially
Token ID7317
Feature activation-1.58e-01

Pos logit contributions
blance+0.336
uments+0.316
arthed+0.315
ondon+0.298
nesota+0.284
Neg logit contributions
ogens-0.278
 Debor-0.259
BUR-0.252
osit-0.245
 supervision-0.242
Token come
Token ID1282
Feature activation+2.39e-01

Pos logit contributions
ogens+0.048
 Debor+0.044
BUR+0.043
osit+0.042
 supervision+0.042
Neg logit contributions
blance-0.060
uments-0.057
arthed-0.056
ondon-0.053
nesota-0.051
Token to
Token ID284
Feature activation+2.03e-02

Pos logit contributions
blance+0.090
uments+0.084
arthed+0.083
ondon+0.079
nesota+0.076
Neg logit contributions
ogens-0.073
 Debor-0.068
BUR-0.066
osit-0.065
iated-0.064
Token mind
Token ID2000
Feature activation+3.66e-01

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Token?
Token ID30
Feature activation-1.90e-02

Pos logit contributions
blance+0.139
uments+0.132
arthed+0.130
ondon+0.124
nesota+0.118
Neg logit contributions
ogens-0.110
 Debor-0.102
BUR-0.099
osit-0.097
 supervision-0.095
Token run
Token ID1057
Feature activation+1.88e-02

Pos logit contributions
ogens+0.021
 Debor+0.020
BUR+0.019
osit+0.018
 supervision+0.018
Neg logit contributions
blance-0.028
uments-0.026
arthed-0.026
ondon-0.025
nesota-0.023
Token-
Token ID12
Feature activation-2.57e-02

Pos logit contributions
blance+0.007
uments+0.006
arthed+0.006
ondon+0.006
nesota+0.005
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.005
Tokenoff
Token ID2364
Feature activation-1.26e-01

Pos logit contributions
ogens+0.006
 Debor+0.006
BUR+0.006
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.011
uments-0.011
arthed-0.010
ondon-0.010
nesota-0.010
Token between
Token ID1022
Feature activation-2.77e-01

Pos logit contributions
ogens+0.039
 Debor+0.036
BUR+0.035
osit+0.034
 supervision+0.034
Neg logit contributions
blance-0.048
uments-0.045
arthed-0.044
ondon-0.042
nesota-0.040
Token Gu
Token ID1962
Feature activation+1.17e-01

Pos logit contributions
ogens+0.085
 Debor+0.080
BUR+0.077
osit+0.075
 supervision+0.074
Neg logit contributions
blance-0.103
uments-0.097
arthed-0.096
ondon-0.092
nesota-0.087
Tokeniller
Token ID4665
Feature activation+9.00e-01

Pos logit contributions
blance+0.035
uments+0.032
arthed+0.032
ondon+0.029
nesota+0.029
Neg logit contributions
ogens-0.045
 Debor-0.042
BUR-0.041
osit-0.041
iated-0.040
Tokenmo
Token ID5908
Feature activation+5.46e-01

Pos logit contributions
blance+0.220
uments+0.200
arthed+0.197
ondon+0.181
nesota+0.167
Neg logit contributions
ogens-0.394
 Debor-0.374
BUR-0.368
osit-0.361
 supervision-0.356
Token L
Token ID406
Feature activation-2.54e-01

Pos logit contributions
blance+0.210
uments+0.198
arthed+0.196
ondon+0.186
nesota+0.179
Neg logit contributions
ogens-0.163
 Debor-0.151
BUR-0.146
osit-0.142
 supervision-0.139
Tokenasso
Token ID28372
Feature activation-3.69e-01

Pos logit contributions
ogens+0.070
 Debor+0.066
BUR+0.065
 supervision+0.061
osit+0.061
Neg logit contributions
blance-0.101
uments-0.097
arthed-0.095
ondon-0.092
aiden-0.087
Token and
Token ID290
Feature activation-2.83e-02

Pos logit contributions
ogens+0.102
 Debor+0.095
BUR+0.092
osit+0.089
 supervision+0.087
Neg logit contributions
blance-0.149
uments-0.141
arthed-0.140
ondon-0.133
nesota-0.127
Token Lenin
Token ID22899
Feature activation-1.96e-01

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.010
ondon-0.009
nesota-0.009
TokenBS
Token ID4462
Feature activation-1.19e-01

Pos logit contributions
blance+0.100
arthed+0.093
uments+0.093
ondon+0.089
nesota+0.086
Neg logit contributions
ogens-0.069
 Debor-0.062
BUR-0.062
osit-0.060
iated-0.058
Token,
Token ID11
Feature activation-7.65e-03

Pos logit contributions
ogens+0.035
 Debor+0.032
BUR+0.031
osit+0.031
 supervision+0.030
Neg logit contributions
blance-0.046
uments-0.043
arthed-0.043
ondon-0.041
nesota-0.039
Token Food
Token ID7318
Feature activation+2.59e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token Network
Token ID7311
Feature activation+1.56e-01

Pos logit contributions
blance+0.085
uments+0.079
arthed+0.078
ondon+0.074
nesota+0.069
Neg logit contributions
ogens-0.092
 Debor-0.086
BUR-0.084
osit-0.082
 supervision-0.081
Token,
Token ID11
Feature activation-7.20e-03

Pos logit contributions
blance+0.061
uments+0.058
arthed+0.057
ondon+0.055
nesota+0.052
Neg logit contributions
ogens-0.046
 Debor-0.042
BUR-0.041
osit-0.040
 supervision-0.039
Token HG
Token ID48698
Feature activation-1.01e+00

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.002
TokenTV
Token ID6849
Feature activation-3.34e-02

Pos logit contributions
ogens+0.271
BUR+0.245
 Debor+0.242
osit+0.230
 supervision+0.226
Neg logit contributions
blance-0.427
uments-0.396
arthed-0.395
ondon-0.378
nesota-0.371
Token,
Token ID11
Feature activation-1.30e-02

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Token Cartoon
Token ID46838
Feature activation+8.54e-02

Pos logit contributions
ogens+0.004
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.004
Token Network
Token ID7311
Feature activation+1.39e-01

Pos logit contributions
blance+0.029
uments+0.027
arthed+0.027
ondon+0.025
nesota+0.024
Neg logit contributions
ogens-0.029
 Debor-0.027
BUR-0.027
osit-0.026
 supervision-0.026
Token,
Token ID11
Feature activation-3.60e-03

Pos logit contributions
blance+0.053
uments+0.050
arthed+0.050
ondon+0.047
nesota+0.045
Neg logit contributions
ogens-0.042
 Debor-0.039
BUR-0.038
osit-0.037
 supervision-0.036
Token Ramadan
Token ID37604
Feature activation-1.98e-01

Pos logit contributions
blance+0.059
uments+0.055
arthed+0.055
ondon+0.052
nesota+0.050
Neg logit contributions
ogens-0.048
 Debor-0.045
BUR-0.043
osit-0.042
 supervision-0.042
Token argues
Token ID11673
Feature activation-1.48e-01

Pos logit contributions
ogens+0.058
 Debor+0.054
BUR+0.053
osit+0.051
 supervision+0.050
Neg logit contributions
blance-0.077
uments-0.073
arthed-0.072
ondon-0.069
nesota-0.065
Token that
Token ID326
Feature activation-7.75e-03

Pos logit contributions
ogens+0.045
 Debor+0.042
BUR+0.041
osit+0.040
 supervision+0.039
Neg logit contributions
blance-0.055
uments-0.052
arthed-0.052
ondon-0.049
nesota-0.047
Token Muhammad
Token ID15870
Feature activation-1.62e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.002
Token dev
Token ID1614
Feature activation+1.07e-01

Pos logit contributions
ogens+0.048
 Debor+0.045
BUR+0.044
osit+0.042
 supervision+0.042
Neg logit contributions
blance-0.062
uments-0.059
arthed-0.058
ondon-0.055
nesota-0.053
Tokeniated
Token ID12931
Feature activation-1.01e+00

Pos logit contributions
blance+0.065
uments+0.063
arthed+0.062
ondon+0.061
nesota+0.059
Neg logit contributions
ogens-0.008
 Debor-0.005
BUR-0.005
osit-0.004
iated-0.003
Token from
Token ID422
Feature activation-1.89e-02

Pos logit contributions
ogens+0.319
 Debor+0.299
BUR+0.289
osit+0.283
iated+0.279
Neg logit contributions
blance-0.367
uments-0.344
arthed-0.341
ondon-0.324
nesota-0.306
Token his
Token ID465
Feature activation+1.98e-02

Pos logit contributions
ogens+0.006
 Debor+0.006
BUR+0.005
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.006
ondon-0.006
nesota-0.006
Token earlier
Token ID2961
Feature activation+3.60e-02

Pos logit contributions
blance+0.008
uments+0.008
arthed+0.008
ondon+0.007
nesota+0.007
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.005
 supervision-0.005
Token,
Token ID11
Feature activation+7.26e-03

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.010
 Debor-0.009
BUR-0.009
osit-0.009
 supervision-0.009
Token more
Token ID517
Feature activation+5.55e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token said
Token ID531
Feature activation-6.86e-02

Pos logit contributions
ogens+0.014
 Debor+0.013
BUR+0.013
osit+0.012
 supervision+0.012
Neg logit contributions
blance-0.019
uments-0.018
arthed-0.018
ondon-0.017
nesota-0.016
Token.
Token ID13
Feature activation-3.42e-02

Pos logit contributions
ogens+0.021
 Debor+0.020
BUR+0.019
osit+0.019
 supervision+0.019
Neg logit contributions
blance-0.025
uments-0.024
arthed-0.024
ondon-0.022
nesota-0.021
Token
Token ID198
Feature activation-1.71e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Token
Token ID198
Feature activation-3.00e-03

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.005
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.006
TokenSm
Token ID7556
Feature activation+8.59e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Tokenoke
Token ID2088
Feature activation-9.61e-01

Pos logit contributions
blance+0.032
uments+0.030
arthed+0.030
ondon+0.028
nesota+0.027
Neg logit contributions
ogens-0.027
 Debor-0.025
BUR-0.024
osit-0.024
iated-0.023
Token Music
Token ID7849
Feature activation+8.00e-02

Pos logit contributions
ogens+0.251
 Debor+0.231
BUR+0.224
osit+0.216
 supervision+0.211
Neg logit contributions
blance-0.404
uments-0.382
arthed-0.379
ondon-0.363
nesota-0.346
Token manager
Token ID4706
Feature activation-8.55e-02

Pos logit contributions
blance+0.032
uments+0.030
arthed+0.029
ondon+0.028
nesota+0.027
Neg logit contributions
ogens-0.023
 Debor-0.021
BUR-0.021
osit-0.020
 supervision-0.020
Token Mark
Token ID2940
Feature activation-1.33e-01

Pos logit contributions
ogens+0.025
 Debor+0.023
BUR+0.023
osit+0.022
 supervision+0.022
Neg logit contributions
blance-0.033
uments-0.031
arthed-0.031
ondon-0.029
nesota-0.028
Token de
Token ID390
Feature activation+2.08e-01

Pos logit contributions
ogens+0.041
 Debor+0.038
BUR+0.037
osit+0.036
 supervision+0.035
Neg logit contributions
blance-0.050
uments-0.047
arthed-0.047
ondon-0.044
nesota-0.042
Token Jong
Token ID17960
Feature activation-1.21e-01

Pos logit contributions
blance+0.076
uments+0.072
arthed+0.071
ondon+0.067
nesota+0.064
Neg logit contributions
ogens-0.066
 Debor-0.061
BUR-0.060
osit-0.058
 supervision-0.057
Token Pride
Token ID21735
Feature activation-1.16e-01

Pos logit contributions
ogens+0.039
 Debor+0.037
BUR+0.035
osit+0.034
 supervision+0.034
Neg logit contributions
blance-0.049
uments-0.046
arthed-0.045
ondon-0.043
nesota-0.041
Token he
Token ID339
Feature activation-1.17e-01

Pos logit contributions
ogens+0.034
 Debor+0.032
BUR+0.031
osit+0.030
 supervision+0.029
Neg logit contributions
blance-0.045
uments-0.042
arthed-0.042
ondon-0.040
nesota-0.039
Token sought
Token ID7194
Feature activation-1.64e-01

Pos logit contributions
ogens+0.036
 Debor+0.033
BUR+0.032
osit+0.031
iated+0.031
Neg logit contributions
blance-0.044
uments-0.041
arthed-0.041
ondon-0.039
nesota-0.037
Token to
Token ID284
Feature activation-3.26e-02

Pos logit contributions
ogens+0.052
 Debor+0.048
BUR+0.047
osit+0.046
 supervision+0.045
Neg logit contributions
blance-0.060
uments-0.056
arthed-0.056
ondon-0.053
nesota-0.050
Token st
Token ID336
Feature activation+5.22e-02

Pos logit contributions
ogens+0.009
 Debor+0.009
BUR+0.009
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Tokenoke
Token ID2088
Feature activation-9.53e-01

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.016
ondon+0.015
nesota+0.015
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.016
osit-0.016
 supervision-0.016
Token through
Token ID832
Feature activation+3.52e-01

Pos logit contributions
ogens+0.284
 Debor+0.264
BUR+0.256
osit+0.249
 supervision+0.246
Neg logit contributions
blance-0.367
uments-0.344
arthed-0.343
ondon-0.324
nesota-0.312
Token Pad
Token ID15744
Feature activation+3.17e-01

Pos logit contributions
blance+0.131
uments+0.123
arthed+0.122
ondon+0.115
nesota+0.111
Neg logit contributions
ogens-0.109
 Debor-0.102
BUR-0.099
osit-0.096
 supervision-0.095
Tokenm
Token ID76
Feature activation-2.11e-02

Pos logit contributions
blance+0.092
uments+0.084
arthed+0.083
ondon+0.078
nesota+0.073
Neg logit contributions
ogens-0.125
 Debor-0.118
BUR-0.116
osit-0.114
 supervision-0.112
Tokenav
Token ID615
Feature activation+1.91e-01

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.005
Tokenati
Token ID7246
Feature activation+8.19e-02

Pos logit contributions
blance+0.062
uments+0.058
arthed+0.057
ondon+0.054
nesota+0.051
Neg logit contributions
ogens-0.068
 Debor-0.064
BUR-0.063
osit-0.061
 supervision-0.060
Token,
Token ID11
Feature activation+2.27e-02

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.016
 Debor-0.015
BUR-0.014
osit-0.014
 supervision-0.013
Token they
Token ID484
Feature activation-3.85e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.005
Token in
Token ID287
Feature activation+3.55e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.010
 supervision+0.009
Neg logit contributions
blance-0.015
uments-0.014
arthed-0.014
ondon-0.014
nesota-0.013
Token­
Token ID3907
Feature activation-1.62e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.014
nesota+0.013
Neg logit contributions
ogens-0.009
 Debor-0.008
BUR-0.008
osit-0.008
 supervision-0.008
Tokenv
Token ID85
Feature activation+9.25e-02

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.005
osit+0.005
iated+0.005
Neg logit contributions
blance-0.006
uments-0.005
arthed-0.005
ondon-0.005
aiden-0.005
Tokenoke
Token ID2088
Feature activation-9.50e-01

Pos logit contributions
blance+0.036
uments+0.034
arthed+0.034
ondon+0.032
nesota+0.031
Neg logit contributions
ogens-0.027
 Debor-0.025
BUR-0.024
osit-0.024
 supervision-0.023
Token him
Token ID683
Feature activation+2.38e-01

Pos logit contributions
ogens+0.297
 Debor+0.279
BUR+0.271
osit+0.263
 supervision+0.259
Neg logit contributions
blance-0.352
uments-0.330
arthed-0.327
ondon-0.310
aiden-0.294
Token.
Token ID13
Feature activation-3.80e-03

Pos logit contributions
blance+0.088
uments+0.083
arthed+0.082
ondon+0.078
nesota+0.074
Neg logit contributions
ogens-0.074
 Debor-0.069
BUR-0.067
osit-0.065
 supervision-0.064
Token
Token ID564
Feature activation-2.94e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token
Token ID250
Feature activation+2.77e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.010
 supervision+0.009
Neg logit contributions
blance-0.009
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.008
TokenI
Token ID40
Feature activation-4.57e-02

Pos logit contributions
blance+0.011
uments+0.010
arthed+0.010
ondon+0.010
nesota+0.009
Neg logit contributions
ogens-0.008
 Debor-0.008
BUR-0.007
osit-0.007
iated-0.007
Token be
Token ID307
Feature activation+3.56e-02

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.003
Token
Token ID564
Feature activation-2.25e-02

Pos logit contributions
blance+0.013
uments+0.013
arthed+0.013
ondon+0.012
nesota+0.011
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.010
 supervision-0.009
Token
Token ID250
Feature activation+3.59e-02

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.005
Tokenb
Token ID65
Feature activation+1.47e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.011
nesota+0.011
Neg logit contributions
ogens-0.012
 Debor-0.011
BUR-0.011
osit-0.010
iated-0.010
Tokenesp
Token ID9774
Feature activation+5.35e-01

Pos logit contributions
blance+0.046
uments+0.043
arthed+0.043
ondon+0.040
nesota+0.038
Neg logit contributions
ogens-0.054
 Debor-0.051
BUR-0.050
osit-0.049
iated-0.048
Tokenoke
Token ID2088
Feature activation-9.49e-01

Pos logit contributions
blance+0.319
uments+0.308
arthed+0.306
ondon+0.297
nesota+0.287
Neg logit contributions
ogens-0.045
 Debor-0.034
BUR-0.030
osit-0.025
 supervision-0.023
Token
Token ID447
Feature activation+2.26e-03

Pos logit contributions
ogens+0.272
 Debor+0.252
BUR+0.245
osit+0.238
 supervision+0.233
Neg logit contributions
blance-0.376
uments-0.354
arthed-0.351
ondon-0.335
nesota-0.319
Token
Token ID251
Feature activation-4.17e-02

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token
Token ID784
Feature activation+3.33e-03

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.011
 supervision+0.010
Neg logit contributions
blance-0.016
uments-0.015
arthed-0.015
ondon-0.014
nesota-0.014
Token rather
Token ID2138
Feature activation+2.90e-01

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token like
Token ID588
Feature activation+2.68e-02

Pos logit contributions
blance+0.097
uments+0.091
arthed+0.089
ondon+0.085
nesota+0.080
Neg logit contributions
ogens-0.101
 Debor-0.095
BUR-0.093
osit-0.090
 supervision-0.089
Token a
Token ID257
Feature activation-8.01e-03

Pos logit contributions
blance+0.009
uments+0.008
arthed+0.008
ondon+0.008
nesota+0.007
Neg logit contributions
ogens-0.007
 Debor-0.007
BUR-0.007
osit-0.006
 supervision-0.006
Token team
Token ID1074
Feature activation+1.05e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token in
Token ID287
Feature activation+5.32e-03

Pos logit contributions
blance+0.042
uments+0.040
arthed+0.039
ondon+0.037
nesota+0.036
Neg logit contributions
ogens-0.030
 Debor-0.027
BUR-0.027
osit-0.026
 supervision-0.025
Token-
Token ID12
Feature activation-2.36e-02

Pos logit contributions
blance+0.002
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Tokenj
Token ID73
Feature activation+2.72e-01

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.008
uments-0.008
arthed-0.007
ondon-0.007
nesota-0.007
Tokenoke
Token ID2088
Feature activation-9.45e-01

Pos logit contributions
blance+0.158
uments+0.152
arthed+0.151
ondon+0.146
nesota+0.142
Neg logit contributions
ogens-0.028
 Debor-0.022
BUR-0.020
osit-0.018
 supervision-0.016
Token from
Token ID422
Feature activation-2.12e-02

Pos logit contributions
ogens+0.278
 Debor+0.259
BUR+0.252
osit+0.244
 supervision+0.241
Neg logit contributions
blance-0.364
uments-0.344
arthed-0.340
ondon-0.324
nesota-0.310
Token down
Token ID866
Feature activation+4.78e-03

Pos logit contributions
ogens+0.007
 Debor+0.006
BUR+0.006
osit+0.006
 supervision+0.006
Neg logit contributions
blance-0.008
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.007
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
blance+0.002
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token years
Token ID812
Feature activation+5.95e-04

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.006
arthed-0.006
ondon-0.005
nesota-0.005
Token?
Token ID30
Feature activation-6.31e-02

Pos logit contributions
blance+0.000
uments+0.000
arthed+0.000
ondon+0.000
nesota+0.000
Neg logit contributions
ogens-0.000
 Debor-0.000
BUR-0.000
osit-0.000
 supervision-0.000
Token or
Token ID393
Feature activation-1.26e-02

Pos logit contributions
ogens+0.075
 Debor+0.070
BUR+0.068
osit+0.066
 supervision+0.065
Neg logit contributions
blance-0.096
uments-0.091
arthed-0.090
ondon-0.085
nesota-0.082
Token may
Token ID743
Feature activation-4.05e-02

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Token perhaps
Token ID3737
Feature activation+1.04e-01

Pos logit contributions
ogens+0.013
 Debor+0.012
BUR+0.012
osit+0.011
 supervision+0.011
Neg logit contributions
blance-0.015
uments-0.014
arthed-0.014
ondon-0.013
nesota-0.012
Token be
Token ID307
Feature activation+8.30e-02

Pos logit contributions
blance+0.039
uments+0.037
arthed+0.037
ondon+0.035
nesota+0.033
Neg logit contributions
ogens-0.032
 Debor-0.029
BUR-0.029
osit-0.028
 supervision-0.027
Token allev
Token ID23863
Feature activation+3.44e-01

Pos logit contributions
blance+0.031
uments+0.029
arthed+0.029
ondon+0.027
nesota+0.026
Neg logit contributions
ogens-0.026
 Debor-0.024
BUR-0.024
osit-0.023
 supervision-0.023
Tokeniated
Token ID12931
Feature activation-9.37e-01

Pos logit contributions
blance+0.216
uments+0.209
arthed+0.208
ondon+0.202
nesota+0.196
Neg logit contributions
ogens-0.017
 Debor-0.011
BUR-0.008
osit-0.005
 supervision-0.004
Token or
Token ID393
Feature activation-1.36e-02

Pos logit contributions
ogens+0.318
 Debor+0.299
BUR+0.290
osit+0.283
iated+0.281
Neg logit contributions
blance-0.322
uments-0.300
arthed-0.298
ondon-0.282
nesota-0.265
Token designed
Token ID3562
Feature activation+1.94e-01

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.004
nesota-0.004
Token out
Token ID503
Feature activation+4.92e-02

Pos logit contributions
blance+0.072
uments+0.068
arthed+0.067
ondon+0.064
nesota+0.061
Neg logit contributions
ogens-0.060
 Debor-0.056
BUR-0.055
osit-0.053
 supervision-0.052
Token of
Token ID286
Feature activation+3.68e-02

Pos logit contributions
blance+0.019
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.016
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.014
osit-0.013
 supervision-0.013
Token the
Token ID262
Feature activation+6.18e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.009
 supervision-0.009
Token subway
Token ID19612
Feature activation-1.23e-01

Pos logit contributions
ogens+0.122
 Debor+0.114
BUR+0.112
osit+0.109
 supervision+0.107
Neg logit contributions
blance-0.129
uments-0.121
arthed-0.120
ondon-0.113
nesota-0.107
Token station
Token ID4429
Feature activation+6.79e-03

Pos logit contributions
ogens+0.034
 Debor+0.031
BUR+0.030
osit+0.029
 supervision+0.028
Neg logit contributions
blance-0.050
uments-0.047
arthed-0.047
ondon-0.045
nesota-0.043
Token in
Token ID287
Feature activation-5.86e-03

Pos logit contributions
blance+0.003
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token Et
Token ID17906
Feature activation-3.76e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Tokenobic
Token ID20803
Feature activation-3.85e-01

Pos logit contributions
ogens+0.078
 Debor+0.071
BUR+0.068
osit+0.064
 supervision+0.063
Neg logit contributions
blance-0.177
uments-0.170
arthed-0.168
ondon-0.162
nesota-0.155
Tokenoke
Token ID2088
Feature activation-9.22e-01

Pos logit contributions
ogens+0.029
 Debor+0.020
BUR+0.018
osit+0.015
 supervision+0.013
Neg logit contributions
blance-0.234
uments-0.225
arthed-0.223
ondon-0.217
nesota-0.211
Token.
Token ID13
Feature activation-2.65e-02

Pos logit contributions
ogens+0.286
 Debor+0.267
BUR+0.260
osit+0.252
 supervision+0.248
Neg logit contributions
blance-0.343
uments-0.322
arthed-0.319
ondon-0.303
nesota-0.287
Token
Token ID198
Feature activation-8.94e-03

Pos logit contributions
ogens+0.008
 Debor+0.008
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.010
uments-0.009
arthed-0.009
ondon-0.009
nesota-0.008
Token
Token ID198
Feature activation-7.51e-03

Pos logit contributions
ogens+0.003
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.004
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
TokenPolice
Token ID9039
Feature activation+1.95e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.002
nesota-0.002
Token have
Token ID423
Feature activation-2.77e-02

Pos logit contributions
blance+0.075
uments+0.071
arthed+0.070
ondon+0.067
nesota+0.064
Neg logit contributions
ogens-0.058
 Debor-0.054
BUR-0.052
osit-0.051
 supervision-0.050
Token identified
Token ID5174
Feature activation+8.64e-03

Pos logit contributions
ogens+0.043
 Debor+0.040
BUR+0.039
osit+0.037
 supervision+0.037
Neg logit contributions
blance-0.053
uments-0.050
arthed-0.049
ondon-0.047
nesota-0.045
Token as
Token ID355
Feature activation-1.28e-01

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token Joshua
Token ID20700
Feature activation-8.09e-02

Pos logit contributions
ogens+0.040
 Debor+0.038
BUR+0.036
osit+0.035
 supervision+0.035
Neg logit contributions
blance-0.048
uments-0.045
arthed-0.044
ondon-0.042
nesota-0.040
Token E
Token ID412
Feature activation-1.71e-01

Pos logit contributions
ogens+0.026
 Debor+0.024
BUR+0.023
osit+0.023
 supervision+0.022
Neg logit contributions
blance-0.030
uments-0.028
arthed-0.028
ondon-0.026
nesota-0.025
Tokenern
Token ID1142
Feature activation+7.80e-02

Pos logit contributions
ogens+0.056
 Debor+0.052
BUR+0.051
osit+0.050
 supervision+0.049
Neg logit contributions
blance-0.061
uments-0.057
arthed-0.057
ondon-0.054
nesota-0.051
Tokenisse
Token ID20782
Feature activation-9.19e-01

Pos logit contributions
blance+0.028
uments+0.027
arthed+0.026
ondon+0.025
nesota+0.024
Neg logit contributions
ogens-0.025
 Debor-0.023
BUR-0.023
osit-0.022
 supervision-0.022
Token and
Token ID290
Feature activation-6.49e-02

Pos logit contributions
ogens+0.255
 Debor+0.238
BUR+0.230
osit+0.223
 supervision+0.218
Neg logit contributions
blance-0.370
uments-0.350
arthed-0.347
ondon-0.330
nesota-0.316
Token Beau
Token ID32831
Feature activation+2.12e-01

Pos logit contributions
ogens+0.020
 Debor+0.018
BUR+0.018
osit+0.017
 supervision+0.017
Neg logit contributions
blance-0.025
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.021
Token Sch
Token ID3059
Feature activation+7.19e-02

Pos logit contributions
blance+0.077
uments+0.072
arthed+0.072
ondon+0.068
nesota+0.065
Neg logit contributions
ogens-0.067
 Debor-0.063
BUR-0.061
osit-0.060
 supervision-0.058
Tokenoen
Token ID6571
Feature activation-3.69e-01

Pos logit contributions
blance+0.026
uments+0.024
arthed+0.024
ondon+0.023
nesota+0.021
Neg logit contributions
ogens-0.023
 Debor-0.022
BUR-0.021
osit-0.021
iated-0.020
Tokenhard
Token ID10424
Feature activation+4.23e-02

Pos logit contributions
ogens+0.114
 Debor+0.106
BUR+0.104
osit+0.101
 supervision+0.099
Neg logit contributions
blance-0.137
uments-0.129
arthed-0.128
ondon-0.121
nesota-0.115
Token (
Token ID357
Feature activation+2.22e-03

Pos logit contributions
ogens+0.043
 Debor+0.040
BUR+0.039
osit+0.038
 supervision+0.037
Neg logit contributions
blance-0.049
uments-0.046
arthed-0.045
ondon-0.043
nesota-0.041
Token1979
Token ID33581
Feature activation+2.99e-01

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.000
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token)
Token ID8
Feature activation-1.55e-02

Pos logit contributions
blance+0.105
uments+0.099
arthed+0.098
ondon+0.093
nesota+0.088
Neg logit contributions
ogens-0.098
 Debor-0.092
BUR-0.090
osit-0.087
 supervision-0.086
Token
Token ID198
Feature activation-1.12e-02

Pos logit contributions
ogens+0.005
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token
Token ID198
Feature activation-5.53e-03

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
TokenGrade
Token ID42233
Feature activation-9.12e-01

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.002
Token:
Token ID25
Feature activation+1.86e-02

Pos logit contributions
ogens+0.268
 Debor+0.247
BUR+0.243
osit+0.236
 supervision+0.229
Neg logit contributions
blance-0.358
uments-0.333
arthed-0.333
ondon-0.316
nesota-0.300
Token A
Token ID317
Feature activation+1.17e-01

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token+
Token ID10
Feature activation+3.18e-01

Pos logit contributions
blance+0.043
uments+0.040
arthed+0.040
ondon+0.038
nesota+0.036
Neg logit contributions
ogens-0.036
 Debor-0.034
BUR-0.033
osit-0.032
 supervision-0.032
Token
Token ID198
Feature activation-5.52e-03

Pos logit contributions
blance+0.119
uments+0.112
arthed+0.111
ondon+0.105
nesota+0.100
Neg logit contributions
ogens-0.098
 Debor-0.091
BUR-0.089
osit-0.086
 supervision-0.084
Token
Token ID198
Feature activation+8.71e-04

Pos logit contributions
ogens+0.002
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token Ver
Token ID4643
Feature activation-1.14e-02

Pos logit contributions
blance+0.094
uments+0.088
arthed+0.087
ondon+0.083
nesota+0.079
Neg logit contributions
ogens-0.084
 Debor-0.078
BUR-0.076
osit-0.074
 supervision-0.073
Tokenh
Token ID71
Feature activation-5.98e-02

Pos logit contributions
ogens+0.004
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Tokenä
Token ID11033
Feature activation+5.83e-02

Pos logit contributions
ogens+0.022
 Debor+0.020
BUR+0.020
osit+0.019
iated+0.019
Neg logit contributions
blance-0.019
uments-0.018
arthed-0.018
ondon-0.017
nesota-0.016
Tokenlt
Token ID2528
Feature activation-3.85e-01

Pos logit contributions
blance+0.026
uments+0.025
arthed+0.025
ondon+0.024
nesota+0.023
Neg logit contributions
ogens-0.014
 Debor-0.012
BUR-0.012
osit-0.012
iated-0.011
Tokenn
Token ID77
Feature activation-5.30e-02

Pos logit contributions
ogens+0.111
 Debor+0.102
BUR+0.100
osit+0.097
 supervision+0.095
Neg logit contributions
blance-0.152
uments-0.143
arthed-0.142
ondon-0.135
nesota-0.129
Tokenisse
Token ID20782
Feature activation-9.01e-01

Pos logit contributions
ogens+0.007
 Debor+0.006
BUR+0.006
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.029
uments-0.028
arthed-0.028
ondon-0.027
nesota-0.026
Token"
Token ID1
Feature activation+3.32e-02

Pos logit contributions
ogens+0.301
 Debor+0.282
BUR+0.276
osit+0.269
 supervision+0.265
Neg logit contributions
blance-0.314
arthed-0.293
uments-0.293
ondon-0.276
nesota-0.261
Token because
Token ID780
Feature activation+1.75e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.011
nesota+0.011
Neg logit contributions
ogens-0.010
 Debor-0.009
BUR-0.009
osit-0.009
 supervision-0.009
Token of
Token ID286
Feature activation-1.36e-02

Pos logit contributions
blance+0.068
uments+0.064
arthed+0.063
ondon+0.060
nesota+0.057
Neg logit contributions
ogens-0.052
 Debor-0.048
BUR-0.047
osit-0.045
 supervision-0.044
Token refugees
Token ID8015
Feature activation-3.35e-02

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.004
Token or
Token ID393
Feature activation-5.74e-02

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Token (
Token ID357
Feature activation+2.34e-02

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.002
Token1978
Token ID37950
Feature activation+2.81e-01

Pos logit contributions
blance+0.007
uments+0.006
arthed+0.006
ondon+0.006
nesota+0.005
Neg logit contributions
ogens-0.009
 Debor-0.009
BUR-0.009
osit-0.009
 supervision-0.008
Token)
Token ID8
Feature activation+4.13e-03

Pos logit contributions
blance+0.100
uments+0.094
arthed+0.093
ondon+0.088
nesota+0.083
Neg logit contributions
ogens-0.092
 Debor-0.086
BUR-0.084
osit-0.081
 supervision-0.080
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
blance+0.002
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token
Token ID198
Feature activation-2.01e-04

Pos logit contributions
blance+0.004
uments+0.004
arthed+0.004
ondon+0.004
nesota+0.004
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
TokenGrade
Token ID42233
Feature activation-8.99e-01

Pos logit contributions
ogens+0.000
 Debor+0.000
BUR+0.000
osit+0.000
 supervision+0.000
Neg logit contributions
blance-0.000
uments-0.000
arthed-0.000
ondon-0.000
nesota-0.000
Token:
Token ID25
Feature activation+3.93e-02

Pos logit contributions
ogens+0.261
 Debor+0.240
BUR+0.238
osit+0.230
 supervision+0.223
Neg logit contributions
blance-0.355
uments-0.331
arthed-0.331
ondon-0.314
nesota-0.298
Token A
Token ID317
Feature activation+1.38e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.011
nesota+0.011
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.013
 supervision-0.012
Token
Token ID198
Feature activation+2.33e-02

Pos logit contributions
blance+0.050
uments+0.048
arthed+0.047
ondon+0.045
nesota+0.042
Neg logit contributions
ogens-0.044
 Debor-0.041
BUR-0.040
osit-0.038
 supervision-0.038
Token
Token ID198
Feature activation+1.28e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
iated-0.006
TokenIn
Token ID818
Feature activation-6.67e-02

Pos logit contributions
blance+0.006
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
Token
Token ID198
Feature activation-3.75e-02

Pos logit contributions
ogens+0.015
 Debor+0.014
BUR+0.013
osit+0.013
 supervision+0.013
Neg logit contributions
blance-0.018
uments-0.017
arthed-0.017
ondon-0.016
nesota-0.015
Token
Token ID198
Feature activation-5.00e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.010
 supervision+0.009
Neg logit contributions
blance-0.015
uments-0.014
arthed-0.014
ondon-0.013
nesota-0.012
TokenKen
Token ID27827
Feature activation-1.93e-02

Pos logit contributions
ogens+0.015
 Debor+0.014
BUR+0.013
osit+0.013
 supervision+0.013
Neg logit contributions
blance-0.019
uments-0.018
arthed-0.018
ondon-0.017
nesota-0.016
Tokenichi
Token ID16590
Feature activation+3.11e-01

Pos logit contributions
ogens+0.006
 Debor+0.006
BUR+0.006
osit+0.006
 supervision+0.006
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.006
nesota-0.006
Token Shin
Token ID11466
Feature activation+1.05e-01

Pos logit contributions
blance+0.117
uments+0.110
arthed+0.109
ondon+0.104
nesota+0.099
Neg logit contributions
ogens-0.095
 Debor-0.088
BUR-0.086
osit-0.083
 supervision-0.082
Tokenoda
Token ID11329
Feature activation-8.95e-01

Pos logit contributions
blance+0.048
uments+0.046
arthed+0.046
ondon+0.044
nesota+0.042
Neg logit contributions
ogens-0.023
 Debor-0.021
BUR-0.020
osit-0.019
 supervision-0.019
Token,
Token ID11
Feature activation-3.16e-02

Pos logit contributions
ogens+0.271
 Debor+0.252
BUR+0.245
osit+0.239
 supervision+0.234
Neg logit contributions
blance-0.339
uments-0.319
arthed-0.316
ondon-0.301
nesota-0.286
Token the
Token ID262
Feature activation-6.32e-02

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.009
 supervision+0.008
Neg logit contributions
blance-0.012
uments-0.011
arthed-0.011
ondon-0.010
nesota-0.010
Token boss
Token ID6478
Feature activation-4.76e-01

Pos logit contributions
ogens+0.019
 Debor+0.017
BUR+0.017
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.024
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.021
Token of
Token ID286
Feature activation-3.84e-02

Pos logit contributions
ogens+0.146
 Debor+0.136
BUR+0.133
osit+0.128
iated+0.126
Neg logit contributions
blance-0.178
uments-0.168
arthed-0.166
ondon-0.158
nesota-0.149
Token Japan
Token ID2869
Feature activation+5.60e-02

Pos logit contributions
ogens+0.012
 Debor+0.012
BUR+0.011
osit+0.011
 supervision+0.011
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Token Rd
Token ID20769
Feature activation-6.27e-02

Pos logit contributions
ogens+0.082
 Debor+0.076
BUR+0.075
osit+0.073
 supervision+0.071
Neg logit contributions
blance-0.085
uments-0.080
arthed-0.079
ondon-0.075
nesota-0.071
Token.
Token ID13
Feature activation+3.93e-02

Pos logit contributions
ogens+0.019
 Debor+0.018
BUR+0.018
osit+0.017
 supervision+0.017
Neg logit contributions
blance-0.023
uments-0.022
arthed-0.022
ondon-0.021
nesota-0.020
Token in
Token ID287
Feature activation+4.38e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.012
Neg logit contributions
ogens-0.012
 Debor-0.011
BUR-0.011
osit-0.011
 supervision-0.011
Token Et
Token ID17906
Feature activation-3.38e-01

Pos logit contributions
blance+0.016
uments+0.015
arthed+0.015
ondon+0.014
nesota+0.013
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.013
 supervision-0.012
Tokenobic
Token ID20803
Feature activation-3.21e-01

Pos logit contributions
ogens+0.070
 Debor+0.063
BUR+0.060
osit+0.057
 supervision+0.056
Neg logit contributions
blance-0.160
uments-0.153
arthed-0.152
ondon-0.147
nesota-0.140
Tokenoke
Token ID2088
Feature activation-8.90e-01

Pos logit contributions
ogens+0.025
 Debor+0.017
BUR+0.015
osit+0.013
 supervision+0.011
Neg logit contributions
blance-0.195
uments-0.188
arthed-0.186
ondon-0.181
nesota-0.176
Token
Token ID447
Feature activation+1.89e-02

Pos logit contributions
ogens+0.272
 Debor+0.253
BUR+0.247
osit+0.240
 supervision+0.235
Neg logit contributions
blance-0.334
uments-0.314
arthed-0.311
ondon-0.297
nesota-0.281
Token
Token ID247
Feature activation+1.43e-02

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.005
ondon+0.005
aiden+0.005
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Tokens
Token ID82
Feature activation+2.49e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token Mark
Token ID2940
Feature activation-7.23e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Tokenland
Token ID1044
Feature activation-1.66e-01

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.018
osit+0.018
 supervision+0.017
Neg logit contributions
blance-0.029
uments-0.027
arthed-0.027
ondon-0.026
nesota-0.025
Token rid
Token ID5755
Feature activation-4.86e-02

Pos logit contributions
blance+0.021
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.017
 Debor-0.016
BUR-0.015
osit-0.015
 supervision-0.015
Token of
Token ID286
Feature activation+2.65e-02

Pos logit contributions
ogens+0.015
 Debor+0.014
BUR+0.013
osit+0.013
 supervision+0.013
Neg logit contributions
blance-0.019
uments-0.017
arthed-0.017
ondon-0.016
nesota-0.016
Token its
Token ID663
Feature activation+7.23e-03

Pos logit contributions
blance+0.010
uments+0.010
arthed+0.010
ondon+0.009
nesota+0.009
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Token Communist
Token ID14884
Feature activation+1.37e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token y
Token ID331
Feature activation+7.71e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.003
 supervision-0.003
Tokenoke
Token ID2088
Feature activation-8.82e-01

Pos logit contributions
blance+0.042
uments+0.040
arthed+0.040
ondon+0.039
aiden+0.037
Neg logit contributions
ogens-0.010
 Debor-0.009
BUR-0.008
osit-0.008
 supervision-0.007
Token.
Token ID13
Feature activation+5.76e-02

Pos logit contributions
ogens+0.262
 Debor+0.244
BUR+0.236
osit+0.228
 supervision+0.226
Neg logit contributions
blance-0.341
uments-0.319
arthed-0.318
ondon-0.301
nesota-0.289
Token For
Token ID1114
Feature activation+9.03e-02

Pos logit contributions
blance+0.022
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.016
osit-0.016
 supervision-0.015
Token conservatives
Token ID12471
Feature activation-2.29e-01

Pos logit contributions
blance+0.034
uments+0.032
arthed+0.032
ondon+0.030
nesota+0.029
Neg logit contributions
ogens-0.027
 Debor-0.026
BUR-0.025
osit-0.024
 supervision-0.024
Token,
Token ID11
Feature activation+4.92e-02

Pos logit contributions
ogens+0.069
 Debor+0.064
BUR+0.062
osit+0.060
 supervision+0.059
Neg logit contributions
blance-0.088
uments-0.083
arthed-0.082
ondon-0.078
nesota-0.074
Token libertarians
Token ID35929
Feature activation-2.00e-01

Pos logit contributions
blance+0.019
uments+0.018
arthed+0.018
ondon+0.017
nesota+0.016
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.013
osit-0.013
 supervision-0.013
Token Ver
Token ID4643
Feature activation+7.80e-03

Pos logit contributions
blance+0.107
uments+0.101
arthed+0.100
ondon+0.095
nesota+0.090
Neg logit contributions
ogens-0.083
 Debor-0.077
BUR-0.075
osit-0.073
 supervision-0.072
Tokenh
Token ID71
Feature activation-7.10e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.003
 Debor-0.002
BUR-0.002
osit-0.002
iated-0.002
Tokenä
Token ID11033
Feature activation+6.91e-02

Pos logit contributions
ogens+0.024
 Debor+0.022
BUR+0.022
osit+0.021
iated+0.021
Neg logit contributions
blance-0.024
uments-0.023
arthed-0.023
ondon-0.021
nesota-0.020
Tokenlt
Token ID2528
Feature activation-3.77e-01

Pos logit contributions
blance+0.029
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.018
 Debor-0.016
BUR-0.016
osit-0.015
iated-0.015
Tokenn
Token ID77
Feature activation-4.48e-02

Pos logit contributions
ogens+0.125
 Debor+0.116
BUR+0.114
osit+0.111
 supervision+0.109
Neg logit contributions
blance-0.133
uments-0.124
arthed-0.123
ondon-0.117
nesota-0.110
Tokenisse
Token ID20782
Feature activation-8.80e-01

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.020
uments-0.019
arthed-0.019
ondon-0.018
nesota-0.017
Token"
Token ID1
Feature activation+6.22e-02

Pos logit contributions
ogens+0.286
 Debor+0.266
BUR+0.260
osit+0.254
 supervision+0.249
Neg logit contributions
blance-0.315
uments-0.294
arthed-0.294
ondon-0.278
nesota-0.265
Token is
Token ID318
Feature activation-1.20e-02

Pos logit contributions
blance+0.024
uments+0.023
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.017
osit-0.016
 supervision-0.016
Token just
Token ID655
Feature activation-7.11e-02

Pos logit contributions
ogens+0.004
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Token another
Token ID1194
Feature activation-2.88e-01

Pos logit contributions
ogens+0.022
 Debor+0.021
BUR+0.020
osit+0.020
 supervision+0.019
Neg logit contributions
blance-0.026
uments-0.025
arthed-0.025
ondon-0.023
nesota-0.022
Token way
Token ID835
Feature activation-4.73e-02

Pos logit contributions
ogens+0.079
 Debor+0.073
BUR+0.071
osit+0.068
 supervision+0.067
Neg logit contributions
blance-0.117
uments-0.111
arthed-0.110
ondon-0.105
nesota-0.101
Token a
Token ID257
Feature activation+3.26e-02

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.017
 Debor-0.016
BUR-0.016
osit-0.015
 supervision-0.015
Token crust
Token ID20048
Feature activation+5.58e-03

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.012
nesota+0.011
Neg logit contributions
ogens-0.009
 Debor-0.009
BUR-0.008
osit-0.008
 supervision-0.008
Tokeny
Token ID88
Feature activation-2.98e-01

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.002
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token old
Token ID1468
Feature activation+1.42e-02

Pos logit contributions
ogens+0.088
 Debor+0.082
BUR+0.079
osit+0.077
 supervision+0.076
Neg logit contributions
blance-0.115
uments-0.109
arthed-0.107
ondon-0.102
nesota-0.097
Token bl
Token ID698
Feature activation+2.41e-01

Pos logit contributions
blance+0.006
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.003
 supervision-0.003
Tokenoke
Token ID2088
Feature activation-8.75e-01

Pos logit contributions
blance+0.144
uments+0.138
arthed+0.137
ondon+0.133
nesota+0.129
Neg logit contributions
ogens-0.021
 Debor-0.015
BUR-0.014
osit-0.013
iated-0.011
Token on
Token ID319
Feature activation+8.28e-02

Pos logit contributions
ogens+0.265
 Debor+0.249
BUR+0.241
osit+0.234
 supervision+0.230
Neg logit contributions
blance-0.331
uments-0.312
arthed-0.309
ondon-0.293
nesota-0.279
Token a
Token ID257
Feature activation+5.98e-02

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.026
 Debor-0.025
BUR-0.024
osit-0.023
 supervision-0.023
Token stool
Token ID38753
Feature activation+3.64e-01

Pos logit contributions
blance+0.023
uments+0.022
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.018
 Debor-0.016
BUR-0.016
osit-0.015
 supervision-0.015
Token,
Token ID11
Feature activation+6.14e-02

Pos logit contributions
blance+0.136
uments+0.128
arthed+0.127
ondon+0.121
nesota+0.115
Neg logit contributions
ogens-0.112
 Debor-0.104
BUR-0.102
osit-0.099
 supervision-0.097
Token ask
Token ID1265
Feature activation-1.21e-01

Pos logit contributions
blance+0.023
uments+0.022
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.019
 Debor-0.017
BUR-0.017
osit-0.016
 supervision-0.016
Token areas
Token ID3006
Feature activation+1.84e-01

Pos logit contributions
blance+0.000
uments+0.000
arthed+0.000
ondon+0.000
nesota+0.000
Neg logit contributions
ogens-0.000
 Debor-0.000
BUR-0.000
osit-0.000
 supervision-0.000
Token might
Token ID1244
Feature activation-6.39e-02

Pos logit contributions
blance+0.069
uments+0.065
arthed+0.064
ondon+0.061
nesota+0.058
Neg logit contributions
ogens-0.057
 Debor-0.053
BUR-0.051
osit-0.050
 supervision-0.049
Token be
Token ID307
Feature activation+4.18e-02

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.018
osit+0.018
 supervision+0.017
Neg logit contributions
blance-0.024
uments-0.022
arthed-0.022
ondon-0.021
nesota-0.020
Token off
Token ID572
Feature activation-1.80e-01

Pos logit contributions
blance+0.016
uments+0.015
arthed+0.015
ondon+0.014
nesota+0.014
Neg logit contributions
ogens-0.012
 Debor-0.011
BUR-0.011
osit-0.011
 supervision-0.011
Token-
Token ID12
Feature activation+2.06e-02

Pos logit contributions
ogens+0.044
 Debor+0.041
BUR+0.039
osit+0.038
 supervision+0.037
Neg logit contributions
blance-0.078
uments-0.074
arthed-0.074
ondon-0.071
nesota-0.068
Tokenlimits
Token ID49196
Feature activation-8.70e-01

Pos logit contributions
blance+0.012
uments+0.012
arthed+0.012
ondon+0.012
nesota+0.011
Neg logit contributions
ogens-0.002
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token.
Token ID13
Feature activation+9.90e-03

Pos logit contributions
ogens+0.270
 Debor+0.252
BUR+0.245
osit+0.238
 supervision+0.235
Neg logit contributions
blance-0.325
uments-0.304
arthed-0.301
ondon-0.287
nesota-0.273
Token
Token ID198
Feature activation+1.37e-02

Pos logit contributions
blance+0.004
uments+0.004
arthed+0.004
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
Token
Token ID198
Feature activation-2.63e-03

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.003
TokenLa
Token ID14772
Feature activation+8.33e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Tokenure
Token ID495
Feature activation+1.44e-01

Pos logit contributions
blance+0.031
uments+0.030
arthed+0.029
ondon+0.028
nesota+0.026
Neg logit contributions
ogens-0.025
 Debor-0.024
BUR-0.023
osit-0.022
 supervision-0.022
Token.
Token ID13
Feature activation-1.67e-03

Pos logit contributions
blance+0.060
uments+0.056
arthed+0.056
ondon+0.053
nesota+0.050
Neg logit contributions
ogens-0.050
 Debor-0.047
BUR-0.046
osit-0.044
 supervision-0.044
Tokenim
Token ID320
Feature activation-3.52e-01

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.000
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.000
nesota-0.000
Tokenaging
Token ID3039
Feature activation+1.17e-03

Pos logit contributions
ogens+0.097
 Debor+0.087
BUR+0.085
osit+0.083
iated+0.081
Neg logit contributions
blance-0.144
arthed-0.136
uments-0.135
ondon-0.128
nesota-0.123
Token.
Token ID13
Feature activation-4.39e-03

Pos logit contributions
blance+0.000
uments+0.000
arthed+0.000
ondon+0.000
nesota+0.000
Neg logit contributions
ogens-0.000
 Debor-0.000
BUR-0.000
osit-0.000
 supervision-0.000
Tokenimage
Token ID9060
Feature activation+3.80e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Tokenformat
Token ID18982
Feature activation-8.55e-01

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.012
nesota+0.011
Neg logit contributions
ogens-0.013
 Debor-0.012
BUR-0.011
osit-0.011
iated-0.011
Token]
Token ID60
Feature activation-1.38e-03

Pos logit contributions
ogens+0.270
 Debor+0.253
BUR+0.246
osit+0.242
iated+0.237
Neg logit contributions
blance-0.311
arthed-0.288
uments-0.287
ondon-0.273
nesota-0.261
Token::
Token ID3712
Feature activation+5.38e-01

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.000
uments-0.000
arthed-0.000
ondon-0.000
nesota-0.000
TokenB
Token ID33
Feature activation+1.90e-01

Pos logit contributions
blance+0.199
uments+0.186
arthed+0.185
ondon+0.176
nesota+0.168
Neg logit contributions
ogens-0.168
 Debor-0.156
BUR-0.154
osit-0.149
iated-0.145
Tokenmp
Token ID3149
Feature activation-3.62e-01

Pos logit contributions
blance+0.072
uments+0.068
arthed+0.067
ondon+0.064
nesota+0.061
Neg logit contributions
ogens-0.057
 Debor-0.053
BUR-0.052
osit-0.051
iated-0.049
Token);
Token ID1776
Feature activation-1.35e-01

Pos logit contributions
ogens+0.113
 Debor+0.105
BUR+0.103
osit+0.101
iated+0.098
Neg logit contributions
blance-0.134
uments-0.124
arthed-0.124
ondon-0.118
nesota-0.113
Token That
Token ID1320
Feature activation-7.86e-02

Pos logit contributions
blance+0.019
uments+0.018
arthed+0.018
ondon+0.017
nesota+0.016
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.012
 supervision-0.012
Token never
Token ID1239
Feature activation-6.68e-02

Pos logit contributions
ogens+0.023
 Debor+0.021
BUR+0.020
osit+0.020
 supervision+0.019
Neg logit contributions
blance-0.031
uments-0.029
arthed-0.029
ondon-0.028
nesota-0.026
Token changes
Token ID2458
Feature activation+6.21e-02

Pos logit contributions
ogens+0.019
 Debor+0.017
BUR+0.017
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.027
uments-0.025
arthed-0.025
ondon-0.024
nesota-0.023
Token for
Token ID329
Feature activation+2.33e-02

Pos logit contributions
blance+0.023
uments+0.022
arthed+0.022
ondon+0.021
nesota+0.020
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.017
osit-0.017
 supervision-0.016
Token me
Token ID502
Feature activation+1.41e-01

Pos logit contributions
blance+0.008
uments+0.007
arthed+0.007
ondon+0.007
nesota+0.006
Neg logit contributions
ogens-0.008
 Debor-0.008
BUR-0.008
osit-0.007
 supervision-0.007
Token anyway
Token ID6949
Feature activation+6.11e-01

Pos logit contributions
blance+0.053
uments+0.050
arthed+0.050
ondon+0.047
nesota+0.045
Neg logit contributions
ogens-0.043
 Debor-0.040
BUR-0.039
osit-0.038
 supervision-0.037
Token.
Token ID13
Feature activation+4.90e-02

Pos logit contributions
blance+0.230
uments+0.216
arthed+0.215
ondon+0.204
nesota+0.194
Neg logit contributions
ogens-0.187
 Debor-0.174
BUR-0.169
osit-0.165
 supervision-0.161
Token I
Token ID314
Feature activation+3.54e-02

Pos logit contributions
blance+0.019
uments+0.018
arthed+0.018
ondon+0.017
nesota+0.016
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.012
 supervision-0.012
Token
Token ID447
Feature activation+5.73e-02

Pos logit contributions
blance+0.013
uments+0.012
arthed+0.012
ondon+0.012
nesota+0.011
Neg logit contributions
ogens-0.011
 Debor-0.010
BUR-0.010
osit-0.010
 supervision-0.010
Token
Token ID247
Feature activation+4.84e-02

Pos logit contributions
blance+0.021
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.017
osit-0.016
iated-0.016
Tokend
Token ID67
Feature activation-1.13e-01

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.015
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.013
osit-0.013
 supervision-0.013
Token
Token ID198
Feature activation+3.93e-02

Pos logit contributions
blance+0.033
uments+0.031
arthed+0.031
ondon+0.029
nesota+0.028
Neg logit contributions
ogens-0.028
 Debor-0.026
BUR-0.026
osit-0.025
 supervision-0.025
Token
Token ID198
Feature activation+2.33e-02

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.014
nesota+0.013
Neg logit contributions
ogens-0.011
 Debor-0.011
BUR-0.010
osit-0.010
 supervision-0.010
Token1992
Token ID23847
Feature activation-1.25e-01

Pos logit contributions
blance+0.008
uments+0.007
arthed+0.007
ondon+0.007
nesota+0.006
Neg logit contributions
ogens-0.008
 Debor-0.008
BUR-0.008
osit-0.008
 supervision-0.007
Token Jerry
Token ID13075
Feature activation+1.15e-01

Pos logit contributions
ogens+0.036
 Debor+0.033
BUR+0.032
osit+0.031
 supervision+0.030
Neg logit contributions
blance-0.050
uments-0.047
arthed-0.046
ondon-0.044
nesota-0.042
Token Se
Token ID1001
Feature activation-1.83e-01

Pos logit contributions
blance+0.043
uments+0.040
arthed+0.040
ondon+0.038
nesota+0.036
Neg logit contributions
ogens-0.035
 Debor-0.033
BUR-0.032
osit-0.031
iated-0.031
Tokeninfeld
Token ID47187
Feature activation+7.27e-01

Pos logit contributions
ogens+0.089
 Debor+0.085
BUR+0.084
osit+0.082
iated+0.081
Neg logit contributions
blance-0.036
uments-0.031
arthed-0.031
ondon-0.027
nesota-0.025
Token 1993
Token ID9656
Feature activation-9.52e-02

Pos logit contributions
blance+0.256
uments+0.241
arthed+0.238
ondon+0.226
nesota+0.213
Neg logit contributions
ogens-0.238
 Debor-0.223
BUR-0.217
osit-0.213
 supervision-0.207
Token Ted
Token ID11396
Feature activation-2.60e-01

Pos logit contributions
ogens+0.028
 Debor+0.026
BUR+0.025
osit+0.025
 supervision+0.024
Neg logit contributions
blance-0.037
uments-0.035
arthed-0.034
ondon-0.033
nesota-0.031
Token D
Token ID360
Feature activation+1.06e-01

Pos logit contributions
ogens+0.083
 Debor+0.079
BUR+0.076
osit+0.074
iated+0.073
Neg logit contributions
blance-0.095
uments-0.088
arthed-0.087
ondon-0.083
nesota-0.079
Tokenanson
Token ID23103
Feature activation-1.12e-02

Pos logit contributions
blance+0.037
uments+0.035
arthed+0.034
ondon+0.033
nesota+0.031
Neg logit contributions
ogens-0.035
 Debor-0.033
BUR-0.032
osit-0.031
 supervision-0.031
Token
Token ID198
Feature activation+1.02e-02

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.004
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
Token
Token ID447
Feature activation+2.03e-03

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.004
 supervision-0.004
Token
Token ID251
Feature activation-6.25e-03

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token said
Token ID531
Feature activation-2.52e-02

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token Owen
Token ID22605
Feature activation+1.52e-01

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.010
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.008
Token Do
Token ID2141
Feature activation+8.79e-02

Pos logit contributions
blance+0.056
uments+0.052
arthed+0.052
ondon+0.049
nesota+0.047
Neg logit contributions
ogens-0.048
 Debor-0.045
BUR-0.044
osit-0.043
 supervision-0.042
Tokenherty
Token ID29029
Feature activation+8.96e-01

Pos logit contributions
blance+0.021
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.016
Neg logit contributions
ogens-0.039
 Debor-0.037
BUR-0.036
osit-0.035
 supervision-0.035
Token,
Token ID11
Feature activation+2.12e-02

Pos logit contributions
blance+0.341
uments+0.321
arthed+0.317
ondon+0.302
nesota+0.287
Neg logit contributions
ogens-0.270
 Debor-0.251
BUR-0.244
osit-0.237
 supervision-0.233
Token climate
Token ID4258
Feature activation-1.53e-01

Pos logit contributions
blance+0.008
uments+0.008
arthed+0.007
ondon+0.007
nesota+0.007
Neg logit contributions
ogens-0.006
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token model
Token ID2746
Feature activation+1.68e-01

Pos logit contributions
ogens+0.046
 Debor+0.042
BUR+0.041
osit+0.040
 supervision+0.039
Neg logit contributions
blance-0.059
uments-0.055
arthed-0.055
ondon-0.052
nesota-0.050
Tokener
Token ID263
Feature activation+1.43e-01

Pos logit contributions
blance+0.058
uments+0.054
arthed+0.053
ondon+0.051
nesota+0.048
Neg logit contributions
ogens-0.057
 Debor-0.053
BUR-0.052
osit-0.051
 supervision-0.050
Token and
Token ID290
Feature activation+2.32e-02

Pos logit contributions
blance+0.055
uments+0.052
arthed+0.051
ondon+0.049
nesota+0.046
Neg logit contributions
ogens-0.042
 Debor-0.040
BUR-0.038
osit-0.037
 supervision-0.037
Token,
Token ID11
Feature activation+6.51e-02

Pos logit contributions
blance+0.139
uments+0.131
arthed+0.129
ondon+0.123
nesota+0.117
Neg logit contributions
ogens-0.110
 Debor-0.102
BUR-0.100
osit-0.097
 supervision-0.095
Token Gand
Token ID17727
Feature activation-7.29e-03

Pos logit contributions
blance+0.023
uments+0.021
arthed+0.021
ondon+0.020
nesota+0.019
Neg logit contributions
ogens-0.022
 Debor-0.020
BUR-0.020
osit-0.019
 supervision-0.019
Tokenhin
Token ID20079
Feature activation+3.04e-01

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.003
iated+0.003
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.001
Tokenagar
Token ID32452
Feature activation-3.23e-01

Pos logit contributions
blance+0.161
uments+0.155
arthed+0.154
ondon+0.149
nesota+0.143
Neg logit contributions
ogens-0.045
 Debor-0.039
BUR-0.037
osit-0.034
 supervision-0.033
Token,
Token ID11
Feature activation+6.48e-02

Pos logit contributions
ogens+0.097
 Debor+0.090
BUR+0.088
osit+0.086
 supervision+0.084
Neg logit contributions
blance-0.123
uments-0.116
arthed-0.114
ondon-0.109
nesota-0.104
Token Gujarat
Token ID30311
Feature activation+6.25e-01

Pos logit contributions
blance+0.020
uments+0.019
arthed+0.019
ondon+0.017
nesota+0.016
Neg logit contributions
ogens-0.024
 Debor-0.023
BUR-0.022
osit-0.022
 supervision-0.021
Token 38
Token ID4353
Feature activation+1.74e-02

Pos logit contributions
blance+0.227
uments+0.212
arthed+0.210
ondon+0.200
nesota+0.190
Neg logit contributions
ogens-0.200
 Debor-0.187
BUR-0.183
osit-0.178
 supervision-0.174
Token2020
Token ID42334
Feature activation+5.79e-01

Pos logit contributions
blance+0.006
uments+0.006
arthed+0.006
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.006
 Debor-0.005
BUR-0.005
osit-0.005
iated-0.005
Token,
Token ID11
Feature activation+6.32e-02

Pos logit contributions
blance+0.214
uments+0.202
arthed+0.199
ondon+0.190
nesota+0.180
Neg logit contributions
ogens-0.180
 Debor-0.168
BUR-0.163
osit-0.159
 supervision-0.156
Token India
Token ID3794
Feature activation+6.63e-02

Pos logit contributions
blance+0.025
uments+0.023
arthed+0.023
ondon+0.022
nesota+0.021
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.016
osit-0.016
 supervision-0.016
Token
Token ID198
Feature activation+3.32e-02

Pos logit contributions
blance+0.026
uments+0.025
arthed+0.024
ondon+0.023
nesota+0.022
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.017
osit-0.017
 supervision-0.016
Token)
Token ID8
Feature activation-5.49e-03

Pos logit contributions
blance+0.041
uments+0.039
arthed+0.038
ondon+0.037
nesota+0.035
Neg logit contributions
ogens-0.035
 Debor-0.032
BUR-0.032
osit-0.031
 supervision-0.030
Token -
Token ID532
Feature activation-7.03e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token Latin
Token ID9133
Feature activation+3.41e-01

Pos logit contributions
ogens+0.022
 Debor+0.021
BUR+0.020
osit+0.019
 supervision+0.019
Neg logit contributions
blance-0.026
uments-0.024
arthed-0.024
ondon-0.023
nesota-0.022
Token American
Token ID1605
Feature activation-2.91e-02

Pos logit contributions
blance+0.145
uments+0.138
arthed+0.137
ondon+0.131
nesota+0.125
Neg logit contributions
ogens-0.087
 Debor-0.080
BUR-0.077
osit-0.075
iated-0.072
Token and
Token ID290
Feature activation-2.60e-02

Pos logit contributions
ogens+0.007
 Debor+0.007
BUR+0.007
osit+0.006
iated+0.006
Neg logit contributions
blance-0.012
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
Token Caribbean
Token ID18020
Feature activation+7.10e-01

Pos logit contributions
ogens+0.011
 Debor+0.011
BUR+0.010
osit+0.010
 supervision+0.010
Neg logit contributions
blance-0.007
uments-0.006
arthed-0.006
ondon-0.005
nesota-0.005
Token leaders
Token ID2766
Feature activation-1.39e-01

Pos logit contributions
blance+0.293
uments+0.278
arthed+0.275
ondon+0.264
nesota+0.251
Neg logit contributions
ogens-0.190
 Debor-0.174
BUR-0.169
osit-0.164
iated-0.159
Token converge
Token ID47873
Feature activation-2.50e-01

Pos logit contributions
ogens+0.040
 Debor+0.037
BUR+0.036
osit+0.035
 supervision+0.034
Neg logit contributions
blance-0.054
uments-0.051
arthed-0.051
ondon-0.048
nesota-0.046
Token on
Token ID319
Feature activation-4.02e-03

Pos logit contributions
ogens+0.077
 Debor+0.072
BUR+0.070
osit+0.068
 supervision+0.067
Neg logit contributions
blance-0.093
uments-0.088
arthed-0.087
ondon-0.082
nesota-0.079
Token Cuba
Token ID14159
Feature activation-2.66e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token this
Token ID428
Feature activation+4.45e-03

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.010
uments-0.010
arthed-0.009
ondon-0.009
nesota-0.009
Token Dev
Token ID6245
Feature activation+3.63e-01

Pos logit contributions
blance+0.025
uments+0.023
arthed+0.023
ondon+0.022
nesota+0.021
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.018
osit-0.017
 supervision-0.017
Tokenial
Token ID498
Feature activation+3.49e-02

Pos logit contributions
blance+0.159
arthed+0.150
uments+0.150
ondon+0.143
nesota+0.137
Neg logit contributions
ogens-0.089
 Debor-0.080
BUR-0.078
osit-0.076
iated-0.075
Tokenets
Token ID1039
Feature activation+2.98e-01

Pos logit contributions
blance+0.011
uments+0.010
arthed+0.010
ondon+0.010
nesota+0.009
Neg logit contributions
ogens-0.013
 Debor-0.012
BUR-0.012
osit-0.011
iated-0.011
Token
Token ID447
Feature activation-5.89e-03

Pos logit contributions
blance+0.118
uments+0.112
arthed+0.111
ondon+0.106
nesota+0.101
Neg logit contributions
ogens-0.085
 Debor-0.079
BUR-0.076
osit-0.074
 supervision-0.072
Token
Token ID247
Feature activation+6.47e-03

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token st
Token ID336
Feature activation+1.03e-01

Pos logit contributions
blance+0.003
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Tokenup
Token ID929
Feature activation-3.65e-01

Pos logit contributions
blance+0.035
uments+0.033
arthed+0.032
ondon+0.030
nesota+0.029
Neg logit contributions
ogens-0.036
 Debor-0.034
BUR-0.033
osit-0.032
 supervision-0.031
Tokenend
Token ID437
Feature activation+1.76e-01

Pos logit contributions
ogens+0.141
 Debor+0.133
BUR+0.130
osit+0.128
 supervision+0.125
Neg logit contributions
blance-0.108
uments-0.100
arthed-0.099
ondon-0.092
nesota-0.087
Tokenous
Token ID516
Feature activation-3.85e-01

Pos logit contributions
blance+0.092
uments+0.088
arthed+0.087
ondon+0.084
nesota+0.082
Neg logit contributions
ogens-0.028
 Debor-0.024
BUR-0.023
osit-0.021
 supervision-0.020
Token imaging
Token ID19560
Feature activation-6.35e-02

Pos logit contributions
ogens+0.108
 Debor+0.100
BUR+0.097
osit+0.094
 supervision+0.092
Neg logit contributions
blance-0.154
uments-0.146
arthed-0.145
ondon-0.138
nesota-0.132
Token,
Token ID11
Feature activation+1.37e-02

Pos logit contributions
ogens+0.018
 Debor+0.017
BUR+0.017
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.025
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.021
Token 9
Token ID860
Feature activation-1.43e-01

Pos logit contributions
ogens+0.003
 Debor+0.003
BUR+0.003
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.002
Token 2007
Token ID4343
Feature activation+1.52e-02

Pos logit contributions
ogens+0.053
 Debor+0.050
BUR+0.049
osit+0.048
 supervision+0.047
Neg logit contributions
blance-0.045
uments-0.042
arthed-0.041
ondon-0.039
nesota-0.036
Token 6
Token ID718
Feature activation-7.40e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.004
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.005
 supervision-0.004
Token 0
Token ID657
Feature activation-1.80e-01

Pos logit contributions
ogens+0.024
 Debor+0.023
BUR+0.022
osit+0.022
 supervision+0.021
Neg logit contributions
blance-0.026
uments-0.024
arthed-0.024
ondon-0.023
nesota-0.022
Token 2008
Token ID3648
Feature activation-3.07e-02

Pos logit contributions
ogens+0.065
 Debor+0.061
BUR+0.060
osit+0.058
 supervision+0.057
Neg logit contributions
blance-0.058
uments-0.054
arthed-0.053
ondon-0.050
nesota-0.047
Token 15
Token ID1315
Feature activation+5.91e-02

Pos logit contributions
ogens+0.010
 Debor+0.010
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.010
ondon-0.009
nesota-0.009
Token 4
Token ID604
Feature activation-7.14e-02

Pos logit contributions
blance+0.021
uments+0.019
arthed+0.019
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.020
 Debor-0.018
BUR-0.018
osit-0.017
 supervision-0.017
Token 2009
Token ID3717
Feature activation-7.27e-02

Pos logit contributions
ogens+0.025
 Debor+0.024
BUR+0.023
osit+0.023
 supervision+0.022
Neg logit contributions
blance-0.023
uments-0.022
arthed-0.021
ondon-0.020
nesota-0.019
Token 10
Token ID838
Feature activation+1.22e-01

Pos logit contributions
ogens+0.024
 Debor+0.023
BUR+0.022
osit+0.022
 supervision+0.021
Neg logit contributions
blance-0.026
uments-0.024
arthed-0.024
ondon-0.022
nesota-0.021
Token 2
Token ID362
Feature activation-2.60e-02

Pos logit contributions
blance+0.043
uments+0.040
arthed+0.040
ondon+0.038
nesota+0.036
Neg logit contributions
ogens-0.040
 Debor-0.038
BUR-0.037
osit-0.036
 supervision-0.035
Token 2010
Token ID3050
Feature activation+4.41e-02

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.008
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.006
Token we
Token ID356
Feature activation+4.95e-02

Pos logit contributions
blance+0.078
uments+0.073
arthed+0.073
ondon+0.069
nesota+0.066
Neg logit contributions
ogens-0.055
 Debor-0.052
BUR-0.050
osit-0.049
 supervision-0.048
Token've
Token ID1053
Feature activation+5.06e-02

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.015
Neg logit contributions
ogens-0.016
 Debor-0.014
BUR-0.014
osit-0.014
iated-0.013
Token all
Token ID477
Feature activation-2.89e-02

Pos logit contributions
blance+0.019
uments+0.018
arthed+0.018
ondon+0.017
nesota+0.016
Neg logit contributions
ogens-0.015
 Debor-0.014
BUR-0.014
osit-0.014
 supervision-0.013
Token agreed
Token ID4987
Feature activation-6.40e-02

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
iated+0.008
Neg logit contributions
blance-0.011
uments-0.010
arthed-0.010
ondon-0.010
nesota-0.009
Token that
Token ID326
Feature activation-1.95e-02

Pos logit contributions
ogens+0.019
 Debor+0.018
BUR+0.018
osit+0.017
 supervision+0.017
Neg logit contributions
blance-0.024
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.020
Token maybe
Token ID3863
Feature activation+1.43e-01

Pos logit contributions
ogens+0.006
 Debor+0.005
BUR+0.005
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.006
Token that
Token ID326
Feature activation-1.95e-02

Pos logit contributions
blance+0.055
uments+0.052
arthed+0.051
ondon+0.049
nesota+0.046
Neg logit contributions
ogens-0.042
 Debor-0.040
BUR-0.039
osit-0.037
 supervision-0.037
Token episode
Token ID4471
Feature activation+4.56e-02

Pos logit contributions
ogens+0.006
 Debor+0.005
BUR+0.005
osit+0.005
 supervision+0.005
Neg logit contributions
blance-0.007
uments-0.007
arthed-0.007
ondon-0.007
nesota-0.006
Token was
Token ID373
Feature activation-3.43e-02

Pos logit contributions
blance+0.017
uments+0.016
arthed+0.016
ondon+0.015
nesota+0.014
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.013
osit-0.013
 supervision-0.012
Token a
Token ID257
Feature activation-5.12e-03

Pos logit contributions
ogens+0.010
 Debor+0.010
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.012
nesota-0.011
Token little
Token ID1310
Feature activation-4.93e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token if
Token ID611
Feature activation+1.37e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token it
Token ID340
Feature activation-2.27e-03

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.004
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token's
Token ID338
Feature activation-2.34e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token answered
Token ID9373
Feature activation-3.09e-01

Pos logit contributions
ogens+0.007
 Debor+0.007
BUR+0.007
osit+0.006
 supervision+0.006
Neg logit contributions
blance-0.009
uments-0.008
arthed-0.008
ondon-0.008
nesota-0.007
Token
Token ID851
Feature activation-1.43e-01

Pos logit contributions
ogens+0.093
 Debor+0.087
BUR+0.084
osit+0.082
 supervision+0.080
Neg logit contributions
blance-0.118
uments-0.111
arthed-0.110
ondon-0.104
nesota-0.100
Token Golden
Token ID8407
Feature activation+9.17e-02

Pos logit contributions
ogens+0.043
 Debor+0.041
BUR+0.039
osit+0.038
 supervision+0.038
Neg logit contributions
blance-0.054
uments-0.051
arthed-0.050
ondon-0.048
nesota-0.045
TokenState
Token ID9012
Feature activation-2.41e-03

Pos logit contributions
blance+0.031
uments+0.029
arthed+0.029
ondon+0.027
nesota+0.025
Neg logit contributions
ogens-0.032
 Debor-0.030
BUR-0.029
osit-0.028
 supervision-0.028
TokenWar
Token ID13195
Feature activation-1.24e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Tokenriors
Token ID8657
Feature activation+7.11e-02

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.004
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token (@
Token ID4275
Feature activation-2.65e-01

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.027
nesota+0.026
Neg logit contributions
ogens-0.019
 Debor-0.017
BUR-0.017
osit-0.016
 supervision-0.016
Tokenwar
Token ID5767
Feature activation+2.75e-02

Pos logit contributions
ogens+0.083
 Debor+0.076
BUR+0.075
osit+0.073
iated+0.071
Neg logit contributions
blance-0.098
uments-0.092
arthed-0.091
ondon-0.087
nesota-0.083
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
ogens+0.043
 Debor+0.040
BUR+0.039
osit+0.038
iated+0.037
Neg logit contributions
blance-0.055
uments-0.052
arthed-0.051
ondon-0.049
nesota-0.046
Token Sun
Token ID3825
Feature activation+9.85e-02

Pos logit contributions
ogens+0.010
 Debor+0.010
BUR+0.009
osit+0.009
 supervision+0.009
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Tokenan
Token ID272
Feature activation+2.18e-01

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.037
 Debor-0.035
BUR-0.034
osit-0.033
iated-0.033
Token Abu
Token ID13098
Feature activation-2.40e-01

Pos logit contributions
blance+0.084
uments+0.079
arthed+0.078
ondon+0.074
nesota+0.071
Neg logit contributions
ogens-0.065
 Debor-0.061
BUR-0.059
osit-0.057
 supervision-0.057
Token Daw
Token ID17552
Feature activation+5.03e-02

Pos logit contributions
ogens+0.076
 Debor+0.071
BUR+0.069
osit+0.067
 supervision+0.066
Neg logit contributions
blance-0.088
uments-0.082
arthed-0.082
ondon-0.078
nesota-0.074
Tokenud
Token ID463
Feature activation+7.15e-02

Pos logit contributions
blance+0.017
uments+0.016
arthed+0.016
ondon+0.015
nesota+0.014
Neg logit contributions
ogens-0.017
 Debor-0.016
BUR-0.015
osit-0.015
 supervision-0.015
Token 14
Token ID1478
Feature activation-1.02e-01

Pos logit contributions
blance+0.028
uments+0.027
arthed+0.026
ondon+0.025
nesota+0.024
Neg logit contributions
ogens-0.020
 Debor-0.019
BUR-0.018
osit-0.018
 supervision-0.018
Token:
Token ID25
Feature activation+1.54e-02

Pos logit contributions
ogens+0.031
 Debor+0.029
BUR+0.028
osit+0.027
 supervision+0.027
Neg logit contributions
blance-0.038
uments-0.036
arthed-0.036
ondon-0.034
nesota-0.032
Token26
Token ID2075
Feature activation+2.09e-01

Pos logit contributions
blance+0.006
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.005
 Debor-0.005
BUR-0.005
osit-0.004
 supervision-0.004
Token65
Token ID2996
Feature activation+6.30e-02

Pos logit contributions
blance+0.082
uments+0.077
arthed+0.077
ondon+0.073
nesota+0.070
Neg logit contributions
ogens-0.060
 Debor-0.056
BUR-0.055
osit-0.053
 supervision-0.052
Token
Token ID198
Feature activation-1.25e-02

Pos logit contributions
blance+0.025
uments+0.023
arthed+0.023
ondon+0.022
nesota+0.021
Neg logit contributions
ogens-0.018
 Debor-0.017
BUR-0.016
osit-0.016
 supervision-0.016
Token
Token ID198
Feature activation+4.84e-02

Pos logit contributions
blance+0.017
uments+0.016
arthed+0.015
ondon+0.015
nesota+0.014
Neg logit contributions
ogens-0.012
 Debor-0.011
BUR-0.011
osit-0.011
 supervision-0.010
TokenLast
Token ID5956
Feature activation-1.61e-01

Pos logit contributions
blance+0.020
uments+0.018
arthed+0.018
ondon+0.018
nesota+0.017
Neg logit contributions
ogens-0.013
 Debor-0.012
BUR-0.012
osit-0.012
iated-0.011
Token year
Token ID614
Feature activation-5.45e-02

Pos logit contributions
ogens+0.047
 Debor+0.044
BUR+0.042
osit+0.041
 supervision+0.040
Neg logit contributions
blance-0.063
uments-0.060
arthed-0.059
ondon-0.056
nesota-0.053
Token at
Token ID379
Feature activation+2.76e-03

Pos logit contributions
ogens+0.016
 Debor+0.015
BUR+0.015
osit+0.014
 supervision+0.014
Neg logit contributions
blance-0.021
uments-0.020
arthed-0.020
ondon-0.019
nesota-0.018
Token this
Token ID428
Feature activation+4.63e-02

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Token time
Token ID640
Feature activation+8.51e-03

Pos logit contributions
blance+0.018
uments+0.017
arthed+0.017
ondon+0.016
nesota+0.015
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.012
osit-0.012
 supervision-0.012
Token,
Token ID11
Feature activation+6.44e-02

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token the
Token ID262
Feature activation+2.22e-02

Pos logit contributions
blance+0.024
uments+0.022
arthed+0.022
ondon+0.021
aiden+0.020
Neg logit contributions
ogens-0.020
 Debor-0.019
BUR-0.018
osit-0.018
 supervision-0.018
Token folks
Token ID7974
Feature activation+2.93e-01

Pos logit contributions
blance+0.008
uments+0.008
arthed+0.008
ondon+0.007
nesota+0.007
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token from
Token ID422
Feature activation+7.12e-03

Pos logit contributions
blance+0.111
uments+0.104
arthed+0.103
ondon+0.098
nesota+0.093
Neg logit contributions
ogens-0.089
 Debor-0.083
BUR-0.081
osit-0.078
 supervision-0.077
Token Boise
Token ID38830
Feature activation+1.74e-02

Pos logit contributions
blance+0.003
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token over
Token ID625
Feature activation-1.58e-01

Pos logit contributions
blance+0.052
uments+0.049
arthed+0.048
ondon+0.046
nesota+0.044
Neg logit contributions
ogens-0.040
 Debor-0.037
BUR-0.036
osit-0.035
iated-0.034
Tokenstep
Token ID9662
Feature activation-3.90e-03

Pos logit contributions
ogens+0.047
 Debor+0.043
BUR+0.042
osit+0.041
 supervision+0.040
Neg logit contributions
blance-0.061
uments-0.057
arthed-0.057
ondon-0.054
nesota-0.052
Token the
Token ID262
Feature activation+1.03e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token bounds
Token ID22303
Feature activation-4.19e-01

Pos logit contributions
blance+0.004
uments+0.004
arthed+0.004
ondon+0.004
nesota+0.004
Neg logit contributions
ogens-0.003
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
Token in
Token ID287
Feature activation+1.39e-02

Pos logit contributions
ogens+0.129
 Debor+0.120
BUR+0.117
osit+0.113
iated+0.111
Neg logit contributions
blance-0.158
uments-0.149
arthed-0.146
ondon-0.140
nesota-0.132
Token peaceful
Token ID12309
Feature activation-3.81e-03

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.004
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token protests
Token ID8536
Feature activation+1.18e-01

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token?
Token ID30
Feature activation-1.49e-02

Pos logit contributions
blance+0.047
uments+0.044
arthed+0.044
ondon+0.041
nesota+0.040
Neg logit contributions
ogens-0.034
 Debor-0.032
BUR-0.031
osit-0.030
 supervision-0.029
Token
Token ID198
Feature activation+9.05e-03

Pos logit contributions
ogens+0.005
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token
Token ID198
Feature activation-1.31e-03

Pos logit contributions
blance+0.004
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.002
BUR-0.002
osit-0.002
 supervision-0.002
TokenWASHINGTON
Token ID21793
Feature activation+4.59e-01

Pos logit contributions
ogens+0.000
 Debor+0.000
BUR+0.000
osit+0.000
 supervision+0.000
Neg logit contributions
blance-0.001
uments-0.000
arthed-0.000
ondon-0.000
nesota-0.000
Tokenrea
Token ID21468
Feature activation-8.58e-02

Pos logit contributions
blance+0.042
uments+0.040
arthed+0.040
ondon+0.038
nesota+0.036
Neg logit contributions
ogens-0.026
 Debor-0.023
BUR-0.023
osit-0.022
iated-0.021
Token bought
Token ID5839
Feature activation+2.32e-01

Pos logit contributions
ogens+0.025
 Debor+0.023
BUR+0.022
osit+0.022
 supervision+0.021
Neg logit contributions
blance-0.034
uments-0.032
arthed-0.031
ondon-0.030
nesota-0.029
Token cocaine
Token ID15144
Feature activation+3.01e-01

Pos logit contributions
blance+0.084
uments+0.078
arthed+0.078
ondon+0.074
nesota+0.070
Neg logit contributions
ogens-0.074
 Debor-0.070
BUR-0.068
osit-0.066
 supervision-0.065
Token from
Token ID422
Feature activation-5.04e-03

Pos logit contributions
blance+0.115
uments+0.108
arthed+0.107
ondon+0.102
nesota+0.097
Neg logit contributions
ogens-0.091
 Debor-0.085
BUR-0.082
osit-0.080
 supervision-0.079
Token Gal
Token ID5027
Feature activation-4.14e-01

Pos logit contributions
ogens+0.002
 Debor+0.002
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Tokenar
Token ID283
Feature activation+3.30e-02

Pos logit contributions
ogens+0.152
 Debor+0.143
BUR+0.140
osit+0.137
iated+0.134
Neg logit contributions
blance-0.130
uments-0.121
arthed-0.120
ondon-0.112
nesota-0.106
Tokenza
Token ID4496
Feature activation-2.15e-01

Pos logit contributions
blance+0.015
uments+0.014
arthed+0.014
ondon+0.013
nesota+0.013
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.006
Token's
Token ID338
Feature activation-6.01e-02

Pos logit contributions
ogens+0.063
 Debor+0.058
BUR+0.056
osit+0.055
 supervision+0.054
Neg logit contributions
blance-0.085
uments-0.079
arthed-0.079
ondon-0.075
nesota-0.072
Token co
Token ID763
Feature activation-1.73e-01

Pos logit contributions
ogens+0.017
 Debor+0.015
BUR+0.015
osit+0.014
 supervision+0.014
Neg logit contributions
blance-0.024
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.021
Token-
Token ID12
Feature activation-3.66e-02

Pos logit contributions
ogens+0.049
 Debor+0.046
BUR+0.044
osit+0.043
 supervision+0.042
Neg logit contributions
blance-0.068
uments-0.065
arthed-0.064
ondon-0.061
nesota-0.058
Tokenworker
Token ID28816
Feature activation-1.95e-01

Pos logit contributions
ogens+0.009
 Debor+0.008
BUR+0.008
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.016
uments-0.015
arthed-0.015
ondon-0.014
nesota-0.014
Token.
Token ID13
Feature activation-2.38e-02

Pos logit contributions
ogens+0.051
 Debor+0.048
BUR+0.047
osit+0.045
iated+0.044
Neg logit contributions
blance-0.066
uments-0.062
arthed-0.062
ondon-0.059
nesota-0.056
Token However
Token ID2102
Feature activation-6.98e-04

Pos logit contributions
ogens+0.007
 Debor+0.007
BUR+0.007
osit+0.006
 supervision+0.006
Neg logit contributions
blance-0.009
uments-0.009
arthed-0.008
ondon-0.008
nesota-0.008
Token he
Token ID339
Feature activation-7.86e-02

Pos logit contributions
ogens+0.000
 Debor+0.000
BUR+0.000
osit+0.000
 supervision+0.000
Neg logit contributions
blance-0.000
uments-0.000
arthed-0.000
ondon-0.000
nesota-0.000
Token has
Token ID468
Feature activation-8.42e-03

Pos logit contributions
ogens+0.023
 Debor+0.022
BUR+0.021
osit+0.021
iated+0.020
Neg logit contributions
blance-0.030
uments-0.029
arthed-0.028
ondon-0.027
nesota-0.026
Token no
Token ID645
Feature activation-8.67e-02

Pos logit contributions
ogens+0.003
 Debor+0.002
BUR+0.002
osit+0.002
 supervision+0.002
Neg logit contributions
blance-0.003
uments-0.003
arthed-0.003
ondon-0.003
nesota-0.003
Token links
Token ID6117
Feature activation-4.79e-02

Pos logit contributions
ogens+0.026
 Debor+0.024
BUR+0.023
osit+0.022
 supervision+0.022
Neg logit contributions
blance-0.033
uments-0.032
arthed-0.031
ondon-0.030
nesota-0.028
Token with
Token ID351
Feature activation+2.47e-02

Pos logit contributions
ogens+0.016
 Debor+0.015
BUR+0.014
osit+0.014
 supervision+0.014
Neg logit contributions
blance-0.017
uments-0.016
arthed-0.016
ondon-0.015
nesota-0.014
Token Pakistan
Token ID7648
Feature activation+7.36e-02

Pos logit contributions
blance+0.010
uments+0.009
arthed+0.009
ondon+0.009
nesota+0.008
Neg logit contributions
ogens-0.007
 Debor-0.007
BUR-0.006
osit-0.006
 supervision-0.006
Token and
Token ID290
Feature activation-3.99e-02

Pos logit contributions
blance+0.030
uments+0.028
arthed+0.028
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.021
 Debor-0.019
BUR-0.019
osit-0.018
 supervision-0.018
Token worked
Token ID3111
Feature activation+1.37e-01

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.010
 supervision+0.010
Neg logit contributions
blance-0.015
uments-0.015
arthed-0.014
ondon-0.014
nesota-0.013
Token in
Token ID287
Feature activation-1.61e-02

Pos logit contributions
blance+0.053
uments+0.050
arthed+0.049
ondon+0.047
nesota+0.045
Neg logit contributions
ogens-0.040
 Debor-0.038
BUR-0.037
osit-0.036
 supervision-0.035
Token
Token ID198
Feature activation-3.29e-02

Pos logit contributions
ogens+0.018
 Debor+0.017
BUR+0.016
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.025
uments-0.023
arthed-0.023
ondon-0.022
nesota-0.021
Token"
Token ID1
Feature activation+2.37e-02

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.011
TokenSome
Token ID4366
Feature activation-6.77e-02

Pos logit contributions
blance+0.010
uments+0.009
arthed+0.009
ondon+0.009
nesota+0.008
Neg logit contributions
ogens-0.007
 Debor-0.006
BUR-0.006
osit-0.006
 supervision-0.006
Token may
Token ID743
Feature activation-1.50e-01

Pos logit contributions
ogens+0.019
 Debor+0.018
BUR+0.017
osit+0.017
 supervision+0.017
Neg logit contributions
blance-0.027
uments-0.025
arthed-0.025
ondon-0.024
nesota-0.023
Token qu
Token ID627
Feature activation-1.26e-02

Pos logit contributions
ogens+0.046
 Debor+0.043
BUR+0.042
osit+0.041
 supervision+0.040
Neg logit contributions
blance-0.056
uments-0.053
arthed-0.053
ondon-0.050
nesota-0.047
Tokenibble
Token ID43992
Feature activation-1.00e-01

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.003
osit+0.003
iated+0.003
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.004
ondon-0.004
nesota-0.004
Token that
Token ID326
Feature activation-6.65e-02

Pos logit contributions
ogens+0.032
 Debor+0.030
BUR+0.029
osit+0.028
 supervision+0.027
Neg logit contributions
blance-0.037
uments-0.035
arthed-0.034
ondon-0.033
nesota-0.031
Token this
Token ID428
Feature activation-4.72e-02

Pos logit contributions
ogens+0.020
 Debor+0.019
BUR+0.018
osit+0.018
 supervision+0.017
Neg logit contributions
blance-0.025
uments-0.024
arthed-0.024
ondon-0.023
nesota-0.021
Token doesn
Token ID1595
Feature activation+5.11e-02

Pos logit contributions
ogens+0.014
 Debor+0.013
BUR+0.012
osit+0.012
 supervision+0.012
Neg logit contributions
blance-0.019
uments-0.018
arthed-0.017
ondon-0.017
nesota-0.016
Token't
Token ID470
Feature activation-1.03e-01

Pos logit contributions
blance+0.021
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.014
 Debor-0.013
BUR-0.012
osit-0.012
 supervision-0.012
Token take
Token ID1011
Feature activation-1.19e-01

Pos logit contributions
ogens+0.030
 Debor+0.028
BUR+0.028
osit+0.027
 supervision+0.026
Neg logit contributions
blance-0.040
arthed-0.038
uments-0.038
ondon-0.036
nesota-0.034
Tokenlez
Token ID36858
Feature activation-2.22e-01

Pos logit contributions
blance+0.002
uments+0.002
arthed+0.002
ondon+0.002
nesota+0.002
Neg logit contributions
ogens-0.002
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Tokenal
Token ID282
Feature activation+1.26e-01

Pos logit contributions
ogens+0.072
 Debor+0.067
BUR+0.065
osit+0.064
iated+0.063
Neg logit contributions
blance-0.079
uments-0.074
arthed-0.074
ondon-0.069
nesota-0.065
Token slide
Token ID10649
Feature activation-3.57e-02

Pos logit contributions
blance+0.050
uments+0.047
arthed+0.046
ondon+0.044
nesota+0.042
Neg logit contributions
ogens-0.036
 Debor-0.034
BUR-0.033
osit-0.032
 supervision-0.031
Token on
Token ID319
Feature activation-3.98e-02

Pos logit contributions
ogens+0.011
 Debor+0.010
BUR+0.010
osit+0.010
 supervision+0.009
Neg logit contributions
blance-0.013
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.011
Token the
Token ID262
Feature activation-3.41e-02

Pos logit contributions
ogens+0.012
 Debor+0.012
BUR+0.011
osit+0.011
 supervision+0.011
Neg logit contributions
blance-0.015
uments-0.014
arthed-0.014
ondon-0.013
nesota-0.012
Token Cait
Token ID34118
Feature activation-5.55e-01

Pos logit contributions
ogens+0.010
 Debor+0.009
BUR+0.009
osit+0.008
 supervision+0.008
Neg logit contributions
blance-0.014
uments-0.013
arthed-0.013
ondon-0.012
nesota-0.012
Tokenlyn
Token ID6213
Feature activation+4.32e-01

Pos logit contributions
ogens+0.260
 Debor+0.248
BUR+0.243
osit+0.240
 supervision+0.236
Neg logit contributions
blance-0.120
arthed-0.106
uments-0.106
ondon-0.095
nesota-0.088
Token Jenner
Token ID39760
Feature activation-6.36e-02

Pos logit contributions
blance+0.164
uments+0.154
arthed+0.153
ondon+0.145
nesota+0.139
Neg logit contributions
ogens-0.130
 Debor-0.122
BUR-0.118
osit-0.115
 supervision-0.113
Token comparisons
Token ID17909
Feature activation+5.62e-02

Pos logit contributions
ogens+0.018
 Debor+0.016
BUR+0.016
osit+0.015
 supervision+0.015
Neg logit contributions
blance-0.026
uments-0.024
arthed-0.024
ondon-0.023
nesota-0.022
Token
Token ID960
Feature activation+8.76e-03

Pos logit contributions
blance+0.021
uments+0.020
arthed+0.020
ondon+0.019
nesota+0.018
Neg logit contributions
ogens-0.017
 Debor-0.016
BUR-0.015
osit-0.015
 supervision-0.015
Tokenand
Token ID392
Feature activation+1.77e-01

Pos logit contributions
blance+0.003
uments+0.003
arthed+0.003
ondon+0.003
nesota+0.003
Neg logit contributions
ogens-0.003
 Debor-0.003
BUR-0.003
osit-0.003
 supervision-0.003
Token of
Token ID286
Feature activation-2.53e-02

Pos logit contributions
ogens+0.056
 Debor+0.052
BUR+0.050
osit+0.049
 supervision+0.048
Neg logit contributions
blance-0.072
uments-0.068
arthed-0.067
ondon-0.064
nesota-0.061
Token animal
Token ID5044
Feature activation+6.16e-02

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.009
uments-0.009
arthed-0.009
ondon-0.008
nesota-0.008
Token care
Token ID1337
Feature activation-2.57e-01

Pos logit contributions
blance+0.028
uments+0.027
arthed+0.027
ondon+0.026
nesota+0.025
Neg logit contributions
ogens-0.014
 Debor-0.012
BUR-0.012
osit-0.012
 supervision-0.011
Token.
Token ID13
Feature activation-5.57e-02

Pos logit contributions
ogens+0.076
 Debor+0.070
BUR+0.068
osit+0.066
 supervision+0.065
Neg logit contributions
blance-0.100
uments-0.094
arthed-0.093
ondon-0.088
nesota-0.084
Token Experimental
Token ID32286
Feature activation-1.97e-01

Pos logit contributions
ogens+0.018
 Debor+0.017
BUR+0.017
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.020
uments-0.019
arthed-0.018
ondon-0.018
aiden-0.017
Token procedures
Token ID9021
Feature activation-4.87e-01

Pos logit contributions
ogens+0.049
 Debor+0.045
BUR+0.044
osit+0.042
 supervision+0.041
Neg logit contributions
blance-0.085
uments-0.081
arthed-0.080
ondon-0.077
nesota-0.074
Token were
Token ID547
Feature activation+1.47e-02

Pos logit contributions
ogens+0.156
 Debor+0.146
BUR+0.140
osit+0.138
 supervision+0.137
Neg logit contributions
blance-0.178
uments-0.166
arthed-0.165
ondon-0.156
nesota-0.148
Token performed
Token ID6157
Feature activation-7.73e-02

Pos logit contributions
blance+0.006
uments+0.005
arthed+0.005
ondon+0.005
nesota+0.005
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.004
 supervision-0.004
Token in
Token ID287
Feature activation-2.77e-02

Pos logit contributions
ogens+0.025
 Debor+0.023
BUR+0.022
 supervision+0.022
osit+0.022
Neg logit contributions
blance-0.028
uments-0.026
arthed-0.026
ondon-0.025
nesota-0.023
Token accordance
Token ID10213
Feature activation-1.68e-01

Pos logit contributions
ogens+0.008
 Debor+0.007
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.011
uments-0.011
arthed-0.011
ondon-0.010
nesota-0.010
Token with
Token ID351
Feature activation+4.49e-02

Pos logit contributions
ogens+0.058
 Debor+0.055
BUR+0.053
osit+0.052
 supervision+0.052
Neg logit contributions
blance-0.057
uments-0.053
arthed-0.052
ondon-0.049
nesota-0.047
Token is
Token ID318
Feature activation-1.58e-02

Pos logit contributions
blance+0.162
uments+0.152
arthed+0.151
ondon+0.143
nesota+0.137
Neg logit contributions
ogens-0.132
 Debor-0.123
BUR-0.120
osit-0.116
 supervision-0.114
Token composed
Token ID13160
Feature activation-4.58e-01

Pos logit contributions
ogens+0.005
 Debor+0.005
BUR+0.005
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token of
Token ID286
Feature activation-3.45e-03

Pos logit contributions
ogens+0.140
 Debor+0.131
BUR+0.128
osit+0.124
 supervision+0.121
Neg logit contributions
blance-0.172
uments-0.162
arthed-0.159
ondon-0.152
nesota-0.144
Token the
Token ID262
Feature activation-2.62e-02

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.001
uments-0.001
arthed-0.001
ondon-0.001
nesota-0.001
Token Un
Token ID791
Feature activation-1.56e-01

Pos logit contributions
ogens+0.008
 Debor+0.008
BUR+0.007
osit+0.007
 supervision+0.007
Neg logit contributions
blance-0.010
uments-0.009
arthed-0.009
ondon-0.009
nesota-0.008
Tokenlocked
Token ID24162
Feature activation-5.34e-01

Pos logit contributions
ogens+0.029
 Debor+0.026
BUR+0.024
osit+0.023
 supervision+0.022
Neg logit contributions
blance-0.078
uments-0.074
arthed-0.073
ondon-0.071
nesota-0.068
Token BIOS
Token ID27553
Feature activation+7.28e-02

Pos logit contributions
ogens+0.172
 Debor+0.161
BUR+0.157
osit+0.153
 supervision+0.150
Neg logit contributions
blance-0.192
uments-0.180
arthed-0.178
ondon-0.169
nesota-0.161
Token,
Token ID11
Feature activation-1.34e-02

Pos logit contributions
blance+0.028
uments+0.026
arthed+0.026
ondon+0.025
nesota+0.024
Neg logit contributions
ogens-0.022
 Debor-0.020
BUR-0.019
osit-0.019
 supervision-0.019
Token Digital
Token ID10231
Feature activation-4.11e-02

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.005
uments-0.004
arthed-0.004
ondon-0.004
nesota-0.004
TokenP
Token ID47
Feature activation+1.58e-01

Pos logit contributions
ogens+0.015
 Debor+0.015
BUR+0.014
osit+0.014
 supervision+0.014
Neg logit contributions
blance-0.013
uments-0.012
arthed-0.012
ondon-0.011
nesota-0.010
TokenWM
Token ID22117
Feature activation-1.19e-01

Pos logit contributions
blance+0.066
uments+0.062
arthed+0.062
ondon+0.059
nesota+0.056
Neg logit contributions
ogens-0.042
 Debor-0.038
BUR-0.038
osit-0.036
 supervision-0.035
Token,
Token ID11
Feature activation+2.57e-02

Pos logit contributions
ogens+0.028
 Debor+0.026
BUR+0.025
osit+0.024
 supervision+0.024
Neg logit contributions
blance-0.036
uments-0.034
arthed-0.033
ondon-0.032
nesota-0.030
Token drew
Token ID9859
Feature activation+1.44e-01

Pos logit contributions
blance+0.010
uments+0.009
arthed+0.009
ondon+0.009
nesota+0.008
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Token just
Token ID655
Feature activation-3.86e-02

Pos logit contributions
blance+0.057
uments+0.054
arthed+0.054
ondon+0.051
nesota+0.049
Neg logit contributions
ogens-0.041
 Debor-0.038
BUR-0.037
osit-0.036
 supervision-0.035
Token eight
Token ID3624
Feature activation+1.90e-01

Pos logit contributions
ogens+0.012
 Debor+0.011
BUR+0.011
osit+0.011
 supervision+0.010
Neg logit contributions
blance-0.014
uments-0.014
arthed-0.013
ondon-0.013
nesota-0.012
Token b
Token ID275
Feature activation+1.36e-01

Pos logit contributions
blance+0.074
uments+0.070
arthed+0.069
ondon+0.066
nesota+0.063
Neg logit contributions
ogens-0.055
 Debor-0.051
BUR-0.049
osit-0.048
iated-0.047
Tokenidd
Token ID1638
Feature activation-6.35e-01

Pos logit contributions
blance+0.069
uments+0.066
arthed+0.066
ondon+0.064
nesota+0.061
Neg logit contributions
ogens-0.023
 Debor-0.021
BUR-0.020
osit-0.019
 supervision-0.018
Tokeners
Token ID364
Feature activation+7.20e-02

Pos logit contributions
ogens+0.200
 Debor+0.184
BUR+0.180
osit+0.179
iated+0.173
Neg logit contributions
blance-0.236
arthed-0.220
uments-0.217
ondon-0.205
nesota-0.196
Token when
Token ID618
Feature activation+1.09e-01

Pos logit contributions
blance+0.028
uments+0.026
arthed+0.026
ondon+0.025
nesota+0.023
Neg logit contributions
ogens-0.021
 Debor-0.020
BUR-0.019
osit-0.019
 supervision-0.018
Token auction
Token ID14389
Feature activation-5.36e-03

Pos logit contributions
blance+0.042
uments+0.040
arthed+0.039
ondon+0.037
nesota+0.035
Neg logit contributions
ogens-0.032
 Debor-0.030
BUR-0.029
osit-0.028
 supervision-0.028
Tokened
Token ID276
Feature activation-2.93e-01

Pos logit contributions
ogens+0.001
 Debor+0.001
BUR+0.001
osit+0.001
 supervision+0.001
Neg logit contributions
blance-0.002
uments-0.002
arthed-0.002
ondon-0.002
nesota-0.002
Token by
Token ID416
Feature activation+8.09e-02

Pos logit contributions
ogens+0.086
 Debor+0.081
BUR+0.078
osit+0.075
 supervision+0.075
Neg logit contributions
blance-0.114
uments-0.107
arthed-0.106
ondon-0.101
nesota-0.096
Tokenced
Token ID771
Feature activation+2.51e-02

Pos logit contributions
blance+0.054
uments+0.050
arthed+0.049
ondon+0.047
nesota+0.044
Neg logit contributions
ogens-0.055
 Debor-0.052
BUR-0.051
osit-0.049
 supervision-0.049
Token:
Token ID25
Feature activation+1.28e-02

Pos logit contributions
blance+0.009
uments+0.009
arthed+0.009
ondon+0.008
nesota+0.008
Neg logit contributions
ogens-0.008
 Debor-0.007
BUR-0.007
osit-0.007
 supervision-0.007
Token
Token ID198
Feature activation-1.34e-02

Pos logit contributions
blance+0.005
uments+0.005
arthed+0.004
ondon+0.004
nesota+0.004
Neg logit contributions
ogens-0.004
 Debor-0.004
BUR-0.004
osit-0.003
 supervision-0.003
Token
Token ID198
Feature activation+3.93e-03

Pos logit contributions
ogens+0.004
 Debor+0.004
BUR+0.004
osit+0.003
 supervision+0.003
Neg logit contributions
blance-0.005
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.004
TokenS
Token ID50
Feature activation-5.82e-02

Pos logit contributions
blance+0.001
uments+0.001
arthed+0.001
ondon+0.001
nesota+0.001
Neg logit contributions
ogens-0.001
 Debor-0.001
BUR-0.001
osit-0.001
 supervision-0.001
Tokenchie
Token ID3043
Feature activation-6.76e-01

Pos logit contributions
ogens+0.018
 Debor+0.017
BUR+0.017
osit+0.016
 supervision+0.016
Neg logit contributions
blance-0.021
uments-0.020
arthed-0.020
ondon-0.019
nesota-0.018
Tokenff
Token ID487
Feature activation+6.11e-02

Pos logit contributions
ogens+0.232
 Debor+0.216
BUR+0.211
osit+0.207
 supervision+0.201
Neg logit contributions
blance-0.230
uments-0.215
arthed-0.213
ondon-0.200
nesota-0.191
Tokenelin
Token ID27176
Feature activation-6.13e-01

Pos logit contributions
blance+0.023
uments+0.021
arthed+0.021
ondon+0.020
nesota+0.019
Neg logit contributions
ogens-0.019
 Debor-0.018
BUR-0.017
osit-0.017
 supervision-0.016
Token,
Token ID11
Feature activation-1.51e-02

Pos logit contributions
ogens+0.185
 Debor+0.171
BUR+0.168
osit+0.163
 supervision+0.159
Neg logit contributions
blance-0.234
uments-0.220
arthed-0.218
ondon-0.207
nesota-0.197
Token B
Token ID347
Feature activation+1.50e-01

Pos logit contributions
ogens+0.005
 Debor+0.004
BUR+0.004
osit+0.004
 supervision+0.004
Neg logit contributions
blance-0.006
uments-0.005
arthed-0.005
ondon-0.005
nesota-0.005
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
blance+0.056
uments+0.053
arthed+0.052
ondon+0.049
nesota+0.047
Neg logit contributions
ogens-0.046
 Debor-0.043
BUR-0.042
osit-0.041
 supervision-0.040