TOP ACTIVATIONS
MAX = 0.274

and would be fully compens ating those injured in the scr
and others would consider compens ating former prisoners , many of
was a level of dishon esty and ir respons ibility ,
ERS ALL V EH IC LES , LAT R IN ES
South African racist regime purs ues the vicious policy of apartheid
access to WA Beer Fest ivals information F requently
ielding problems Fil tering problems Design problems
Ay at ollah Ali Kham enei , warned that the day
pro - cor porate arbit rators . A separate
." I fur row my eyebrows at the intruder
in passing . ( Prov idence is restrained in its gore
- long roller - co aster ride followed , as Re
of the Joint Chiefs of Staff , called Jones on Wednesday
Ar ag orn , Gand alf , Gim li the Dwarf
for Prosper ity : Dist orting climate change science and economics
Bay ern Munich Jun iors [ 92 ][ 93 ]
ing a slightly controversial pen alty . Next the victim d
8 b ET pic . twitter . com / W 8
Conf idence is sky high now but
There they unexpectedly meet Gand alf . Gand alf explains that

MIN ACTIVATIONS
MIN = -0.253

a 2 . 5 per cent increase in the first year
<|endoftext|> Our ELE X Woo Commerce Catalog Mode , Wh oles
ased as del ayed unfolding of independence
, capped at 20 per cent overall .) M
home habits . 42 per cent of workers revealed that they
dollar leaves a 50 per cent price gap ," he writes
home prices were 66 per cent above average U . S
examples : a 90 per cent reduction in HIV - related
showed that about 14 per cent of families in traditionally middle
as much as 20 per cent . Ad vertising
Not ley gathered 70 per cent of the votes . (
they 're making 20 per cent more than their private sector
, or about three per cent of the 9 , 204
likelihood is that 50 per cent of turtles that eat fewer
estimate that over 50 per cent of sea turtles around the
ost ino says 14 per cent of families struggling to afford
year and then two per cent in both of the following
we know that 50 per cent of turtles have eaten debris
of the del ayed unfolding of independence
finance is growing 50 per cent faster than traditional banking

INTERVAL 0.142 - 0.274
CONTAINS 0.021%

3 model is clearly distinguish able from its earlier predecessor ,
the police stations were barric ades and other signs of security
ERS ALL V EH IC LES , LAT R IN ES
never called . pic . twitter . com / CS 3
media bus ) pic . twitter . com / z J

INTERVAL 0.011 - 0.142
CONTAINS 27.922%

some . Similarly , millions of post men opausal women were
Canada and the United States widened to a record level in
the alleged victim and at least one of the arresting officers
, and they wouldn 't push two tables together to accommodate
ap the file , this code would actually run really fast

INTERVAL -0.121 - 0.011
CONTAINS 71.988%

an interview on 26 May 1965 , Zh uk ov stated
tten who released her fourth album Are We
owned by Alex Jones that propag ates conspiracy theories like the
ered Bob ro vs ky with 19 shots ( to just
deputy Conservative leader Lisa Ra itt said . " I am

INTERVAL -0.253 - -0.121
CONTAINS 0.068%

ac rest , Louis Vu itton , Gil more
counterparts . Analy sts say that the Kremlin
Kal up ur , Ahmed abad , Gujarat 38 0001 ,
The City Ord inance According to the
M itch has exce lled through his final stages of
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
 Zar+0.010
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Token would
Token ID561
Feature activation+2.71e-02

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.011
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.010
anch-0.010
 doi-0.010
Token be
Token ID307
Feature activation+1.25e-02

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.019
nces+0.018
Neg logit contributions
 Zar-0.025
 Pax-0.025
-0.022
anch-0.022
 doi-0.021
Token fully
Token ID3938
Feature activation+2.85e-02

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token compens
Token ID7144
Feature activation-1.13e-02

Pos logit contributions
outhern+0.025
 328+0.023
 fantasy+0.022
28+0.021
nces+0.021
Neg logit contributions
 Zar-0.025
 Pax-0.024
-0.022
anch-0.021
 doi-0.021
Tokenating
Token ID803
Feature activation+2.74e-01

Pos logit contributions
 Zar+0.012
 Pax+0.011
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
Token those
Token ID883
Feature activation+1.51e-02

Pos logit contributions
outhern+0.231
 328+0.208
 fantasy+0.201
28+0.194
nces+0.191
Neg logit contributions
 Zar-0.251
 Pax-0.243
-0.221
anch-0.215
 doi-0.210
Token injured
Token ID6686
Feature activation+9.52e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.014
anch-0.013
 doi-0.013
Token in
Token ID287
Feature activation+2.57e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.019
nces+0.018
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.020
 doi-0.019
Token scr
Token ID6040
Feature activation+4.55e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token and
Token ID290
Feature activation+2.15e-03

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token others
Token ID1854
Feature activation-1.40e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token would
Token ID561
Feature activation+1.13e-02

Pos logit contributions
 Zar+0.012
 Pax+0.011
+0.010
anch+0.010
 doi+0.009
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.012
28-0.011
nces-0.011
Token consider
Token ID2074
Feature activation-3.33e-03

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.009
anch-0.009
 doi-0.008
Token compens
Token ID7144
Feature activation-3.67e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.002
28-0.002
nces-0.002
Tokenating
Token ID803
Feature activation+2.53e-01

Pos logit contributions
 Zar+0.037
 Pax+0.035
+0.033
anch+0.032
 doi+0.031
Neg logit contributions
outhern-0.028
 328-0.025
 fantasy-0.024
28-0.023
nces-0.023
Token former
Token ID1966
Feature activation-3.10e-02

Pos logit contributions
outhern+0.200
 328+0.177
 fantasy+0.170
28+0.165
nces+0.163
Neg logit contributions
 Zar-0.247
 Pax-0.239
-0.218
anch-0.213
 doi-0.208
Token prisoners
Token ID10577
Feature activation-5.97e-03

Pos logit contributions
 Zar+0.028
 Pax+0.027
+0.024
anch+0.024
 doi+0.023
Neg logit contributions
outhern-0.027
 328-0.024
 fantasy-0.023
28-0.022
nces-0.022
Token,
Token ID11
Feature activation-1.71e-02

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token many
Token ID867
Feature activation-1.36e-04

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.016
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.013
 328-0.011
 fantasy-0.011
nces-0.010
28-0.010
Token of
Token ID286
Feature activation-5.74e-03

Pos logit contributions
 Zar+0.000
 Pax+0.000
+0.000
anch+0.000
 doi+0.000
Neg logit contributions
outhern-0.000
 328-0.000
 fantasy-0.000
nces-0.000
28-0.000
Token was
Token ID373
Feature activation+1.92e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token a
Token ID257
Feature activation+1.25e-04

Pos logit contributions
outhern+0.017
 328+0.015
 fantasy+0.014
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.015
anch-0.014
 doi-0.014
Token level
Token ID1241
Feature activation-1.32e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token of
Token ID286
Feature activation-5.17e-03

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
Token dishon
Token ID32045
Feature activation+4.74e-03

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.003
nces-0.003
Tokenesty
Token ID9673
Feature activation+2.15e-01

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.005
 doi-0.005
Token and
Token ID290
Feature activation+7.95e-03

Pos logit contributions
outhern+0.185
 328+0.166
 fantasy+0.160
28+0.155
nces+0.153
Neg logit contributions
 Zar-0.194
 Pax-0.187
-0.170
anch-0.165
 doi-0.162
Token ir
Token ID4173
Feature activation-4.62e-02

Pos logit contributions
outhern+0.006
 328+0.006
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.007
 doi-0.006
Tokenrespons
Token ID16733
Feature activation+3.45e-03

Pos logit contributions
 Zar+0.041
 Pax+0.040
+0.036
anch+0.035
 doi+0.034
Neg logit contributions
outhern-0.040
 328-0.036
 fantasy-0.035
28-0.034
nces-0.034
Tokenibility
Token ID2247
Feature activation-5.49e-02

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Token,
Token ID11
Feature activation-1.02e-03

Pos logit contributions
 Zar+0.048
 Pax+0.046
+0.042
anch+0.041
 doi+0.040
Neg logit contributions
outhern-0.049
 328-0.044
 fantasy-0.042
28-0.041
nces-0.041
TokenERS
Token ID4877
Feature activation+2.62e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.012
Token ALL
Token ID11096
Feature activation+7.36e-03

Pos logit contributions
outhern+0.021
 328+0.019
 fantasy+0.018
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.025
 Pax-0.024
-0.022
anch-0.022
 doi-0.021
Token V
Token ID569
Feature activation+1.74e-02

Pos logit contributions
outhern+0.005
 328+0.005
 fantasy+0.005
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.007
 doi-0.006
TokenEH
Token ID42413
Feature activation+2.02e-02

Pos logit contributions
outhern+0.015
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.013
anch-0.013
 doi-0.013
TokenIC
Token ID2149
Feature activation+4.13e-02

Pos logit contributions
outhern+0.017
 328+0.015
 fantasy+0.015
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.016
anch-0.016
 doi-0.016
TokenLES
Token ID28378
Feature activation+2.07e-01

Pos logit contributions
outhern+0.018
 328+0.014
 fantasy+0.013
nces+0.012
28+0.012
Neg logit contributions
 Zar-0.055
 Pax-0.054
-0.050
anch-0.049
 doi-0.049
Token,
Token ID11
Feature activation+8.78e-03

Pos logit contributions
outhern+0.163
 328+0.144
 fantasy+0.139
28+0.134
nces+0.132
Neg logit contributions
 Zar-0.203
 Pax-0.197
-0.180
anch-0.176
 doi-0.172
Token LAT
Token ID42355
Feature activation+5.49e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
TokenR
Token ID49
Feature activation+2.26e-02

Pos logit contributions
outhern+0.042
 328+0.037
 fantasy+0.035
28+0.034
nces+0.034
Neg logit contributions
 Zar-0.055
 Pax-0.054
-0.049
anch-0.048
 doi-0.047
TokenIN
Token ID1268
Feature activation-2.25e-02

Pos logit contributions
outhern+0.018
 328+0.016
 fantasy+0.015
nces+0.015
28+0.015
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.019
 doi-0.018
TokenES
Token ID1546
Feature activation-1.46e-02

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.020
anch+0.020
 doi+0.019
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.014
Token South
Token ID2520
Feature activation+1.27e-04

Pos logit contributions
outhern+0.027
 328+0.024
 fantasy+0.023
28+0.022
nces+0.022
Neg logit contributions
 Zar-0.032
 Pax-0.031
-0.028
anch-0.027
 doi-0.027
Token African
Token ID5510
Feature activation+7.48e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token racist
Token ID9811
Feature activation+5.94e-02

Pos logit contributions
outhern+0.062
 328+0.055
 fantasy+0.053
28+0.051
nces+0.051
Neg logit contributions
 Zar-0.070
 Pax-0.068
-0.062
anch-0.060
 doi-0.059
Token regime
Token ID7142
Feature activation-7.91e-03

Pos logit contributions
outhern+0.050
 328+0.045
 fantasy+0.043
28+0.042
nces+0.041
Neg logit contributions
 Zar-0.055
 Pax-0.053
-0.048
anch-0.047
 doi-0.046
Token purs
Token ID8012
Feature activation-1.16e-02

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.007
 328-0.006
 fantasy-0.006
28-0.006
nces-0.006
Tokenues
Token ID947
Feature activation+2.04e-01

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.006
Token the
Token ID262
Feature activation+3.83e-02

Pos logit contributions
outhern+0.176
 328+0.158
 fantasy+0.153
28+0.148
nces+0.146
Neg logit contributions
 Zar-0.183
 Pax-0.177
-0.161
anch-0.157
 doi-0.153
Token vicious
Token ID17686
Feature activation+1.47e-02

Pos logit contributions
outhern+0.032
 328+0.029
 fantasy+0.028
28+0.027
nces+0.026
Neg logit contributions
 Zar-0.036
 Pax-0.034
-0.031
anch-0.030
 doi-0.030
Token policy
Token ID2450
Feature activation-2.03e-03

Pos logit contributions
outhern+0.013
 328+0.011
 fantasy+0.011
28+0.011
nces+0.010
Neg logit contributions
 Zar-0.013
 Pax-0.013
-0.012
anch-0.011
 doi-0.011
Token of
Token ID286
Feature activation+3.41e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token apartheid
Token ID38264
Feature activation-4.81e-02

Pos logit contributions
outhern+0.030
 328+0.027
 fantasy+0.026
28+0.025
nces+0.025
Neg logit contributions
 Zar-0.031
 Pax-0.029
-0.027
anch-0.026
 doi-0.025
Token access
Token ID1895
Feature activation+3.48e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token to
Token ID284
Feature activation-2.03e-02

Pos logit contributions
outhern+0.029
 328+0.026
 fantasy+0.025
28+0.024
nces+0.024
Neg logit contributions
 Zar-0.032
 Pax-0.031
-0.028
anch-0.028
 doi-0.027
Token WA
Token ID16400
Feature activation-1.86e-02

Pos logit contributions
 Zar+0.020
 Pax+0.020
+0.018
anch+0.017
 doi+0.017
Neg logit contributions
outhern-0.016
 328-0.014
 fantasy-0.013
28-0.013
nces-0.013
Token Beer
Token ID16971
Feature activation+2.67e-02

Pos logit contributions
 Zar+0.014
 Pax+0.014
+0.012
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.018
 328-0.017
 fantasy-0.016
28-0.016
nces-0.016
Token Fest
Token ID26812
Feature activation+1.76e-02

Pos logit contributions
outhern+0.023
 328+0.021
 fantasy+0.020
28+0.019
nces+0.019
Neg logit contributions
 Zar-0.024
 Pax-0.023
-0.021
anch-0.020
 doi-0.020
Tokenivals
Token ID10336
Feature activation+1.96e-01

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.010
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.019
 Pax-0.019
-0.017
anch-0.017
 doi-0.017
Token information
Token ID1321
Feature activation+4.03e-03

Pos logit contributions
outhern+0.158
 328+0.141
 fantasy+0.136
28+0.131
nces+0.129
Neg logit contributions
 Zar-0.187
 Pax-0.181
-0.165
anch-0.161
 doi-0.158
Token
Token ID198
Feature activation+5.95e-03

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.003
anch-0.003
 doi-0.003
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
TokenF
Token ID37
Feature activation-2.77e-03

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.009
anch-0.009
 doi-0.009
Tokenrequently
Token ID37971
Feature activation+4.28e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.001
Tokenielding
Token ID30449
Feature activation+4.28e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.016
 Pax-0.015
-0.014
anch-0.013
 doi-0.013
Token problems
Token ID2761
Feature activation-7.41e-03

Pos logit contributions
outhern+0.038
 328+0.034
 fantasy+0.033
28+0.032
nces+0.031
Neg logit contributions
 Zar-0.038
 Pax-0.037
-0.033
anch-0.032
 doi-0.031
Token
Token ID198
Feature activation+1.50e-02

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token
Token ID198
Feature activation+8.89e-03

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.010
28+0.010
 AD+0.010
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.013
 doi-0.012
TokenFil
Token ID11928
Feature activation+2.13e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Tokentering
Token ID20212
Feature activation+1.93e-01

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.024
 Pax-0.023
-0.021
anch-0.021
 doi-0.021
Token problems
Token ID2761
Feature activation-2.43e-03

Pos logit contributions
outhern+0.165
 328+0.148
 fantasy+0.143
28+0.139
nces+0.137
Neg logit contributions
 Zar-0.176
 Pax-0.169
-0.154
anch-0.150
 doi-0.146
Token
Token ID198
Feature activation+7.13e-03

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token
Token ID198
Feature activation+1.17e-03

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
 AD+0.005
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
TokenDesign
Token ID23067
Feature activation+2.07e-03

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token problems
Token ID2761
Feature activation+6.34e-03

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.002
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token Ay
Token ID13709
Feature activation-4.68e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.018
 328-0.017
 fantasy-0.017
28-0.016
nces-0.016
Tokenat
Token ID265
Feature activation+2.06e-02

Pos logit contributions
 Zar+0.038
 Pax+0.036
+0.033
anch+0.032
 doi+0.031
Neg logit contributions
outhern-0.044
 328-0.040
 fantasy-0.039
28-0.038
nces-0.037
Tokenollah
Token ID17999
Feature activation-7.28e-02

Pos logit contributions
outhern+0.023
 328+0.021
 fantasy+0.021
28+0.020
nces+0.020
Neg logit contributions
 Zar-0.013
 Pax-0.012
-0.011
anch-0.010
 doi-0.010
Token Ali
Token ID12104
Feature activation-1.69e-02

Pos logit contributions
 Zar+0.039
 Pax+0.038
+0.032
anch+0.030
 doi+0.029
Neg logit contributions
outhern-0.088
 328-0.082
 fantasy-0.080
28-0.078
nces-0.078
Token Kham
Token ID45159
Feature activation-3.23e-02

Pos logit contributions
 Zar+0.006
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.024
 328-0.022
 fantasy-0.022
28-0.021
nces-0.021
Tokenenei
Token ID46009
Feature activation+1.90e-01

Pos logit contributions
 Zar+0.036
 Pax+0.035
+0.033
anch+0.032
 doi+0.031
Neg logit contributions
outhern-0.021
 328-0.018
 fantasy-0.017
28-0.016
nces-0.016
Token,
Token ID11
Feature activation+8.14e-03

Pos logit contributions
outhern+0.156
 328+0.140
 fantasy+0.135
28+0.132
nces+0.129
Neg logit contributions
 Zar-0.176
 Pax-0.172
-0.157
anch-0.152
 doi-0.149
Token warned
Token ID7728
Feature activation+6.99e-03

Pos logit contributions
outhern+0.007
 328+0.007
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
Token that
Token ID326
Feature activation-4.52e-02

Pos logit contributions
outhern+0.006
 328+0.006
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token the
Token ID262
Feature activation-2.33e-02

Pos logit contributions
 Zar+0.039
 Pax+0.038
+0.035
anch+0.033
 doi+0.033
Neg logit contributions
outhern-0.040
 328-0.036
 fantasy-0.035
28-0.034
nces-0.034
Token day
Token ID1110
Feature activation+1.79e-02

Pos logit contributions
 Zar+0.024
 Pax+0.023
+0.021
anch+0.021
 doi+0.021
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.014
Token pro
Token ID386
Feature activation+5.70e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token-
Token ID12
Feature activation-1.10e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.005
 doi-0.005
Tokencor
Token ID10215
Feature activation-4.26e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Tokenporate
Token ID38133
Feature activation+7.80e-03

Pos logit contributions
 Zar+0.038
 Pax+0.037
+0.033
anch+0.033
 doi+0.032
Neg logit contributions
outhern-0.037
 328-0.033
 fantasy-0.032
28-0.031
nces-0.031
Token arbit
Token ID9277
Feature activation-1.53e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
Tokenrators
Token ID18942
Feature activation+1.86e-01

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.016
anch+0.016
 doi+0.015
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Token.
Token ID13
Feature activation-7.25e-03

Pos logit contributions
outhern+0.147
 328+0.130
 fantasy+0.125
28+0.121
nces+0.119
Neg logit contributions
 Zar-0.181
 Pax-0.176
-0.161
anch-0.157
 doi-0.153
Token
Token ID198
Feature activation-9.63e-03

Pos logit contributions
 Zar+0.007
 Pax+0.006
+0.006
anch+0.006
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token
Token ID198
Feature activation-5.16e-03

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.006
nces-0.006
TokenA
Token ID32
Feature activation+2.01e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token separate
Token ID4553
Feature activation-3.46e-03

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.020
 Pax-0.019
-0.018
anch-0.017
 doi-0.017
Token."
Token ID526
Feature activation-7.54e-02

Pos logit contributions
 Zar+0.007
 Pax+0.006
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token
Token ID198
Feature activation-4.27e-02

Pos logit contributions
 Zar+0.070
 Pax+0.068
+0.062
anch+0.060
 doi+0.059
Neg logit contributions
outhern-0.063
 328-0.056
 fantasy-0.054
28-0.053
nces-0.052
Token
Token ID198
Feature activation-3.53e-02

Pos logit contributions
 Zar+0.042
 Pax+0.041
+0.037
anch+0.036
 doi+0.035
Neg logit contributions
outhern-0.033
 328-0.030
 fantasy-0.029
28-0.028
 AD-0.027
TokenI
Token ID40
Feature activation-1.64e-02

Pos logit contributions
 Zar+0.032
 Pax+0.031
+0.028
anch+0.027
 doi+0.026
Neg logit contributions
outhern-0.031
 328-0.028
 fantasy-0.027
28-0.026
nces-0.025
Token fur
Token ID9230
Feature activation+6.92e-03

Pos logit contributions
 Zar+0.015
 Pax+0.014
+0.013
anch+0.013
 doi+0.012
Neg logit contributions
outhern-0.014
 328-0.013
 fantasy-0.012
28-0.012
nces-0.012
Tokenrow
Token ID808
Feature activation+1.81e-01

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.004
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token my
Token ID616
Feature activation-5.30e-02

Pos logit contributions
outhern+0.161
 328+0.145
 fantasy+0.141
28+0.136
nces+0.134
Neg logit contributions
 Zar-0.159
 Pax-0.153
-0.139
anch-0.134
 doi-0.131
Token eyebrows
Token ID26928
Feature activation+1.59e-02

Pos logit contributions
 Zar+0.043
 Pax+0.042
+0.038
anch+0.036
 doi+0.035
Neg logit contributions
outhern-0.050
 328-0.046
 fantasy-0.044
28-0.043
nces-0.042
Token at
Token ID379
Feature activation+4.23e-02

Pos logit contributions
outhern+0.013
 328+0.011
 fantasy+0.011
28+0.011
nces+0.010
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.013
anch-0.013
 doi-0.013
Token the
Token ID262
Feature activation-7.57e-03

Pos logit contributions
outhern+0.036
 328+0.032
 fantasy+0.031
28+0.030
nces+0.030
Neg logit contributions
 Zar-0.038
 Pax-0.037
-0.034
anch-0.033
 doi-0.032
Token intruder
Token ID48927
Feature activation-4.08e-02

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.007
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
nces-0.005
28-0.005
Token in
Token ID287
Feature activation-2.03e-02

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token passing
Token ID6427
Feature activation-9.25e-04

Pos logit contributions
 Zar+0.019
 Pax+0.018
+0.016
anch+0.016
 doi+0.016
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.015
28-0.014
nces-0.014
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token (
Token ID357
Feature activation-5.72e-03

Pos logit contributions
 Zar+0.010
 Pax+0.010
+0.009
anch+0.009
 doi+0.008
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
TokenProv
Token ID15946
Feature activation-2.41e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.005
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Tokenidence
Token ID1704
Feature activation+1.79e-01

Pos logit contributions
 Zar+0.029
 Pax+0.029
+0.027
anch+0.026
 doi+0.026
Neg logit contributions
outhern-0.013
 328-0.011
 fantasy-0.010
28-0.010
nces-0.010
Token is
Token ID318
Feature activation-2.08e-02

Pos logit contributions
outhern+0.159
 328+0.143
 fantasy+0.138
28+0.134
nces+0.133
Neg logit contributions
 Zar-0.157
 Pax-0.151
-0.136
anch-0.133
 doi-0.130
Token restrained
Token ID31531
Feature activation-2.08e-02

Pos logit contributions
 Zar+0.020
 Pax+0.019
+0.017
anch+0.017
 doi+0.017
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.015
28-0.014
nces-0.014
Token in
Token ID287
Feature activation-2.32e-02

Pos logit contributions
 Zar+0.020
 Pax+0.019
+0.018
anch+0.017
 doi+0.017
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.014
Token its
Token ID663
Feature activation+9.96e-03

Pos logit contributions
 Zar+0.021
 Pax+0.020
+0.019
anch+0.018
 doi+0.018
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.016
Token gore
Token ID46835
Feature activation-1.18e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.006
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.009
anch-0.008
 doi-0.008
Token-
Token ID12
Feature activation+5.49e-04

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Tokenlong
Token ID6511
Feature activation+7.75e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token roller
Token ID24471
Feature activation-2.04e-02

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.007
anch-0.006
 doi-0.006
Token-
Token ID12
Feature activation+1.99e-04

Pos logit contributions
 Zar+0.017
 Pax+0.017
+0.015
anch+0.015
 doi+0.014
Neg logit contributions
outhern-0.019
 328-0.017
 fantasy-0.016
nces-0.016
28-0.016
Tokenco
Token ID1073
Feature activation-1.57e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
nces+0.000
28+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Tokenaster
Token ID1603
Feature activation+1.79e-01

Pos logit contributions
 Zar+0.021
 Pax+0.021
+0.020
anch+0.019
 doi+0.019
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.004
nces-0.004
Token ride
Token ID6594
Feature activation-1.92e-03

Pos logit contributions
outhern+0.145
 328+0.129
 fantasy+0.124
28+0.120
nces+0.119
Neg logit contributions
 Zar-0.171
 Pax-0.165
-0.150
anch-0.147
 doi-0.144
Token followed
Token ID3940
Feature activation-1.88e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.001
28-0.001
nces-0.001
Token,
Token ID11
Feature activation-6.33e-04

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.016
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.015
 328-0.014
 fantasy-0.013
28-0.013
nces-0.012
Token as
Token ID355
Feature activation+6.84e-03

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.000
 fantasy-0.000
28-0.000
nces-0.000
Token Re
Token ID797
Feature activation+2.80e-03

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token of
Token ID286
Feature activation-4.04e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.005
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token the
Token ID262
Feature activation+1.73e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token Joint
Token ID16798
Feature activation-1.10e-02

Pos logit contributions
outhern+0.002
 328+0.001
 fantasy+0.001
nces+0.001
ungle+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token Chiefs
Token ID18733
Feature activation+1.17e-02

Pos logit contributions
 Zar+0.006
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.014
 328-0.013
 fantasy-0.013
28-0.012
nces-0.012
Token of
Token ID286
Feature activation+1.44e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.012
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token Staff
Token ID9983
Feature activation+1.77e-01

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.016
anch-0.015
 doi-0.015
Token,
Token ID11
Feature activation-5.35e-04

Pos logit contributions
outhern+0.145
 328+0.130
 fantasy+0.125
28+0.121
nces+0.119
Neg logit contributions
 Zar-0.166
 Pax-0.161
-0.147
anch-0.143
 doi-0.140
Token called
Token ID1444
Feature activation-3.25e-03

Pos logit contributions
 Zar+0.000
 Pax+0.000
+0.000
anch+0.000
 doi+0.000
Neg logit contributions
outhern-0.000
 328-0.000
 fantasy-0.000
28-0.000
nces-0.000
Token Jones
Token ID5437
Feature activation+7.75e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token on
Token ID319
Feature activation+9.91e-03

Pos logit contributions
outhern+0.006
 328+0.006
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
Token Wednesday
Token ID3583
Feature activation-1.56e-02

Pos logit contributions
outhern+0.008
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token Ar
Token ID943
Feature activation-2.52e-02

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Tokenag
Token ID363
Feature activation-3.37e-02

Pos logit contributions
 Zar+0.021
 Pax+0.020
+0.018
anch+0.018
 doi+0.017
Neg logit contributions
outhern-0.023
 328-0.021
 fantasy-0.021
28-0.020
nces-0.020
Tokenorn
Token ID1211
Feature activation+3.63e-02

Pos logit contributions
 Zar+0.041
 Pax+0.040
+0.037
anch+0.036
 doi+0.036
Neg logit contributions
outhern-0.019
 328-0.016
 fantasy-0.015
28-0.014
nces-0.014
Token,
Token ID11
Feature activation+1.28e-02

Pos logit contributions
outhern+0.030
 328+0.027
 fantasy+0.026
28+0.025
nces+0.025
Neg logit contributions
 Zar-0.034
 Pax-0.033
-0.030
anch-0.029
 doi-0.028
Token Gand
Token ID17727
Feature activation-3.85e-02

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.009
Tokenalf
Token ID1604
Feature activation+1.74e-01

Pos logit contributions
 Zar+0.056
 Pax+0.055
+0.051
anch+0.051
 doi+0.050
Neg logit contributions
outhern-0.012
 328-0.008
 fantasy-0.007
nces-0.006
28-0.006
Token,
Token ID11
Feature activation+1.15e-02

Pos logit contributions
outhern+0.145
 328+0.129
 fantasy+0.125
28+0.121
nces+0.120
Neg logit contributions
 Zar-0.163
 Pax-0.157
-0.143
anch-0.139
 doi-0.136
Token Gim
Token ID41123
Feature activation+3.97e-03

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.009
anch-0.009
 doi-0.008
Tokenli
Token ID4528
Feature activation+7.60e-02

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
nces+0.002
28+0.002
Neg logit contributions
 Zar-0.004
 Pax-0.004
anch-0.004
-0.004
 doi-0.004
Token the
Token ID262
Feature activation+1.70e-02

Pos logit contributions
outhern+0.063
 328+0.056
 fantasy+0.054
28+0.053
nces+0.052
Neg logit contributions
 Zar-0.071
 Pax-0.069
-0.062
anch-0.061
 doi-0.060
Token Dwarf
Token ID33196
Feature activation-1.75e-03

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
nces+0.011
28+0.011
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Token for
Token ID329
Feature activation-8.45e-03

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.010
-0.009
anch-0.009
 doi-0.009
Token Prosper
Token ID41342
Feature activation+8.48e-02

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Tokenity
Token ID414
Feature activation-1.57e-02

Pos logit contributions
outhern+0.062
 328+0.056
 fantasy+0.054
28+0.052
 AD+0.051
Neg logit contributions
 Zar-0.086
 Pax-0.084
-0.076
anch-0.074
 doi-0.074
Token:
Token ID25
Feature activation+1.91e-02

Pos logit contributions
 Zar+0.014
 Pax+0.014
+0.012
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.014
 328-0.012
 fantasy-0.012
28-0.011
nces-0.011
Token Dist
Token ID4307
Feature activation+2.60e-02

Pos logit contributions
outhern+0.019
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.014
 Pax-0.014
-0.012
anch-0.012
 doi-0.011
Tokenorting
Token ID24707
Feature activation+1.74e-01

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.018
nces+0.018
Neg logit contributions
 Zar-0.024
 Pax-0.023
-0.021
anch-0.020
 doi-0.020
Token climate
Token ID4258
Feature activation+2.35e-02

Pos logit contributions
outhern+0.154
 328+0.138
 fantasy+0.133
28+0.129
nces+0.128
Neg logit contributions
 Zar-0.154
 Pax-0.149
-0.134
anch-0.131
 doi-0.128
Token change
Token ID1487
Feature activation+1.62e-02

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.020
28+0.019
nces+0.019
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.016
anch-0.016
 doi-0.016
Token science
Token ID3783
Feature activation+3.40e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.012
nces+0.011
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.013
 doi-0.012
Token and
Token ID290
Feature activation+9.27e-03

Pos logit contributions
outhern+0.028
 328+0.025
 fantasy+0.024
28+0.023
nces+0.023
Neg logit contributions
 Zar-0.032
 Pax-0.031
-0.028
anch-0.027
 doi-0.027
Token economics
Token ID12446
Feature activation-3.25e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token
Token ID198
Feature activation+2.61e-02

Pos logit contributions
outhern+0.023
 328+0.020
 fantasy+0.019
28+0.019
 AD+0.018
Neg logit contributions
 Zar-0.028
 Pax-0.027
-0.025
anch-0.024
 doi-0.023
TokenBay
Token ID15262
Feature activation-4.14e-02

Pos logit contributions
outhern+0.020
 328+0.018
 fantasy+0.017
nces+0.016
28+0.016
Neg logit contributions
 Zar-0.026
 Pax-0.025
-0.023
anch-0.023
 doi-0.022
Tokenern
Token ID1142
Feature activation-2.97e-02

Pos logit contributions
 Zar+0.039
 Pax+0.038
+0.034
anch+0.034
 doi+0.033
Neg logit contributions
outhern-0.034
 328-0.030
 fantasy-0.029
28-0.028
nces-0.028
Token Munich
Token ID22418
Feature activation+2.14e-02

Pos logit contributions
 Zar+0.032
 Pax+0.030
+0.028
anch+0.027
 doi+0.027
Neg logit contributions
outhern-0.021
 328-0.018
 fantasy-0.018
28-0.017
nces-0.017
Token Jun
Token ID7653
Feature activation+3.76e-02

Pos logit contributions
outhern+0.017
 328+0.015
 fantasy+0.015
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.021
 Pax-0.020
-0.018
anch-0.018
 doi-0.017
Tokeniors
Token ID12706
Feature activation+1.74e-01

Pos logit contributions
outhern+0.024
 328+0.020
 fantasy+0.019
28+0.018
nces+0.018
Neg logit contributions
 Zar-0.043
 Pax-0.042
-0.039
anch-0.038
 doi-0.037
Token[
Token ID58
Feature activation+2.93e-02

Pos logit contributions
outhern+0.137
 328+0.120
 fantasy+0.116
28+0.112
nces+0.111
Neg logit contributions
 Zar-0.171
 Pax-0.165
-0.151
anch-0.147
 doi-0.145
Token92
Token ID5892
Feature activation+1.07e-02

Pos logit contributions
outhern+0.029
 328+0.026
 fantasy+0.026
28+0.025
nces+0.025
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.019
anch-0.019
 doi-0.018
Token][
Token ID7131
Feature activation+6.40e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.009
Token93
Token ID6052
Feature activation+8.41e-04

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.004
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Token]
Token ID60
Feature activation+2.79e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Tokening
Token ID278
Feature activation-5.38e-02

Pos logit contributions
outhern+0.039
 328+0.034
 fantasy+0.033
28+0.032
nces+0.031
Neg logit contributions
 Zar-0.054
 Pax-0.052
-0.048
anch-0.047
 doi-0.046
Token a
Token ID257
Feature activation+6.42e-03

Pos logit contributions
 Zar+0.049
 Pax+0.047
+0.042
anch+0.041
 doi+0.040
Neg logit contributions
outhern-0.046
 328-0.041
 fantasy-0.040
28-0.039
nces-0.039
Token slightly
Token ID4622
Feature activation+2.28e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
nces+0.004
28+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token controversial
Token ID8381
Feature activation+3.10e-02

Pos logit contributions
outhern+0.018
 328+0.016
 fantasy+0.016
28+0.015
nces+0.015
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.019
 doi-0.018
Tokenpen
Token ID3617
Feature activation+2.04e-02

Pos logit contributions
outhern+0.025
 328+0.022
 fantasy+0.021
28+0.020
nces+0.020
Neg logit contributions
 Zar-0.030
 Pax-0.029
-0.027
anch-0.026
 doi-0.025
Tokenalty
Token ID6017
Feature activation+1.73e-01

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.009
nces+0.009
28+0.009
Neg logit contributions
 Zar-0.024
 Pax-0.024
-0.022
anch-0.022
 doi-0.021
Token.
Token ID13
Feature activation-9.93e-03

Pos logit contributions
outhern+0.141
 328+0.125
 fantasy+0.121
28+0.117
nces+0.116
Neg logit contributions
 Zar-0.165
 Pax-0.160
-0.145
anch-0.142
 doi-0.139
Token Next
Token ID7406
Feature activation-9.42e-04

Pos logit contributions
 Zar+0.009
 Pax+0.008
+0.008
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
Token the
Token ID262
Feature activation+9.92e-04

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token victim
Token ID3117
Feature activation+1.90e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token d
Token ID288
Feature activation+1.64e-02

Pos logit contributions
outhern+0.016
 328+0.015
 fantasy+0.014
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Token8
Token ID23
Feature activation-2.38e-03

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.006
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Tokenb
Token ID65
Feature activation+3.60e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
TokenET
Token ID2767
Feature activation+1.27e-02

Pos logit contributions
outhern+0.029
 328+0.026
 fantasy+0.025
28+0.024
nces+0.024
Neg logit contributions
 Zar-0.034
 Pax-0.033
-0.030
anch-0.029
 doi-0.029
Token pic
Token ID8301
Feature activation+2.37e-02

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.012
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token.
Token ID13
Feature activation-8.71e-03

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.016
28+0.016
nces+0.015
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.021
anch-0.020
 doi-0.020
Tokentwitter
Token ID6956
Feature activation+1.73e-01

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.007
 328-0.007
 fantasy-0.006
28-0.006
nces-0.006
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
outhern+0.133
 328+0.119
 fantasy+0.114
28+0.112
 AD+0.108
Neg logit contributions
 Zar-0.170
 Pax-0.165
-0.151
anch-0.147
 doi-0.143
Tokencom
Token ID785
Feature activation-1.63e-02

Pos logit contributions
 Zar+0.017
 Pax+0.017
+0.016
anch+0.016
 doi+0.015
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.006
28-0.006
nces-0.006
Token/
Token ID14
Feature activation-4.52e-02

Pos logit contributions
 Zar+0.017
 Pax+0.017
+0.015
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.009
nces-0.009
TokenW
Token ID54
Feature activation-4.49e-03

Pos logit contributions
 Zar+0.042
 Pax+0.041
+0.037
anch+0.037
 doi+0.036
Neg logit contributions
outhern-0.037
 328-0.033
 fantasy-0.032
28-0.031
nces-0.031
Token8
Token ID23
Feature activation-5.59e-03

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.004
 doi+0.003
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token
Token ID198
Feature activation+6.15e-05

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.004
 doi-0.004
Token
Token ID198
Feature activation+7.82e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token
Token ID447
Feature activation-2.58e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
Token
Token ID250
Feature activation+1.97e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.001
nces-0.001
TokenConf
Token ID18546
Feature activation+1.67e-02

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.001
 doi-0.001
Tokenidence
Token ID1704
Feature activation+1.70e-01

Pos logit contributions
outhern+0.010
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.020
 Pax-0.019
-0.018
anch-0.018
 doi-0.017
Token is
Token ID318
Feature activation-1.76e-02

Pos logit contributions
outhern+0.150
 328+0.135
 fantasy+0.131
28+0.127
nces+0.125
Neg logit contributions
 Zar-0.149
 Pax-0.144
-0.130
anch-0.126
 doi-0.124
Token sky
Token ID6766
Feature activation-1.19e-02

Pos logit contributions
 Zar+0.016
 Pax+0.016
+0.014
anch+0.014
 doi+0.014
Neg logit contributions
outhern-0.015
 328-0.013
 fantasy-0.013
28-0.012
nces-0.012
Token high
Token ID1029
Feature activation-2.48e-03

Pos logit contributions
 Zar+0.012
 Pax+0.011
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Token now
Token ID783
Feature activation-9.96e-03

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token but
Token ID475
Feature activation-9.47e-04

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
Token There
Token ID1318
Feature activation+1.22e-02

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.001
anch-0.001
 doi-0.001
Token they
Token ID484
Feature activation+1.02e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.009
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.009
Token unexpectedly
Token ID25884
Feature activation-4.58e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.007
 doi-0.007
Token meet
Token ID1826
Feature activation+2.17e-02

Pos logit contributions
 Zar+0.040
 Pax+0.039
+0.035
anch+0.034
 doi+0.033
Neg logit contributions
outhern-0.040
 328-0.036
 fantasy-0.035
28-0.034
nces-0.034
Token Gand
Token ID17727
Feature activation-2.77e-02

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.016
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.019
 Pax-0.019
-0.017
anch-0.016
 doi-0.016
Tokenalf
Token ID1604
Feature activation+1.70e-01

Pos logit contributions
 Zar+0.041
 Pax+0.040
+0.037
anch+0.037
 doi+0.036
Neg logit contributions
outhern-0.008
 328-0.006
 fantasy-0.005
nces-0.004
28-0.004
Token.
Token ID13
Feature activation-1.45e-02

Pos logit contributions
outhern+0.138
 328+0.122
 fantasy+0.118
28+0.114
nces+0.113
Neg logit contributions
 Zar-0.162
 Pax-0.157
-0.143
anch-0.139
 doi-0.136
Token Gand
Token ID17727
Feature activation-1.66e-02

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.012
28-0.012
nces-0.011
Tokenalf
Token ID1604
Feature activation+1.55e-01

Pos logit contributions
 Zar+0.024
 Pax+0.023
anch+0.022
+0.022
 doi+0.021
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.003
nces-0.003
28-0.003
Token explains
Token ID6688
Feature activation+4.42e-03

Pos logit contributions
outhern+0.143
 328+0.129
 fantasy+0.125
28+0.122
nces+0.121
Neg logit contributions
 Zar-0.131
 Pax-0.125
-0.113
anch-0.110
 doi-0.107
Token that
Token ID326
Feature activation+3.08e-02

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.003
anch-0.003
 doi-0.003
Token a
Token ID257
Feature activation+8.45e-03

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.010
28-0.009
nces-0.009
Token 2
Token ID362
Feature activation-8.26e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token.
Token ID13
Feature activation+8.88e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token5
Token ID20
Feature activation-2.18e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
nces+0.005
28+0.005
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token per
Token ID583
Feature activation+9.98e-03

Pos logit contributions
 Zar+0.024
 Pax+0.023
+0.021
anch+0.021
 doi+0.020
Neg logit contributions
outhern-0.015
 328-0.013
 fantasy-0.012
nces-0.012
28-0.012
Token cent
Token ID1247
Feature activation-2.49e-01

Pos logit contributions
outhern+0.011
 328+0.011
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token increase
Token ID2620
Feature activation+2.05e-02

Pos logit contributions
 Zar+0.189
 Pax+0.181
+0.160
anch+0.155
 doi+0.152
Neg logit contributions
outhern-0.251
 328-0.228
 fantasy-0.220
nces-0.216
28-0.215
Token in
Token ID287
Feature activation+6.11e-02

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.014
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.020
 Pax-0.019
-0.018
anch-0.017
 doi-0.017
Token the
Token ID262
Feature activation-9.41e-03

Pos logit contributions
outhern+0.057
 328+0.051
 fantasy+0.049
28+0.048
nces+0.048
Neg logit contributions
 Zar-0.051
 Pax-0.049
-0.044
anch-0.043
 doi-0.042
Token first
Token ID717
Feature activation-1.34e-02

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.007
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.006
nces-0.006
Token year
Token ID614
Feature activation-1.87e-02

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.012
 doi+0.011
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
Token<|endoftext|>
Token ID50256
Feature activation+7.15e-04

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.012
TokenOur
Token ID5122
Feature activation+8.32e-03

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token ELE
Token ID40342
Feature activation+7.25e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
TokenX
Token ID55
Feature activation-1.06e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token Woo
Token ID39832
Feature activation-6.32e-03

Pos logit contributions
 Zar+0.010
 Pax+0.010
+0.009
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
TokenCommerce
Token ID47662
Feature activation-2.43e-01

Pos logit contributions
 Zar+0.006
 Pax+0.005
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.005
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token Catalog
Token ID44515
Feature activation-1.21e-02

Pos logit contributions
 Zar+0.231
 Pax+0.224
+0.202
anch+0.198
 doi+0.194
Neg logit contributions
outhern-0.199
 328-0.174
 fantasy-0.167
nces-0.163
28-0.163
Token Mode
Token ID10363
Feature activation+3.30e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Token,
Token ID11
Feature activation+1.49e-02

Pos logit contributions
outhern+0.030
 328+0.027
 fantasy+0.026
28+0.025
nces+0.025
Neg logit contributions
 Zar-0.029
 Pax-0.028
-0.025
anch-0.024
 doi-0.024
Token Wh
Token ID854
Feature activation+3.31e-02

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.011
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.014
 Pax-0.014
-0.012
anch-0.012
 doi-0.012
Tokenoles
Token ID4316
Feature activation+2.84e-02

Pos logit contributions
outhern+0.029
 328+0.026
 fantasy+0.025
28+0.024
nces+0.024
Neg logit contributions
 Zar-0.029
 Pax-0.028
-0.026
anch-0.025
 doi-0.024
Tokenased
Token ID839
Feature activation+2.63e-02

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.013
 Pax-0.013
-0.012
anch-0.011
 doi-0.011
Token as
Token ID355
Feature activation-5.21e-03

Pos logit contributions
outhern+0.021
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.026
 Pax-0.025
-0.023
anch-0.022
 doi-0.022
Token
Token ID564
Feature activation-1.28e-02

Pos logit contributions
 Zar+0.005
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token
Token ID246
Feature activation-2.01e-02

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.010
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Tokendel
Token ID12381
Feature activation+3.88e-02

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.016
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.017
 328-0.016
 fantasy-0.015
28-0.015
nces-0.014
Tokenayed
Token ID16548
Feature activation-2.42e-01

Pos logit contributions
outhern+0.034
 328+0.030
 fantasy+0.029
28+0.029
nces+0.028
Neg logit contributions
 Zar-0.034
 Pax-0.033
-0.030
anch-0.029
 doi-0.029
Token unfolding
Token ID34502
Feature activation-2.07e-02

Pos logit contributions
 Zar+0.220
 Pax+0.213
+0.193
anch+0.188
 doi+0.184
Neg logit contributions
outhern-0.207
 328-0.186
 fantasy-0.179
28-0.174
nces-0.171
Token of
Token ID286
Feature activation-1.23e-02

Pos logit contributions
 Zar+0.019
 Pax+0.019
+0.017
anch+0.016
 doi+0.016
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.015
28-0.014
nces-0.014
Token independence
Token ID10404
Feature activation-2.20e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Token
Token ID447
Feature activation+8.49e-05

Pos logit contributions
 Zar+0.020
 Pax+0.019
+0.017
anch+0.017
 doi+0.016
Neg logit contributions
outhern-0.019
 328-0.017
 fantasy-0.017
28-0.016
nces-0.016
Token
Token ID247
Feature activation+1.38e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
nces+0.000
28+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.010
nces+0.009
Neg logit contributions
 Zar-0.013
 Pax-0.012
-0.011
anch-0.011
 doi-0.011
Token capped
Token ID28490
Feature activation+8.27e-03

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.012
 doi+0.011
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Token at
Token ID379
Feature activation+1.61e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.007
 doi-0.006
Token 20
Token ID1160
Feature activation-7.55e-03

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token per
Token ID583
Feature activation+8.38e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token cent
Token ID1247
Feature activation-2.40e-01

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.009
nces+0.008
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token overall
Token ID4045
Feature activation-2.38e-02

Pos logit contributions
 Zar+0.221
 Pax+0.213
+0.194
anch+0.189
 doi+0.185
Neg logit contributions
outhern-0.203
 328-0.182
 fantasy-0.175
28-0.169
nces-0.168
Token.)
Token ID2014
Feature activation-2.81e-02

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.019
anch+0.019
 doi+0.018
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.016
Token
Token ID198
Feature activation-1.08e-02

Pos logit contributions
 Zar+0.026
 Pax+0.025
+0.023
anch+0.022
 doi+0.022
Neg logit contributions
outhern-0.024
 328-0.021
 fantasy-0.020
28-0.020
nces-0.020
Token
Token ID198
Feature activation-3.75e-03

Pos logit contributions
 Zar+0.010
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.008
 328-0.008
 fantasy-0.007
28-0.007
 AD-0.007
TokenM
Token ID44
Feature activation+6.93e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token home
Token ID1363
Feature activation-6.89e-03

Pos logit contributions
outhern+0.011
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.015
anch-0.015
 doi-0.015
Token habits
Token ID13870
Feature activation-1.37e-03

Pos logit contributions
 Zar+0.007
 Pax+0.006
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token.
Token ID13
Feature activation-6.85e-03

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token 42
Token ID5433
Feature activation+1.36e-02

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token per
Token ID583
Feature activation+1.65e-02

Pos logit contributions
outhern+0.010
 328+0.008
 fantasy+0.008
nces+0.008
28+0.008
Neg logit contributions
 Zar-0.014
 Pax-0.014
-0.013
anch-0.012
 doi-0.012
Token cent
Token ID1247
Feature activation-2.40e-01

Pos logit contributions
outhern+0.019
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.008
anch-0.008
 doi-0.007
Token of
Token ID286
Feature activation+2.03e-02

Pos logit contributions
 Zar+0.231
 Pax+0.222
+0.204
anch+0.198
 doi+0.195
Neg logit contributions
outhern-0.192
 328-0.171
 fantasy-0.162
nces-0.157
28-0.157
Token workers
Token ID3259
Feature activation+4.39e-02

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.014
28+0.014
ungle+0.013
Neg logit contributions
 Zar-0.019
 Pax-0.019
-0.017
anch-0.017
 doi-0.016
Token revealed
Token ID4602
Feature activation+1.97e-02

Pos logit contributions
outhern+0.038
 328+0.034
 fantasy+0.033
28+0.032
nces+0.032
Neg logit contributions
 Zar-0.040
 Pax-0.038
-0.035
anch-0.034
 doi-0.033
Token that
Token ID326
Feature activation-6.47e-03

Pos logit contributions
outhern+0.018
 328+0.016
 fantasy+0.015
28+0.015
nces+0.015
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.015
anch-0.015
 doi-0.014
Token they
Token ID484
Feature activation-7.13e-03

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token dollar
Token ID8872
Feature activation+4.21e-02

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.020
anch+0.020
 doi+0.019
Neg logit contributions
outhern-0.019
 328-0.016
 fantasy-0.016
28-0.015
nces-0.015
Token leaves
Token ID5667
Feature activation-4.57e-02

Pos logit contributions
outhern+0.036
 328+0.032
 fantasy+0.031
28+0.030
nces+0.030
Neg logit contributions
 Zar-0.038
 Pax-0.037
-0.034
anch-0.033
 doi-0.032
Token a
Token ID257
Feature activation+2.84e-02

Pos logit contributions
 Zar+0.041
 Pax+0.040
+0.036
anch+0.035
 doi+0.034
Neg logit contributions
outhern-0.039
 328-0.035
 fantasy-0.034
28-0.033
nces-0.033
Token 50
Token ID2026
Feature activation-1.51e-03

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.018
nces+0.018
Neg logit contributions
 Zar-0.028
 Pax-0.027
-0.025
anch-0.024
 doi-0.024
Token per
Token ID583
Feature activation+2.18e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
nces-0.001
28-0.001
Token cent
Token ID1247
Feature activation-2.39e-01

Pos logit contributions
outhern+0.025
 328+0.023
 fantasy+0.023
28+0.022
nces+0.022
Neg logit contributions
 Zar-0.013
 Pax-0.013
-0.011
anch-0.010
 doi-0.010
Token price
Token ID2756
Feature activation+1.45e-02

Pos logit contributions
 Zar+0.220
 Pax+0.213
+0.193
anch+0.188
 doi+0.184
Neg logit contributions
outhern-0.201
 328-0.179
 fantasy-0.171
nces-0.167
28-0.167
Token gap
Token ID7625
Feature activation-2.37e-02

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.013
 Pax-0.012
-0.011
anch-0.011
 doi-0.011
Token,"
Token ID553
Feature activation+1.99e-02

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.019
anch+0.019
 doi+0.018
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.016
Token he
Token ID339
Feature activation+9.95e-03

Pos logit contributions
outhern+0.018
 328+0.016
 fantasy+0.015
28+0.015
nces+0.015
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.015
anch-0.015
 doi-0.014
Token writes
Token ID6797
Feature activation+9.19e-03

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
Token home
Token ID1363
Feature activation-9.34e-03

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token prices
Token ID4536
Feature activation+5.51e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.006
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
Token were
Token ID547
Feature activation+6.45e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token 66
Token ID7930
Feature activation-8.27e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Token per
Token ID583
Feature activation+1.16e-02

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
nces-0.005
28-0.005
Token cent
Token ID1247
Feature activation-2.39e-01

Pos logit contributions
outhern+0.014
 328+0.013
 fantasy+0.012
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.007
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token above
Token ID2029
Feature activation+4.07e-03

Pos logit contributions
 Zar+0.227
 Pax+0.220
+0.199
anch+0.195
 doi+0.191
Neg logit contributions
outhern-0.194
 328-0.171
 fantasy-0.164
nces-0.160
28-0.160
Token average
Token ID2811
Feature activation+4.50e-02

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.003
anch-0.003
 doi-0.003
Token U
Token ID471
Feature activation-1.06e-02

Pos logit contributions
outhern+0.035
 328+0.030
 fantasy+0.029
28+0.028
nces+0.028
Neg logit contributions
 Zar-0.045
 Pax-0.043
-0.040
anch-0.039
 doi-0.038
Token.
Token ID13
Feature activation+4.57e-03

Pos logit contributions
 Zar+0.010
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
TokenS
Token ID50
Feature activation-9.85e-03

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
 AD+0.003
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token examples
Token ID6096
Feature activation+9.72e-03

Pos logit contributions
 Zar+0.033
 Pax+0.032
+0.029
anch+0.029
 doi+0.028
Neg logit contributions
outhern-0.027
 328-0.024
 fantasy-0.023
28-0.022
nces-0.022
Token:
Token ID25
Feature activation-5.03e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token a
Token ID257
Feature activation+6.35e-03

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.004
nces-0.003
Token 90
Token ID4101
Feature activation-3.11e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Token per
Token ID583
Feature activation+1.59e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.002
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
nces-0.002
28-0.002
Token cent
Token ID1247
Feature activation-2.38e-01

Pos logit contributions
outhern+0.018
 328+0.017
 fantasy+0.016
28+0.016
 AD+0.016
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.007
Token reduction
Token ID7741
Feature activation+1.95e-02

Pos logit contributions
 Zar+0.225
 Pax+0.218
+0.199
anch+0.194
 doi+0.189
Neg logit contributions
outhern-0.195
 328-0.173
 fantasy-0.166
28-0.161
nces-0.161
Token in
Token ID287
Feature activation-1.34e-02

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.013
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.019
 Pax-0.019
-0.017
anch-0.017
 doi-0.016
Token HIV
Token ID10498
Feature activation-1.46e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.011
28-0.011
nces-0.011
Token-
Token ID12
Feature activation+5.63e-04

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.012
 328-0.011
 fantasy-0.011
28-0.010
nces-0.010
Tokenrelated
Token ID5363
Feature activation-1.01e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.000
anch-0.000
 doi-0.000
Token showed
Token ID3751
Feature activation-1.54e-02

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token that
Token ID326
Feature activation+1.78e-02

Pos logit contributions
 Zar+0.014
 Pax+0.014
+0.012
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.011
28-0.011
nces-0.011
Token about
Token ID546
Feature activation+1.50e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.012
nces+0.011
Neg logit contributions
 Zar-0.017
 Pax-0.017
-0.015
anch-0.015
 doi-0.015
Token 14
Token ID1478
Feature activation+4.85e-03

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.010
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.013
 doi-0.013
Token per
Token ID583
Feature activation+1.28e-02

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
nces+0.003
28+0.003
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.005
 doi-0.005
Token cent
Token ID1247
Feature activation-2.38e-01

Pos logit contributions
outhern+0.015
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.006
anch-0.006
 doi-0.006
Token of
Token ID286
Feature activation+4.39e-02

Pos logit contributions
 Zar+0.230
 Pax+0.222
+0.203
anch+0.198
 doi+0.194
Neg logit contributions
outhern-0.188
 328-0.167
 fantasy-0.160
28-0.155
nces-0.154
Token families
Token ID4172
Feature activation+3.50e-02

Pos logit contributions
outhern+0.040
 328+0.035
 fantasy+0.034
28+0.033
nces+0.033
Neg logit contributions
 Zar-0.038
 Pax-0.037
-0.033
anch-0.032
 doi-0.031
Token in
Token ID287
Feature activation+1.85e-02

Pos logit contributions
outhern+0.029
 328+0.026
 fantasy+0.025
28+0.024
nces+0.024
Neg logit contributions
 Zar-0.032
 Pax-0.031
-0.028
anch-0.028
 doi-0.027
Token traditionally
Token ID16083
Feature activation-3.23e-03

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.012
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.018
 Pax-0.018
-0.016
anch-0.016
 doi-0.015
Token middle
Token ID3504
Feature activation-2.23e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token as
Token ID355
Feature activation-4.01e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token much
Token ID881
Feature activation-2.20e-02

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token as
Token ID355
Feature activation-1.23e-02

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.020
anch+0.020
 doi+0.019
Neg logit contributions
outhern-0.016
 328-0.014
 fantasy-0.014
28-0.013
nces-0.013
Token 20
Token ID1160
Feature activation-6.84e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.014
 328-0.013
 fantasy-0.012
28-0.012
nces-0.012
Token per
Token ID583
Feature activation+4.74e-03

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
nces-0.004
28-0.004
Token cent
Token ID1247
Feature activation-2.37e-01

Pos logit contributions
outhern+0.005
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.002
anch-0.002
 doi-0.002
Token.
Token ID13
Feature activation-6.25e-03

Pos logit contributions
 Zar+0.228
 Pax+0.220
+0.201
anch+0.197
 doi+0.192
Neg logit contributions
outhern-0.190
 328-0.169
 fantasy-0.162
28-0.157
nces-0.155
Token
Token ID198
Feature activation+8.44e-03

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.005
 328-0.005
 fantasy-0.005
28-0.004
nces-0.004
Token
Token ID198
Feature activation+7.12e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
 AD+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
TokenAd
Token ID2782
Feature activation+1.31e-03

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Tokenvertising
Token ID31809
Feature activation-2.83e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token Not
Token ID1892
Feature activation+3.74e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.000
 doi-0.000
Tokenley
Token ID1636
Feature activation+1.78e-04

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token gathered
Token ID9272
Feature activation-5.94e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token 70
Token ID4317
Feature activation-1.32e-04

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token per
Token ID583
Feature activation+5.27e-03

Pos logit contributions
 Zar+0.000
 Pax+0.000
+0.000
anch+0.000
 doi+0.000
Neg logit contributions
outhern-0.000
 328-0.000
 fantasy-0.000
28-0.000
nces-0.000
Token cent
Token ID1247
Feature activation-2.36e-01

Pos logit contributions
outhern+0.006
 328+0.006
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.002
 doi-0.002
Token of
Token ID286
Feature activation+1.24e-02

Pos logit contributions
 Zar+0.233
 Pax+0.226
+0.206
anch+0.201
 doi+0.197
Neg logit contributions
outhern-0.182
 328-0.161
 fantasy-0.153
nces-0.148
28-0.148
Token the
Token ID262
Feature activation+3.92e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.009
 doi-0.009
Token votes
Token ID5690
Feature activation-9.76e-03

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.006
Token (
Token ID357
Feature activation-1.38e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.012
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token they
Token ID484
Feature activation+2.03e-03

Pos logit contributions
outhern+0.002
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.001
Token're
Token ID821
Feature activation+5.73e-04

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token making
Token ID1642
Feature activation+2.67e-03

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.000
anch-0.000
 doi-0.000
Token 20
Token ID1160
Feature activation-7.06e-03

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token per
Token ID583
Feature activation+8.59e-03

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token cent
Token ID1247
Feature activation-2.35e-01

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token more
Token ID517
Feature activation-1.30e-02

Pos logit contributions
 Zar+0.240
 Pax+0.233
+0.213
anch+0.208
 doi+0.205
Neg logit contributions
outhern-0.176
 328-0.154
 fantasy-0.147
28-0.142
nces-0.141
Token than
Token ID621
Feature activation-1.19e-02

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.011
 doi+0.010
Neg logit contributions
outhern-0.011
 328-0.009
 fantasy-0.009
28-0.009
nces-0.009
Token their
Token ID511
Feature activation+1.46e-02

Pos logit contributions
 Zar+0.011
 Pax+0.011
+0.010
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
Token private
Token ID2839
Feature activation+8.49e-04

Pos logit contributions
outhern+0.010
 328+0.008
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.016
 Pax-0.015
-0.014
anch-0.014
 doi-0.014
Token sector
Token ID6567
Feature activation-4.32e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
 Zar+0.051
 Pax+0.049
+0.045
anch+0.044
 doi+0.043
Neg logit contributions
outhern-0.043
 328-0.039
 fantasy-0.037
28-0.036
nces-0.036
Token or
Token ID393
Feature activation-2.10e-02

Pos logit contributions
 Zar+0.010
 Pax+0.009
+0.009
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Token about
Token ID546
Feature activation+2.95e-03

Pos logit contributions
 Zar+0.020
 Pax+0.020
+0.018
anch+0.017
 doi+0.017
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.014
Token three
Token ID1115
Feature activation-7.95e-03

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.002
 doi-0.002
Token per
Token ID583
Feature activation+8.62e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token cent
Token ID1247
Feature activation-2.33e-01

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token of
Token ID286
Feature activation+1.23e-02

Pos logit contributions
 Zar+0.232
 Pax+0.224
+0.206
anch+0.201
 doi+0.197
Neg logit contributions
outhern-0.179
 328-0.158
 fantasy-0.152
28-0.147
nces-0.145
Token the
Token ID262
Feature activation-3.33e-03

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.012
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token 9
Token ID860
Feature activation+5.65e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token,
Token ID11
Feature activation+1.35e-02

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.004
nces+0.004
28+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.005
-0.005
anch-0.005
 doi-0.005
Token204
Token ID18638
Feature activation+8.72e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.010
nces+0.009
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.011
anch-0.011
 doi-0.010
Token likelihood
Token ID14955
Feature activation-1.41e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token is
Token ID318
Feature activation-3.37e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token that
Token ID326
Feature activation-3.36e-02

Pos logit contributions
 Zar+0.032
 Pax+0.030
+0.028
anch+0.027
 doi+0.026
Neg logit contributions
outhern-0.028
 328-0.025
 fantasy-0.024
28-0.023
nces-0.023
Token 50
Token ID2026
Feature activation-1.79e-02

Pos logit contributions
 Zar+0.030
 Pax+0.029
+0.026
anch+0.026
 doi+0.025
Neg logit contributions
outhern-0.029
 328-0.026
 fantasy-0.025
28-0.024
nces-0.024
Token per
Token ID583
Feature activation+5.96e-03

Pos logit contributions
 Zar+0.020
 Pax+0.019
+0.018
anch+0.017
 doi+0.017
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.009
nces-0.009
Token cent
Token ID1247
Feature activation-2.33e-01

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.004
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Token of
Token ID286
Feature activation-8.42e-03

Pos logit contributions
 Zar+0.221
 Pax+0.213
+0.195
anch+0.189
 doi+0.186
Neg logit contributions
outhern-0.190
 328-0.169
 fantasy-0.162
28-0.157
nces-0.156
Token turtles
Token ID36288
Feature activation+2.56e-02

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.007
 328-0.006
 fantasy-0.006
28-0.006
nces-0.006
Token that
Token ID326
Feature activation-1.37e-02

Pos logit contributions
outhern+0.023
 328+0.021
 fantasy+0.020
28+0.020
nces+0.020
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.018
 doi-0.018
Token eat
Token ID4483
Feature activation+5.51e-03

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.012
 328-0.011
 fantasy-0.010
28-0.010
nces-0.010
Token fewer
Token ID7380
Feature activation+1.69e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token estimate
Token ID8636
Feature activation+4.27e-02

Pos logit contributions
 Zar+0.019
 Pax+0.018
+0.016
anch+0.016
 doi+0.016
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.017
Token that
Token ID326
Feature activation-7.59e-02

Pos logit contributions
outhern+0.038
 328+0.034
 fantasy+0.033
28+0.032
nces+0.031
Neg logit contributions
 Zar-0.038
 Pax-0.036
-0.033
anch-0.032
 doi-0.031
Token over
Token ID625
Feature activation-2.76e-02

Pos logit contributions
 Zar+0.068
 Pax+0.065
+0.059
anch+0.057
 doi+0.056
Neg logit contributions
outhern-0.066
 328-0.059
 fantasy-0.057
28-0.056
nces-0.055
Token 50
Token ID2026
Feature activation-1.69e-02

Pos logit contributions
 Zar+0.027
 Pax+0.026
+0.024
anch+0.023
 doi+0.023
Neg logit contributions
outhern-0.022
 328-0.019
 fantasy-0.019
28-0.018
nces-0.018
Token per
Token ID583
Feature activation+2.42e-03

Pos logit contributions
 Zar+0.017
 Pax+0.016
+0.015
anch+0.014
 doi+0.014
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.011
28-0.011
nces-0.011
Token cent
Token ID1247
Feature activation-2.32e-01

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token of
Token ID286
Feature activation+4.01e-03

Pos logit contributions
 Zar+0.227
 Pax+0.219
+0.201
anch+0.195
 doi+0.192
Neg logit contributions
outhern-0.183
 328-0.161
 fantasy-0.155
28-0.149
nces-0.149
Token sea
Token ID5417
Feature activation+2.41e-02

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.003
anch-0.003
 doi-0.003
Token turtles
Token ID36288
Feature activation+4.60e-02

Pos logit contributions
outhern+0.020
 328+0.017
 fantasy+0.017
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.020
 doi-0.019
Token around
Token ID1088
Feature activation-3.45e-02

Pos logit contributions
outhern+0.038
 328+0.034
 fantasy+0.033
28+0.032
nces+0.032
Neg logit contributions
 Zar-0.043
 Pax-0.041
-0.038
anch-0.037
 doi-0.036
Token the
Token ID262
Feature activation-1.70e-03

Pos logit contributions
 Zar+0.031
 Pax+0.030
+0.027
anch+0.027
 doi+0.026
Neg logit contributions
outhern-0.030
 328-0.027
 fantasy-0.026
28-0.025
nces-0.024
Tokenost
Token ID455
Feature activation-5.00e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
ungle+0.004
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.002
 doi-0.002
Tokenino
Token ID2879
Feature activation-1.66e-02

Pos logit contributions
 Zar+0.051
 Pax+0.049
+0.045
anch+0.044
 doi+0.043
Neg logit contributions
outhern-0.037
 328-0.033
 fantasy-0.032
28-0.030
nces-0.030
Token says
Token ID1139
Feature activation-1.11e-02

Pos logit contributions
 Zar+0.015
 Pax+0.014
+0.013
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.015
 328-0.013
 fantasy-0.013
28-0.012
nces-0.012
Token 14
Token ID1478
Feature activation-5.36e-03

Pos logit contributions
 Zar+0.011
 Pax+0.011
+0.010
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Token per
Token ID583
Feature activation-9.29e-03

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token cent
Token ID1247
Feature activation-2.31e-01

Pos logit contributions
 Zar+0.006
 Pax+0.005
+0.005
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.010
28-0.010
nces-0.009
Token of
Token ID286
Feature activation+1.69e-02

Pos logit contributions
 Zar+0.224
 Pax+0.216
+0.197
anch+0.193
 doi+0.189
Neg logit contributions
outhern-0.184
 328-0.163
 fantasy-0.154
28-0.150
nces-0.150
Token families
Token ID4172
Feature activation+4.12e-04

Pos logit contributions
outhern+0.011
 328+0.009
 fantasy+0.009
nces+0.009
28+0.008
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.017
anch-0.017
 doi-0.016
Token struggling
Token ID9648
Feature activation-1.36e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token to
Token ID284
Feature activation-1.10e-02

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.011
 doi+0.010
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.010
28-0.010
nces-0.009
Token afford
Token ID5368
Feature activation+8.83e-04

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.007
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.009
nces-0.009
Token year
Token ID614
Feature activation-1.87e-02

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.012
 doi+0.011
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
Token and
Token ID290
Feature activation+8.32e-03

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.016
anch+0.016
 doi+0.015
Neg logit contributions
outhern-0.015
 328-0.013
 fantasy-0.013
28-0.012
nces-0.012
Token then
Token ID788
Feature activation+7.29e-04

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.006
 doi-0.006
Token two
Token ID734
Feature activation-1.37e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token per
Token ID583
Feature activation+4.16e-03

Pos logit contributions
 Zar+0.015
 Pax+0.015
+0.013
anch+0.013
 doi+0.013
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
Token cent
Token ID1247
Feature activation-2.31e-01

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
 AD+0.004
Neg logit contributions
 Zar-0.003
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token in
Token ID287
Feature activation+1.34e-02

Pos logit contributions
 Zar+0.223
 Pax+0.216
+0.197
anch+0.192
 doi+0.189
Neg logit contributions
outhern-0.184
 328-0.163
 fantasy-0.156
28-0.152
nces-0.150
Token both
Token ID1111
Feature activation+4.35e-03

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.011
anch-0.010
 doi-0.010
Token of
Token ID286
Feature activation+1.42e-02

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token the
Token ID262
Feature activation+2.07e-03

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.011
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.013
 Pax-0.012
-0.011
anch-0.011
 doi-0.011
Token following
Token ID1708
Feature activation-2.87e-02

Pos logit contributions
outhern+0.002
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token we
Token ID356
Feature activation+5.68e-03

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.020
anch+0.019
 doi+0.019
Neg logit contributions
outhern-0.024
 328-0.022
 fantasy-0.021
28-0.020
nces-0.020
Token know
Token ID760
Feature activation-1.29e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token that
Token ID326
Feature activation-2.35e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token 50
Token ID2026
Feature activation-3.14e-02

Pos logit contributions
 Zar+0.021
 Pax+0.021
+0.019
anch+0.018
 doi+0.018
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.017
Token per
Token ID583
Feature activation+2.59e-04

Pos logit contributions
 Zar+0.035
 Pax+0.034
+0.031
anch+0.030
 doi+0.030
Neg logit contributions
outhern-0.021
 328-0.018
 fantasy-0.017
28-0.016
nces-0.016
Token cent
Token ID1247
Feature activation-2.30e-01

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token of
Token ID286
Feature activation+1.06e-02

Pos logit contributions
 Zar+0.221
 Pax+0.213
+0.195
anch+0.190
 doi+0.187
Neg logit contributions
outhern-0.185
 328-0.164
 fantasy-0.157
28-0.152
nces-0.151
Token turtles
Token ID36288
Feature activation+2.33e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.009
anch-0.009
 doi-0.008
Token have
Token ID423
Feature activation-7.16e-03

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.016
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.019
 doi-0.019
Token eaten
Token ID17065
Feature activation-2.05e-02

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token debris
Token ID16468
Feature activation-3.77e-02

Pos logit contributions
 Zar+0.018
 Pax+0.018
+0.016
anch+0.016
 doi+0.015
Neg logit contributions
outhern-0.018
 328-0.016
 fantasy-0.015
28-0.015
nces-0.015
Token of
Token ID286
Feature activation+1.17e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
Token the
Token ID262
Feature activation+1.19e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.010
-0.009
anch-0.009
 doi-0.009
Token
Token ID564
Feature activation+8.32e-03

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token
Token ID246
Feature activation-2.32e-02

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
Tokendel
Token ID12381
Feature activation+4.39e-02

Pos logit contributions
 Zar+0.024
 Pax+0.023
+0.022
anch+0.021
 doi+0.021
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.013
Tokenayed
Token ID16548
Feature activation-2.29e-01

Pos logit contributions
outhern+0.057
 328+0.053
 fantasy+0.052
28+0.051
nces+0.050
Neg logit contributions
 Zar-0.021
 Pax-0.019
-0.016
anch-0.014
 doi-0.014
Token unfolding
Token ID34502
Feature activation-4.40e-03

Pos logit contributions
 Zar+0.205
 Pax+0.198
+0.179
anch+0.174
 doi+0.171
Neg logit contributions
outhern-0.199
 328-0.179
 fantasy-0.173
28-0.168
nces-0.165
Token of
Token ID286
Feature activation-9.00e-03

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token independence
Token ID10404
Feature activation-3.39e-02

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.008
 328-0.008
 fantasy-0.007
28-0.007
nces-0.007
Token
Token ID447
Feature activation+1.10e-02

Pos logit contributions
 Zar+0.029
 Pax+0.028
+0.025
anch+0.025
 doi+0.024
Neg logit contributions
outhern-0.031
 328-0.028
 fantasy-0.027
28-0.026
nces-0.026
Token
Token ID247
Feature activation+3.13e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
nces+0.003
28+0.003
Neg logit contributions
 Zar-0.014
 Pax-0.014
-0.013
anch-0.013
 doi-0.013
Token finance
Token ID9604
Feature activation-4.90e-03

Pos logit contributions
 Zar+0.045
 Pax+0.043
+0.039
anch+0.038
 doi+0.037
Neg logit contributions
outhern-0.048
 328-0.043
 fantasy-0.042
28-0.041
nces-0.040
Token is
Token ID318
Feature activation-1.21e-02

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token growing
Token ID3957
Feature activation-3.74e-02

Pos logit contributions
 Zar+0.011
 Pax+0.011
+0.010
anch+0.010
 doi+0.009
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.009
28-0.008
nces-0.008
Token 50
Token ID2026
Feature activation-4.10e-03

Pos logit contributions
 Zar+0.037
 Pax+0.036
+0.033
anch+0.032
 doi+0.031
Neg logit contributions
outhern-0.029
 328-0.026
 fantasy-0.025
28-0.024
nces-0.023
Token per
Token ID583
Feature activation+9.75e-03

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.003
28-0.002
nces-0.002
Token cent
Token ID1247
Feature activation-2.28e-01

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.004
Token faster
Token ID5443
Feature activation+1.29e-02

Pos logit contributions
 Zar+0.228
 Pax+0.221
+0.202
anch+0.197
 doi+0.194
Neg logit contributions
outhern-0.174
 328-0.154
 fantasy-0.148
28-0.143
nces-0.141
Token than
Token ID621
Feature activation-5.98e-02

Pos logit contributions
outhern+0.011
 328+0.009
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.011
anch-0.010
 doi-0.010
Token traditional
Token ID4569
Feature activation-7.73e-03

Pos logit contributions
 Zar+0.061
 Pax+0.059
+0.054
anch+0.053
 doi+0.052
Neg logit contributions
outhern-0.045
 328-0.039
 fantasy-0.038
28-0.037
nces-0.036
Token banking
Token ID11754
Feature activation-4.01e-02

Pos logit contributions
 Zar+0.008
 Pax+0.007
+0.007
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token
Token ID447
Feature activation+9.18e-03

Pos logit contributions
 Zar+0.038
 Pax+0.036
+0.033
anch+0.032
 doi+0.032
Neg logit contributions
outhern-0.033
 328-0.030
 fantasy-0.029
28-0.028
nces-0.027
Token3
Token ID18
Feature activation-1.05e-02

Pos logit contributions
outhern+0.028
 328+0.024
 fantasy+0.023
28+0.022
nces+0.022
Neg logit contributions
 Zar-0.042
 Pax-0.041
-0.037
anch-0.037
 doi-0.036
Token model
Token ID2746
Feature activation+2.31e-02

Pos logit contributions
 Zar+0.010
 Pax+0.009
+0.008
anch+0.008
 doi+0.008
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Token is
Token ID318
Feature activation-3.30e-03

Pos logit contributions
outhern+0.021
 328+0.018
 fantasy+0.018
nces+0.017
28+0.017
Neg logit contributions
 Zar-0.020
 Pax-0.019
-0.018
anch-0.017
 doi-0.017
Token clearly
Token ID4084
Feature activation-4.16e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token distinguish
Token ID15714
Feature activation+2.11e-02

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Tokenable
Token ID540
Feature activation+1.64e-01

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.024
 Pax-0.023
-0.021
anch-0.021
 doi-0.020
Token from
Token ID422
Feature activation+7.01e-02

Pos logit contributions
outhern+0.126
 328+0.111
 fantasy+0.106
28+0.103
nces+0.101
Neg logit contributions
 Zar-0.164
 Pax-0.159
-0.145
anch-0.142
 doi-0.139
Token its
Token ID663
Feature activation+2.52e-02

Pos logit contributions
outhern+0.061
 328+0.054
 fantasy+0.053
28+0.051
nces+0.050
Neg logit contributions
 Zar-0.063
 Pax-0.061
-0.055
anch-0.054
 doi-0.052
Token earlier
Token ID2961
Feature activation+1.28e-02

Pos logit contributions
outhern+0.019
 328+0.016
 fantasy+0.016
nces+0.015
28+0.015
Neg logit contributions
 Zar-0.026
 Pax-0.025
-0.023
anch-0.022
 doi-0.022
Token predecessor
Token ID18476
Feature activation-2.76e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.011
anch-0.010
 doi-0.010
Token,
Token ID11
Feature activation-7.70e-03

Pos logit contributions
 Zar+0.026
 Pax+0.025
+0.023
anch+0.022
 doi+0.022
Neg logit contributions
outhern-0.023
 328-0.020
 fantasy-0.019
28-0.019
nces-0.018
Token the
Token ID262
Feature activation+1.81e-03

Pos logit contributions
outhern+0.014
 328+0.013
 fantasy+0.013
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.013
 doi-0.012
Token police
Token ID1644
Feature activation+9.25e-03

Pos logit contributions
outhern+0.002
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.001
anch-0.001
 doi-0.001
Token stations
Token ID8985
Feature activation+8.27e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.010
28+0.009
 AD+0.009
Neg logit contributions
 Zar-0.006
 Pax-0.005
-0.005
anch-0.004
 doi-0.004
Token were
Token ID547
Feature activation+2.38e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.007
 doi-0.006
Token barric
Token ID31853
Feature activation+1.69e-02

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.017
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.019
 doi-0.019
Tokenades
Token ID2367
Feature activation+1.42e-01

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.020
 Pax-0.020
-0.019
anch-0.018
 doi-0.018
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
outhern+0.123
 328+0.110
 fantasy+0.107
28+0.103
nces+0.102
Neg logit contributions
 Zar-0.128
 Pax-0.124
-0.112
anch-0.109
 doi-0.107
Token other
Token ID584
Feature activation+1.46e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.007
Token signs
Token ID5895
Feature activation+5.68e-03

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.012
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.012
 Pax-0.012
-0.011
anch-0.010
 doi-0.010
Token of
Token ID286
Feature activation+2.26e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.005
 doi-0.004
Token security
Token ID2324
Feature activation+3.23e-02

Pos logit contributions
outhern+0.020
 328+0.018
 fantasy+0.017
28+0.017
nces+0.016
Neg logit contributions
 Zar-0.020
 Pax-0.019
-0.018
anch-0.017
 doi-0.017
TokenERS
Token ID4877
Feature activation+2.62e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.012
Token ALL
Token ID11096
Feature activation+7.36e-03

Pos logit contributions
outhern+0.021
 328+0.019
 fantasy+0.018
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.025
 Pax-0.024
-0.022
anch-0.022
 doi-0.021
Token V
Token ID569
Feature activation+1.74e-02

Pos logit contributions
outhern+0.005
 328+0.005
 fantasy+0.005
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.008
 Pax-0.007
-0.007
anch-0.007
 doi-0.006
TokenEH
Token ID42413
Feature activation+2.02e-02

Pos logit contributions
outhern+0.015
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.013
anch-0.013
 doi-0.013
TokenIC
Token ID2149
Feature activation+4.13e-02

Pos logit contributions
outhern+0.017
 328+0.015
 fantasy+0.015
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.016
anch-0.016
 doi-0.016
TokenLES
Token ID28378
Feature activation+2.07e-01

Pos logit contributions
outhern+0.018
 328+0.014
 fantasy+0.013
nces+0.012
28+0.012
Neg logit contributions
 Zar-0.055
 Pax-0.054
-0.050
anch-0.049
 doi-0.049
Token,
Token ID11
Feature activation+8.78e-03

Pos logit contributions
outhern+0.163
 328+0.144
 fantasy+0.139
28+0.134
nces+0.132
Neg logit contributions
 Zar-0.203
 Pax-0.197
-0.180
anch-0.176
 doi-0.172
Token LAT
Token ID42355
Feature activation+5.49e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
TokenR
Token ID49
Feature activation+2.26e-02

Pos logit contributions
outhern+0.042
 328+0.037
 fantasy+0.035
28+0.034
nces+0.034
Neg logit contributions
 Zar-0.055
 Pax-0.054
-0.049
anch-0.048
 doi-0.047
TokenIN
Token ID1268
Feature activation-2.25e-02

Pos logit contributions
outhern+0.018
 328+0.016
 fantasy+0.015
nces+0.015
28+0.015
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.019
 doi-0.018
TokenES
Token ID1546
Feature activation-1.46e-02

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.020
anch+0.020
 doi+0.019
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.014
28-0.014
nces-0.014
Token never
Token ID1239
Feature activation+8.76e-03

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.013
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token called
Token ID1444
Feature activation-6.08e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.007
 Pax-0.007
-0.006
anch-0.006
 doi-0.006
Token.
Token ID13
Feature activation+1.35e-03

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.005
anch+0.005
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.005
 fantasy-0.005
28-0.005
nces-0.004
Token pic
Token ID8301
Feature activation+1.70e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token.
Token ID13
Feature activation-6.91e-03

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
 AD+0.011
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Tokentwitter
Token ID6956
Feature activation+1.53e-01

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.006
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token.
Token ID13
Feature activation-1.18e-02

Pos logit contributions
outhern+0.118
 328+0.105
 fantasy+0.101
28+0.099
 AD+0.095
Neg logit contributions
 Zar-0.151
 Pax-0.147
-0.134
anch-0.130
 doi-0.127
Tokencom
Token ID785
Feature activation-2.49e-02

Pos logit contributions
 Zar+0.014
 Pax+0.014
+0.013
anch+0.013
 doi+0.012
Neg logit contributions
outhern-0.007
 328-0.006
 fantasy-0.005
28-0.005
nces-0.005
Token/
Token ID14
Feature activation-3.79e-02

Pos logit contributions
 Zar+0.026
 Pax+0.025
+0.023
anch+0.023
 doi+0.022
Neg logit contributions
outhern-0.018
 328-0.016
 fantasy-0.015
28-0.014
nces-0.014
TokenCS
Token ID7902
Feature activation-6.28e-03

Pos logit contributions
 Zar+0.036
 Pax+0.034
+0.031
anch+0.031
 doi+0.030
Neg logit contributions
outhern-0.031
 328-0.028
 fantasy-0.027
28-0.026
nces-0.026
Token3
Token ID18
Feature activation+1.39e-02

Pos logit contributions
 Zar+0.006
 Pax+0.006
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.005
 328-0.005
 fantasy-0.005
28-0.004
nces-0.004
Token media
Token ID2056
Feature activation-2.42e-03

Pos logit contributions
outhern+0.020
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.020
 doi-0.019
Token bus
Token ID1323
Feature activation+1.69e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token)
Token ID8
Feature activation+1.10e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.016
 Pax-0.015
-0.014
anch-0.014
 doi-0.013
Token pic
Token ID8301
Feature activation+2.60e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token.
Token ID13
Feature activation-3.06e-02

Pos logit contributions
outhern+0.020
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.025
 Pax-0.025
-0.023
anch-0.022
 doi-0.021
Tokentwitter
Token ID6956
Feature activation+1.58e-01

Pos logit contributions
 Zar+0.028
 Pax+0.028
+0.025
anch+0.024
 doi+0.024
Neg logit contributions
outhern-0.025
 328-0.023
 fantasy-0.022
28-0.022
nces-0.021
Token.
Token ID13
Feature activation-2.32e-02

Pos logit contributions
outhern+0.122
 328+0.110
 fantasy+0.105
28+0.103
 AD+0.099
Neg logit contributions
 Zar-0.156
 Pax-0.151
-0.138
anch-0.135
 doi-0.131
Tokencom
Token ID785
Feature activation-1.40e-02

Pos logit contributions
 Zar+0.028
 Pax+0.027
+0.025
anch+0.025
 doi+0.024
Neg logit contributions
outhern-0.013
 328-0.011
 fantasy-0.010
28-0.010
nces-0.010
Token/
Token ID14
Feature activation-4.31e-02

Pos logit contributions
 Zar+0.015
 Pax+0.014
+0.013
anch+0.013
 doi+0.013
Neg logit contributions
outhern-0.010
 328-0.009
 fantasy-0.008
28-0.008
nces-0.008
Tokenz
Token ID89
Feature activation-2.17e-02

Pos logit contributions
 Zar+0.041
 Pax+0.039
+0.036
anch+0.035
 doi+0.034
Neg logit contributions
outhern-0.035
 328-0.032
 fantasy-0.031
28-0.029
nces-0.029
TokenJ
Token ID41
Feature activation-4.19e-03

Pos logit contributions
 Zar+0.021
 Pax+0.020
+0.018
anch+0.018
 doi+0.017
Neg logit contributions
outhern-0.018
 328-0.016
 fantasy-0.015
28-0.015
nces-0.015
Token some
Token ID617
Feature activation+2.83e-03

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.013
anch-0.013
 doi-0.013
Token.
Token ID13
Feature activation-5.75e-03

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.002
anch-0.002
 doi-0.002
Token Similarly
Token ID15298
Feature activation-5.04e-03

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.005
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
nces-0.004
28-0.004
Token,
Token ID11
Feature activation-3.21e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.003
nces-0.003
Token millions
Token ID5242
Feature activation+1.66e-02

Pos logit contributions
 Zar+0.030
 Pax+0.029
+0.026
anch+0.026
 doi+0.025
Neg logit contributions
outhern-0.027
 328-0.024
 fantasy-0.023
28-0.022
nces-0.022
Token of
Token ID286
Feature activation+2.88e-02

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token post
Token ID1281
Feature activation+3.03e-02

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.018
nces+0.018
Neg logit contributions
 Zar-0.029
 Pax-0.028
-0.025
anch-0.025
 doi-0.024
Tokenmen
Token ID3653
Feature activation+4.52e-02

Pos logit contributions
outhern+0.025
 328+0.022
 fantasy+0.021
28+0.021
nces+0.020
Neg logit contributions
 Zar-0.029
 Pax-0.028
-0.025
anch-0.025
 doi-0.024
Tokenopausal
Token ID47637
Feature activation+3.56e-03

Pos logit contributions
outhern+0.040
 328+0.036
 fantasy+0.035
nces+0.034
28+0.033
Neg logit contributions
 Zar-0.040
 Pax-0.038
-0.035
anch-0.034
 doi-0.033
Token women
Token ID1466
Feature activation+1.04e-02

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
nces+0.002
28+0.002
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token were
Token ID547
Feature activation-1.01e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.009
anch-0.008
 doi-0.008
Token Canada
Token ID3340
Feature activation-2.30e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token and
Token ID290
Feature activation+1.52e-02

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.019
anch+0.018
 doi+0.018
Neg logit contributions
outhern-0.019
 328-0.017
 fantasy-0.016
28-0.016
nces-0.016
Token the
Token ID262
Feature activation-1.63e-03

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.011
Token United
Token ID1578
Feature activation-1.60e-03

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token States
Token ID1829
Feature activation-5.22e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token widened
Token ID36405
Feature activation+3.04e-02

Pos logit contributions
 Zar+0.045
 Pax+0.043
+0.039
anch+0.038
 doi+0.037
Neg logit contributions
outhern-0.047
 328-0.042
 fantasy-0.041
28-0.040
nces-0.039
Token to
Token ID284
Feature activation-9.18e-03

Pos logit contributions
outhern+0.023
 328+0.020
 fantasy+0.020
28+0.019
nces+0.019
Neg logit contributions
 Zar-0.030
 Pax-0.029
-0.027
anch-0.026
 doi-0.026
Token a
Token ID257
Feature activation-1.72e-03

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
Token record
Token ID1700
Feature activation-8.33e-03

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token level
Token ID1241
Feature activation-1.54e-02

Pos logit contributions
 Zar+0.008
 Pax+0.008
+0.007
anch+0.007
 doi+0.007
Neg logit contributions
outhern-0.007
 328-0.006
 fantasy-0.006
28-0.005
nces-0.005
Token in
Token ID287
Feature activation-1.10e-02

Pos logit contributions
 Zar+0.015
 Pax+0.015
+0.014
anch+0.013
 doi+0.013
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.010
nces-0.010
Token the
Token ID262
Feature activation-1.54e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.005
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token alleged
Token ID4260
Feature activation+3.82e-02

Pos logit contributions
 Zar+0.014
 Pax+0.013
+0.012
anch+0.012
 doi+0.011
Neg logit contributions
outhern-0.013
 328-0.012
 fantasy-0.012
28-0.011
nces-0.011
Token victim
Token ID3117
Feature activation+4.84e-03

Pos logit contributions
outhern+0.021
 328+0.017
 fantasy+0.016
28+0.016
nces+0.015
Neg logit contributions
 Zar-0.047
 Pax-0.045
-0.042
anch-0.041
 doi-0.041
Token and
Token ID290
Feature activation-1.44e-02

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token at
Token ID379
Feature activation+6.15e-03

Pos logit contributions
 Zar+0.014
 Pax+0.013
+0.012
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.010
nces-0.009
Token least
Token ID1551
Feature activation+2.01e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Token one
Token ID530
Feature activation-1.29e-02

Pos logit contributions
outhern+0.016
 328+0.015
 fantasy+0.014
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.017
anch-0.016
 doi-0.016
Token of
Token ID286
Feature activation-9.65e-03

Pos logit contributions
 Zar+0.013
 Pax+0.013
+0.012
anch+0.012
 doi+0.011
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Token the
Token ID262
Feature activation-1.05e-03

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.007
Neg logit contributions
outhern-0.008
 328-0.007
 fantasy-0.007
28-0.007
nces-0.007
Token arresting
Token ID33936
Feature activation-4.73e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token officers
Token ID3790
Feature activation-2.20e-02

Pos logit contributions
 Zar+0.035
 Pax+0.033
+0.030
anch+0.028
 doi+0.028
Neg logit contributions
outhern-0.049
 328-0.044
 fantasy-0.043
28-0.042
nces-0.042
Token,
Token ID11
Feature activation+9.48e-03

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.012
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Token and
Token ID290
Feature activation+5.80e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token they
Token ID484
Feature activation+1.84e-02

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.005
 doi-0.004
Token wouldn
Token ID3636
Feature activation+2.02e-02

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Token't
Token ID470
Feature activation+4.24e-02

Pos logit contributions
outhern+0.016
 328+0.015
 fantasy+0.014
28+0.014
nces+0.013
Neg logit contributions
 Zar-0.019
 Pax-0.018
-0.017
anch-0.016
 doi-0.016
Token push
Token ID4574
Feature activation+1.82e-02

Pos logit contributions
outhern+0.037
 328+0.033
 fantasy+0.032
nces+0.031
28+0.031
Neg logit contributions
 Zar-0.038
 Pax-0.036
-0.032
anch-0.032
 doi-0.031
Token two
Token ID734
Feature activation-1.29e-02

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.014
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token tables
Token ID8893
Feature activation+1.22e-02

Pos logit contributions
 Zar+0.012
 Pax+0.011
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Token together
Token ID1978
Feature activation-4.07e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.012
 Pax-0.011
-0.010
anch-0.010
 doi-0.010
Token to
Token ID284
Feature activation-5.60e-03

Pos logit contributions
 Zar+0.039
 Pax+0.038
+0.034
anch+0.033
 doi+0.033
Neg logit contributions
outhern-0.033
 328-0.029
 fantasy-0.028
28-0.027
nces-0.027
Token accommodate
Token ID15550
Feature activation+1.29e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Tokenap
Token ID499
Feature activation-1.38e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token the
Token ID262
Feature activation+9.39e-03

Pos logit contributions
 Zar+0.013
 Pax+0.012
+0.011
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.010
nces-0.010
Token file
Token ID2393
Feature activation+4.06e-02

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token,
Token ID11
Feature activation+7.99e-03

Pos logit contributions
outhern+0.033
 328+0.030
 fantasy+0.029
28+0.028
nces+0.028
Neg logit contributions
 Zar-0.038
 Pax-0.037
-0.034
anch-0.033
 doi-0.032
Token this
Token ID428
Feature activation+1.15e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.007
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Token code
Token ID2438
Feature activation+2.52e-02

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token would
Token ID561
Feature activation+9.25e-03

Pos logit contributions
outhern+0.024
 328+0.021
 fantasy+0.021
28+0.020
nces+0.020
Neg logit contributions
 Zar-0.021
 Pax-0.020
-0.018
anch-0.017
 doi-0.017
Token actually
Token ID1682
Feature activation+5.32e-03

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token run
Token ID1057
Feature activation+9.10e-05

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token really
Token ID1107
Feature activation-1.03e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token fast
Token ID3049
Feature activation-1.67e-02

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.011
 doi+0.010
Neg logit contributions
outhern-0.006
 328-0.005
 fantasy-0.005
28-0.005
nces-0.005
Token an
Token ID281
Feature activation+1.45e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.009
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.008
anch-0.008
 doi-0.008
Token interview
Token ID2720
Feature activation+1.18e-02

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.012
Token on
Token ID319
Feature activation+2.06e-02

Pos logit contributions
outhern+0.010
 328+0.009
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.009
Token 26
Token ID2608
Feature activation-3.03e-03

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.013
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.021
 Pax-0.020
-0.018
anch-0.018
 doi-0.017
Token May
Token ID1737
Feature activation-1.24e-02

Pos logit contributions
 Zar+0.003
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token 1965
Token ID17672
Feature activation+2.14e-03

Pos logit contributions
 Zar+0.013
 Pax+0.012
+0.011
anch+0.011
 doi+0.011
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
Token,
Token ID11
Feature activation+2.01e-02

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.002
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Token Zh
Token ID10511
Feature activation-1.26e-03

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.016
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.017
 Pax-0.016
-0.015
anch-0.014
 doi-0.014
Tokenuk
Token ID2724
Feature activation+3.70e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Tokenov
Token ID709
Feature activation-2.49e-02

Pos logit contributions
outhern+0.033
 328+0.030
 fantasy+0.029
28+0.028
nces+0.028
Neg logit contributions
 Zar-0.032
 Pax-0.031
-0.028
anch-0.027
 doi-0.027
Token stated
Token ID5081
Feature activation+7.91e-03

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.019
anch+0.018
 doi+0.018
Neg logit contributions
outhern-0.022
 328-0.020
 fantasy-0.019
28-0.019
nces-0.019
Tokentten
Token ID32407
Feature activation+4.57e-02

Pos logit contributions
outhern+0.017
 328+0.015
 fantasy+0.014
28+0.014
nces+0.014
Neg logit contributions
 Zar-0.019
 Pax-0.019
-0.017
anch-0.017
 doi-0.016
Token
Token ID784
Feature activation+1.66e-02

Pos logit contributions
outhern+0.039
 328+0.035
 fantasy+0.034
28+0.033
nces+0.033
Neg logit contributions
 Zar-0.041
 Pax-0.040
-0.036
anch-0.035
 doi-0.034
Token who
Token ID508
Feature activation+3.01e-02

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.013
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.012
 doi-0.012
Token released
Token ID2716
Feature activation+3.43e-02

Pos logit contributions
outhern+0.026
 328+0.023
 fantasy+0.023
28+0.022
nces+0.022
Neg logit contributions
 Zar-0.027
 Pax-0.026
-0.024
anch-0.023
 doi-0.023
Token her
Token ID607
Feature activation+1.90e-02

Pos logit contributions
outhern+0.028
 328+0.025
 fantasy+0.024
28+0.023
nces+0.023
Neg logit contributions
 Zar-0.033
 Pax-0.032
-0.029
anch-0.028
 doi-0.028
Token fourth
Token ID5544
Feature activation-6.90e-04

Pos logit contributions
outhern+0.012
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.020
anch-0.019
 doi-0.019
Token album
Token ID5062
Feature activation+1.73e-02

Pos logit contributions
 Zar+0.001
 Pax+0.001
+0.001
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.001
 328-0.001
 fantasy-0.001
28-0.001
nces-0.001
Token
Token ID564
Feature activation+1.56e-02

Pos logit contributions
outhern+0.014
 328+0.013
 fantasy+0.012
28+0.012
nces+0.012
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token
Token ID246
Feature activation+6.32e-03

Pos logit contributions
outhern+0.012
 328+0.011
 fantasy+0.010
28+0.010
nces+0.010
Neg logit contributions
 Zar-0.016
 Pax-0.015
-0.014
anch-0.014
 doi-0.013
TokenAre
Token ID8491
Feature activation-5.52e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.006
anch-0.005
 doi-0.005
Token We
Token ID775
Feature activation+1.40e-01

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.005
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token owned
Token ID6898
Feature activation-1.13e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.002
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token by
Token ID416
Feature activation-3.86e-03

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Token Alex
Token ID4422
Feature activation-1.25e-02

Pos logit contributions
 Zar+0.004
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token Jones
Token ID5437
Feature activation-1.45e-02

Pos logit contributions
 Zar+0.011
 Pax+0.010
+0.009
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.010
28-0.010
nces-0.010
Token that
Token ID326
Feature activation-1.31e-02

Pos logit contributions
 Zar+0.014
 Pax+0.013
+0.012
anch+0.012
 doi+0.012
Neg logit contributions
outhern-0.012
 328-0.011
 fantasy-0.010
28-0.010
nces-0.010
Token propag
Token ID8928
Feature activation+9.71e-04

Pos logit contributions
 Zar+0.012
 Pax+0.011
+0.010
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.012
 328-0.010
 fantasy-0.010
28-0.010
nces-0.010
Tokenates
Token ID689
Feature activation+9.15e-02

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token conspiracy
Token ID10086
Feature activation-7.31e-03

Pos logit contributions
outhern+0.078
 328+0.069
 fantasy+0.066
28+0.065
nces+0.064
Neg logit contributions
 Zar-0.084
 Pax-0.081
-0.073
anch-0.072
 doi-0.070
Token theories
Token ID10946
Feature activation-7.27e-02

Pos logit contributions
 Zar+0.004
 Pax+0.004
+0.004
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.008
 328-0.008
 fantasy-0.008
28-0.007
nces-0.007
Token like
Token ID588
Feature activation+2.78e-03

Pos logit contributions
 Zar+0.068
 Pax+0.066
+0.059
anch+0.058
 doi+0.057
Neg logit contributions
outhern-0.061
 328-0.054
 fantasy-0.052
28-0.050
nces-0.050
Token the
Token ID262
Feature activation-1.01e-02

Pos logit contributions
outhern+0.002
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.002
-0.002
anch-0.002
 doi-0.002
Tokenered
Token ID1068
Feature activation+1.04e-01

Pos logit contributions
 Zar+0.042
 Pax+0.041
+0.038
anch+0.037
 doi+0.037
Neg logit contributions
outhern-0.023
 328-0.020
 fantasy-0.019
28-0.018
nces-0.018
Token Bob
Token ID5811
Feature activation+4.94e-03

Pos logit contributions
outhern+0.098
 328+0.088
 fantasy+0.085
28+0.083
nces+0.082
Neg logit contributions
 Zar-0.085
 Pax-0.082
-0.074
anch-0.071
 doi-0.070
Tokenro
Token ID305
Feature activation+1.90e-02

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.004
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.005
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Tokenvs
Token ID14259
Feature activation-2.54e-03

Pos logit contributions
outhern+0.018
 328+0.017
 fantasy+0.016
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.015
 Pax-0.015
-0.013
anch-0.013
 doi-0.012
Tokenky
Token ID2584
Feature activation+1.37e-02

Pos logit contributions
 Zar+0.002
 Pax+0.002
+0.002
anch+0.001
 doi+0.001
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token with
Token ID351
Feature activation-4.89e-03

Pos logit contributions
outhern+0.011
 328+0.010
 fantasy+0.009
28+0.009
nces+0.009
Neg logit contributions
 Zar-0.013
 Pax-0.013
-0.012
anch-0.011
 doi-0.011
Token 19
Token ID678
Feature activation+2.39e-02

Pos logit contributions
 Zar+0.005
 Pax+0.005
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Token shots
Token ID6934
Feature activation+1.14e-02

Pos logit contributions
outhern+0.019
 328+0.017
 fantasy+0.016
28+0.016
nces+0.016
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.020
 doi-0.019
Token (
Token ID357
Feature activation-3.33e-03

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.011
 Pax-0.010
-0.009
anch-0.009
 doi-0.009
Tokento
Token ID1462
Feature activation+8.46e-03

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
nces-0.002
28-0.002
Token just
Token ID655
Feature activation-4.84e-03

Pos logit contributions
outhern+0.007
 328+0.006
 fantasy+0.006
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token deputy
Token ID10636
Feature activation-2.15e-02

Pos logit contributions
 Zar+0.005
 Pax+0.004
+0.004
anch+0.004
 doi+0.004
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token Conservative
Token ID11132
Feature activation-2.35e-02

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.020
anch+0.019
 doi+0.019
Neg logit contributions
outhern-0.016
 328-0.014
 fantasy-0.013
28-0.013
nces-0.013
Token leader
Token ID3554
Feature activation-3.52e-02

Pos logit contributions
 Zar+0.026
 Pax+0.025
+0.023
anch+0.022
 doi+0.022
Neg logit contributions
outhern-0.016
 328-0.014
 fantasy-0.013
28-0.013
nces-0.013
Token Lisa
Token ID15378
Feature activation+2.49e-02

Pos logit contributions
 Zar+0.031
 Pax+0.030
+0.027
anch+0.026
 doi+0.026
Neg logit contributions
outhern-0.031
 328-0.028
 fantasy-0.027
28-0.026
nces-0.026
Token Ra
Token ID7567
Feature activation-1.47e-02

Pos logit contributions
outhern+0.022
 328+0.020
 fantasy+0.019
28+0.018
nces+0.018
Neg logit contributions
 Zar-0.022
 Pax-0.021
-0.019
anch-0.019
 doi-0.018
Tokenitt
Token ID715
Feature activation+6.58e-03

Pos logit contributions
 Zar+0.015
 Pax+0.015
+0.013
anch+0.013
 doi+0.013
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Token said
Token ID531
Feature activation-2.60e-02

Pos logit contributions
outhern+0.006
 328+0.006
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.006
 Pax-0.005
-0.005
anch-0.005
 doi-0.005
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
 Zar+0.025
 Pax+0.024
+0.022
anch+0.022
 doi+0.021
Neg logit contributions
outhern-0.021
 328-0.018
 fantasy-0.018
28-0.017
nces-0.017
Token "
Token ID366
Feature activation-3.52e-02

Pos logit contributions
 Zar+0.012
 Pax+0.012
+0.011
anch+0.010
 doi+0.010
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.010
28-0.010
nces-0.009
TokenI
Token ID40
Feature activation-3.09e-02

Pos logit contributions
 Zar+0.030
 Pax+0.029
+0.026
anch+0.026
 doi+0.025
Neg logit contributions
outhern-0.032
 328-0.029
 fantasy-0.028
28-0.027
nces-0.026
Token am
Token ID716
Feature activation-7.59e-02

Pos logit contributions
 Zar+0.027
 Pax+0.026
+0.023
anch+0.023
 doi+0.022
Neg logit contributions
outhern-0.028
 328-0.025
 fantasy-0.024
28-0.023
nces-0.023
Tokenac
Token ID330
Feature activation+3.31e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.018
 Pax-0.017
-0.016
anch-0.016
 doi-0.015
Tokenrest
Token ID2118
Feature activation-4.29e-02

Pos logit contributions
outhern+0.035
 328+0.032
 fantasy+0.031
28+0.030
nces+0.030
Neg logit contributions
 Zar-0.023
 Pax-0.022
-0.020
anch-0.019
 doi-0.018
Token,
Token ID11
Feature activation-3.09e-03

Pos logit contributions
 Zar+0.041
 Pax+0.040
+0.036
anch+0.035
 doi+0.035
Neg logit contributions
outhern-0.034
 328-0.031
 fantasy-0.030
28-0.029
nces-0.028
Token Louis
Token ID5593
Feature activation+2.41e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.002
anch+0.002
 doi+0.002
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Token Vu
Token ID35816
Feature activation+7.74e-03

Pos logit contributions
outhern+0.025
 328+0.023
 fantasy+0.022
28+0.021
nces+0.021
Neg logit contributions
 Zar-0.018
 Pax-0.017
-0.015
anch-0.015
 doi-0.014
Tokenitton
Token ID47304
Feature activation-1.42e-01

Pos logit contributions
outhern+0.008
 328+0.008
 fantasy+0.007
28+0.007
 AD+0.007
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.004
anch-0.004
 doi-0.004
Token,
Token ID11
Feature activation+9.21e-04

Pos logit contributions
 Zar+0.134
 Pax+0.129
+0.118
anch+0.115
 doi+0.112
Neg logit contributions
outhern-0.116
 328-0.104
 fantasy-0.100
28-0.097
nces-0.096
Token
Token ID564
Feature activation+5.26e-03

Pos logit contributions
outhern+0.001
 328+0.001
 fantasy+0.001
28+0.001
nces+0.001
Neg logit contributions
 Zar-0.001
 Pax-0.001
-0.001
anch-0.001
 doi-0.001
Token
Token ID250
Feature activation-3.15e-03

Pos logit contributions
outhern+0.003
 328+0.003
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
TokenGil
Token ID40747
Feature activation+5.52e-02

Pos logit contributions
 Zar+0.003
 Pax+0.003
+0.003
anch+0.003
 doi+0.002
Neg logit contributions
outhern-0.003
 328-0.002
 fantasy-0.002
28-0.002
nces-0.002
Tokenmore
Token ID3549
Feature activation+1.64e-02

Pos logit contributions
outhern+0.043
 328+0.038
 fantasy+0.037
28+0.036
nces+0.035
Neg logit contributions
 Zar-0.054
 Pax-0.052
-0.048
anch-0.047
 doi-0.046
Token counterparts
Token ID16054
Feature activation+5.37e-03

Pos logit contributions
 Zar+0.026
 Pax+0.025
+0.023
anch+0.023
 doi+0.022
Neg logit contributions
outhern-0.020
 328-0.018
 fantasy-0.017
28-0.017
nces-0.016
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.005
 Pax-0.005
-0.005
anch-0.004
 doi-0.004
Token
Token ID198
Feature activation-2.77e-02

Pos logit contributions
 Zar+0.018
 Pax+0.018
+0.016
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.018
 328-0.016
 fantasy-0.016
28-0.015
nces-0.015
Token
Token ID198
Feature activation-1.95e-02

Pos logit contributions
 Zar+0.027
 Pax+0.026
+0.024
anch+0.023
 doi+0.023
Neg logit contributions
outhern-0.022
 328-0.020
 fantasy-0.019
28-0.018
nces-0.018
TokenAnaly
Token ID37702
Feature activation-3.67e-02

Pos logit contributions
 Zar+0.018
 Pax+0.017
+0.015
anch+0.015
 doi+0.015
Neg logit contributions
outhern-0.017
 328-0.015
 fantasy-0.015
28-0.014
nces-0.014
Tokensts
Token ID6448
Feature activation-1.51e-01

Pos logit contributions
 Zar+0.023
 Pax+0.022
+0.019
anch+0.018
 doi+0.018
Neg logit contributions
outhern-0.042
 328-0.038
 fantasy-0.037
28-0.037
nces-0.036
Token say
Token ID910
Feature activation-3.66e-02

Pos logit contributions
 Zar+0.142
 Pax+0.137
+0.125
anch+0.122
 doi+0.120
Neg logit contributions
outhern-0.124
 328-0.110
 fantasy-0.106
28-0.103
nces-0.102
Token that
Token ID326
Feature activation+6.10e-03

Pos logit contributions
 Zar+0.032
 Pax+0.030
+0.027
anch+0.027
 doi+0.026
Neg logit contributions
outhern-0.033
 328-0.030
 fantasy-0.029
28-0.028
nces-0.028
Token the
Token ID262
Feature activation-5.68e-03

Pos logit contributions
outhern+0.005
 328+0.004
 fantasy+0.004
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.006
 Pax-0.006
-0.005
anch-0.005
 doi-0.005
Token Kremlin
Token ID19077
Feature activation-3.42e-02

Pos logit contributions
 Zar+0.006
 Pax+0.005
+0.005
anch+0.005
 doi+0.005
Neg logit contributions
outhern-0.004
 328-0.004
 fantasy-0.004
28-0.004
nces-0.004
Token
Token ID447
Feature activation-4.84e-04

Pos logit contributions
 Zar+0.030
 Pax+0.029
+0.027
anch+0.026
 doi+0.025
Neg logit contributions
outhern-0.030
 328-0.027
 fantasy-0.026
28-0.025
nces-0.025
Token Kal
Token ID12612
Feature activation+4.02e-02

Pos logit contributions
 Zar+0.004
 Pax+0.003
+0.003
anch+0.003
 doi+0.003
Neg logit contributions
outhern-0.004
 328-0.003
 fantasy-0.003
28-0.003
nces-0.003
Tokenup
Token ID929
Feature activation-7.72e-03

Pos logit contributions
outhern+0.035
 328+0.031
 fantasy+0.030
28+0.029
nces+0.029
Neg logit contributions
 Zar-0.036
 Pax-0.035
-0.032
anch-0.031
 doi-0.030
Tokenur
Token ID333
Feature activation-2.45e-02

Pos logit contributions
 Zar+0.007
 Pax+0.007
+0.006
anch+0.006
 doi+0.006
Neg logit contributions
outhern-0.007
 328-0.006
 fantasy-0.006
28-0.006
nces-0.006
Token,
Token ID11
Feature activation+1.92e-02

Pos logit contributions
 Zar+0.022
 Pax+0.021
+0.019
anch+0.019
 doi+0.018
Neg logit contributions
outhern-0.021
 328-0.019
 fantasy-0.018
28-0.018
nces-0.017
Token Ahmed
Token ID21157
Feature activation+1.59e-02

Pos logit contributions
outhern+0.016
 328+0.014
 fantasy+0.014
28+0.013
nces+0.013
Neg logit contributions
 Zar-0.018
 Pax-0.017
-0.016
anch-0.015
 doi-0.015
Tokenabad
Token ID17325
Feature activation-1.41e-01

Pos logit contributions
outhern+0.019
 328+0.018
 fantasy+0.018
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.007
anch-0.007
 doi-0.006
Token,
Token ID11
Feature activation+1.14e-02

Pos logit contributions
 Zar+0.133
 Pax+0.129
+0.117
anch+0.114
 doi+0.112
Neg logit contributions
outhern-0.115
 328-0.102
 fantasy-0.099
28-0.095
nces-0.095
Token Gujarat
Token ID30311
Feature activation+2.24e-02

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.011
 Pax-0.011
-0.010
anch-0.010
 doi-0.009
Token 38
Token ID4353
Feature activation-2.11e-02

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.012
nces+0.012
28+0.012
Neg logit contributions
 Zar-0.025
 Pax-0.024
-0.022
anch-0.021
 doi-0.021
Token0001
Token ID18005
Feature activation-5.28e-02

Pos logit contributions
 Zar+0.023
 Pax+0.023
+0.021
anch+0.020
 doi+0.020
Neg logit contributions
outhern-0.014
 328-0.012
 fantasy-0.012
nces-0.011
ungle-0.011
Token,
Token ID11
Feature activation+2.10e-02

Pos logit contributions
 Zar+0.049
 Pax+0.048
+0.043
anch+0.042
 doi+0.041
Neg logit contributions
outhern-0.044
 328-0.039
 fantasy-0.038
28-0.036
nces-0.036
Token
Token ID198
Feature activation+1.00e-02

Pos logit contributions
outhern+0.000
 328+0.000
 fantasy+0.000
28+0.000
nces+0.000
Neg logit contributions
 Zar-0.000
 Pax-0.000
-0.000
anch-0.000
 doi-0.000
Token
Token ID198
Feature activation+1.11e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
 AD+0.006
Neg logit contributions
 Zar-0.010
 Pax-0.009
-0.009
anch-0.008
 doi-0.008
TokenThe
Token ID464
Feature activation+3.49e-03

Pos logit contributions
outhern+0.009
 328+0.008
 fantasy+0.008
28+0.008
nces+0.008
Neg logit contributions
 Zar-0.010
 Pax-0.010
-0.009
anch-0.009
 doi-0.009
Token City
Token ID2254
Feature activation-1.24e-02

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Token Ord
Token ID14230
Feature activation-1.03e-02

Pos logit contributions
 Zar+0.011
 Pax+0.011
+0.010
anch+0.009
 doi+0.009
Neg logit contributions
outhern-0.011
 328-0.010
 fantasy-0.009
28-0.009
nces-0.009
Tokeninance
Token ID14149
Feature activation-1.47e-01

Pos logit contributions
 Zar+0.009
 Pax+0.009
+0.008
anch+0.008
 doi+0.007
Neg logit contributions
outhern-0.009
 328-0.008
 fantasy-0.008
28-0.008
nces-0.008
Token
Token ID198
Feature activation+1.79e-02

Pos logit contributions
 Zar+0.127
 Pax+0.122
+0.110
anch+0.107
 doi+0.105
Neg logit contributions
outhern-0.133
 328-0.119
 fantasy-0.116
28-0.112
nces-0.111
Token
Token ID198
Feature activation+1.78e-02

Pos logit contributions
outhern+0.014
 328+0.012
 fantasy+0.012
28+0.012
 AD+0.011
Neg logit contributions
 Zar-0.018
 Pax-0.017
-0.016
anch-0.015
 doi-0.015
TokenAccording
Token ID4821
Feature activation-3.27e-02

Pos logit contributions
outhern+0.015
 328+0.013
 fantasy+0.013
28+0.013
nces+0.012
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token to
Token ID284
Feature activation+9.37e-03

Pos logit contributions
 Zar+0.031
 Pax+0.030
+0.027
anch+0.027
 doi+0.026
Neg logit contributions
outhern-0.027
 328-0.024
 fantasy-0.023
28-0.022
nces-0.022
Token the
Token ID262
Feature activation-1.18e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.007
nces+0.007
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
Token
Token ID250
Feature activation+1.50e-02

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.004
nces+0.004
Neg logit contributions
 Zar-0.011
 Pax-0.010
-0.010
anch-0.009
 doi-0.009
TokenM
Token ID44
Feature activation+1.57e-02

Pos logit contributions
outhern+0.013
 328+0.011
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.014
 Pax-0.013
-0.012
anch-0.012
 doi-0.011
Tokenitch
Token ID2007
Feature activation+1.91e-02

Pos logit contributions
outhern+0.013
 328+0.012
 fantasy+0.011
28+0.011
nces+0.011
Neg logit contributions
 Zar-0.015
 Pax-0.014
-0.013
anch-0.013
 doi-0.012
Token has
Token ID468
Feature activation+9.27e-03

Pos logit contributions
outhern+0.017
 328+0.016
 fantasy+0.015
28+0.015
nces+0.015
Neg logit contributions
 Zar-0.016
 Pax-0.016
-0.014
anch-0.014
 doi-0.014
Token exce
Token ID43748
Feature activation+1.57e-02

Pos logit contributions
outhern+0.008
 328+0.007
 fantasy+0.007
28+0.006
nces+0.006
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.008
anch-0.007
 doi-0.007
Tokenlled
Token ID3353
Feature activation-1.30e-01

Pos logit contributions
outhern+0.019
 328+0.018
 fantasy+0.017
28+0.017
nces+0.017
Neg logit contributions
 Zar-0.009
 Pax-0.008
-0.007
anch-0.006
 doi-0.006
Token through
Token ID832
Feature activation+4.76e-03

Pos logit contributions
 Zar+0.126
 Pax+0.122
+0.110
anch+0.108
 doi+0.106
Neg logit contributions
outhern-0.105
 328-0.092
 fantasy-0.088
28-0.086
nces-0.085
Token his
Token ID465
Feature activation+8.12e-03

Pos logit contributions
outhern+0.004
 328+0.004
 fantasy+0.003
28+0.003
nces+0.003
Neg logit contributions
 Zar-0.004
 Pax-0.004
-0.004
anch-0.004
 doi-0.004
Token final
Token ID2457
Feature activation+3.42e-03

Pos logit contributions
outhern+0.006
 328+0.005
 fantasy+0.005
28+0.005
nces+0.005
Neg logit contributions
 Zar-0.008
 Pax-0.008
-0.007
anch-0.007
 doi-0.007
Token stages
Token ID9539
Feature activation-2.83e-02

Pos logit contributions
outhern+0.003
 328+0.002
 fantasy+0.002
28+0.002
nces+0.002
Neg logit contributions
 Zar-0.003
 Pax-0.003
-0.003
anch-0.003
 doi-0.003
Token of
Token ID286
Feature activation+4.55e-02

Pos logit contributions
 Zar+0.028
 Pax+0.027
+0.024
anch+0.024
 doi+0.023
Neg logit contributions
outhern-0.022
 328-0.020
 fantasy-0.019
28-0.018
nces-0.018