INDEX
Explanations
references to conflict and struggle in various forms
New Auto-Interp
Negative Logits
setVerticalGroup
-0.93
AssemblyProduct
-0.74
EnglishChoose
-0.71
myſelf
-0.68
twimg
-0.67
raiſ
-0.65
tranſ
-0.64
ſeveral
-0.64
Anſ
-0.64
purpoſe
-0.64
POSITIVE LOGITS
ó
0.66
ੋ
0.66
Bo
0.66
o
0.64
lo
0.64
ો
0.62
ho
0.62
ko
0.61
ো
0.60
Po
0.59
Activations Density 0.823%