INDEX
Explanations
biographical details about individuals - such as birthdates, nationalities, occupations, and achievements
biographical information about individuals, particularly their nationality and professions
New Auto-Interp
Negative Logits
ħĭ
-0.84
İĭ
-0.79
Tokens
-0.76
beforehand
-0.71
chwitz
-0.69
doms
-0.68
ĪĴ
-0.67
Ĥİ
-0.67
tnc
-0.66
soType
-0.66
POSITIVE LOGITS
ocument
0.72
versatile
0.70
oriented
0.68
ablished
0.67
sleeper
0.65
combining
0.65
enthusiast
0.64
otropic
0.64
consisting
0.61
agonist
0.61
Activations Density 0.608%