INDEX
Explanations
forms of the first-person singular pronoun "I"
New Auto-Interp
Negative Logits
ſever
-0.65
Autoritní
-0.65
Beſ
-0.65
-0.64
Theſe
-0.64
pegat
-0.64
houſe
-0.63
elog
-0.62
Eſ
-0.61
cach
-0.61
POSITIVE LOGITS
i
3.46
i
2.25
I
1.55
i
1.33
ii
1.28
I
1.27
𝗶
1.10
𝑖
1.05
iI
1.03
ive
1.02
Activations Density 2.425%