INDEX
Explanations
pronouns and informal speech patterns
expressions of need or desire
New Auto-Interp
Negative Logits
pedia
-0.59
Ars
-0.56
âĩ
-0.53
Trap
-0.52
Cells
-0.51
Archive
-0.49
KDE
-0.49
Wiki
-0.47
sparse
-0.47
Respons
-0.47
POSITIVE LOGITS
.'"
0.97
]."
0.88
â̦"
0.88
'."
0.83
'"
0.79
!'"
0.76
)."
0.76
,'"
0.72
}"
0.71
?'"
0.70
Activations Density 0.639%