INDEX
Explanations
closing punctuation marks in sentences
New Auto-Interp
Negative Logits
TagMode
-0.45
-0.42
1
-0.42
’
-0.42
B
-0.42
L
-0.41
lu
-0.40
-0.40
(
-0.39
sp
-0.38
POSITIVE LOGITS
]")
1.59
)")
1.59
')")
1.50
.")
1.48
]')
1.47
?")
1.47
)')
1.45
")
1.45
)"),
1.43
'")
1.42
Activations Density 0.318%