Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific measurements and experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.22
     ‘
    -1.14
     ’
    -1.07
     ”
    -1.04
     …
    -0.99
    ’
    -0.94
    …”
    -0.90
     �
    -0.88
     #
    -0.86
     ‘’
    -0.85
    POSITIVE LOGITS
    \
    1.51
    \[
    1.33
    \&
    1.32
    \%)
    1.20
     $\&$
    1.18
     $\$
    1.16
    \#
    1.14
     \&
    1.11
    $\
    1.10
     myſelf
    1.09
    Act Density 0.067%

    No Known Activations