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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,
    -0.60
     
    -0.58
    enumi
    -0.57
     is
    -0.56
     in
    -0.56
     of
    -0.52
    \{\\
    -0.52
     also
    -0.47
     too
    -0.45
     are
    -0.44
    POSITIVE LOGITS
    ьаж
    1.30
    ArrowToggle
    1.25
    Vidite
    1.23
     Италијани
    1.21
     Савезне
    1.13
     betweenstory
    1.13
    IndentedString
    1.11
     Paglinawan
    1.10
     propOrder
    1.09
    aarrggbb
    1.09
    Act Density 3.286%

    No Known Activations