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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or programming notations and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.45
    getActiveSheet
    -0.43
    ListItemIcon
    -0.38
     đẳng
    -0.36
    änden
    -0.35
     Hobbes
    -0.35
    ordano
    -0.35
    ẫy
    -0.35
    msgTypes
    -0.35
     Messing
    -0.34
    POSITIVE LOGITS
     UA
    1.14
    UU
    1.12
    U
    1.11
     UT
    1.11
     UD
    1.09
     UE
    1.08
     UF
    1.07
     U
    1.07
    UE
    1.07
     u
    1.06
    Act Density 10.986%

    No Known Activations