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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or alternative scenarios in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moriarty
    -0.65
    stanford
    -0.61
     AFF
    -0.59
    rolid
    -0.59
     Jody
    -0.58
     Taras
    -0.58
    صلة
    -0.57
     Pittman
    -0.57
     affine
    -0.56
     zuk
    -0.56
    POSITIVE LOGITS
     else
    1.38
    else
    1.31
     Else
    1.18
     ELSE
    1.17
    ELSE
    1.08
    Else
    1.02
    UnknownFieldSet
    0.90
    ⓧ
    0.90
    telse
    0.87
    帖最后由
    0.85
    Act Density 0.014%

    No Known Activations