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

    Neuronpedia

    INDEX
    Explanations

    references to processes, products, and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newOwner
    -0.67
     Efq
    -0.61
    Tikang
    -0.60
    chitz
    -0.58
     Affected
    -0.58
     Shakspeare
    -0.57
    ToReturn
    -0.57
     Majefty
    -0.57
     Yarm
    -0.57
     daggers
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.78
     результате
    0.65
    IsPostBack
    0.60
     ходе
    0.60
    經過
    0.60
     urma
    0.55
    endregion
    0.54
     careful
    0.53
     diligent
    0.52
     esfuerzo
    0.52
    Act Density 0.743%

    No Known Activations