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

    Neuronpedia

    INDEX
    Explanations

    numeric values or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.96
    endpush
    -0.64
     hỏi
    -0.54
    ).
    -0.54
    .
    -0.53
    volley
    -0.51
     .
    -0.51
    "].
    -0.51
    Mixin
    -0.51
    [toxicity=0]
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.91
    LookAnd
    0.81
    styleType
    0.77
     propOrder
    0.75
    0.73
    principalTable
    0.66
    存于互联网档案馆
    0.64
    expandindo
    0.64
     kaarangay
    0.64
    ыгана
    0.63
    Act Density 0.703%

    No Known Activations