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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific website or company name

    oai_token-act-pair · gpt-3.5-turbo

    references to "arc" or related concepts within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.79
    ãģŁ
    -0.73
    fficiency
    -0.73
    FUL
    -0.71
     à¤
    -0.70
    ãĥĹ
    -0.69
    lihood
    -0.69
    loo
    -0.68
    ãĥīãĥ©
    -0.66
    mble
    -0.66
    POSITIVE LOGITS
    otics
    1.04
    adian
    1.00
    arc
    1.00
    aine
    0.93
    asm
    0.93
    adia
    0.91
    inia
    0.88
    issa
    0.82
    assin
    0.80
    itect
    0.79
    Act Density 0.007%

    No Known Activations