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

    Neuronpedia

    INDEX
    Explanations

    words related to ventilation or openings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ventilation systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hitman
    -0.71
    lihood
    -0.67
    FT
    -0.65
    makers
    -0.65
    Else
    -0.64
    anded
    -0.63
     artisan
    -0.61
    ģĸ
    -0.61
    ×Ķ
    -0.61
     Nare
    -0.60
    POSITIVE LOGITS
    ricular
    1.40
    ilated
    1.21
    ral
    1.20
    rue
    1.16
    urous
    1.07
    uring
    1.05
    ilation
    1.04
    uri
    0.97
    raint
    0.91
    ras
    0.88
    Act Density 0.026%

    No Known Activations