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

    Neuronpedia

    INDEX
    Explanations

    words related to knockout, KO, and physical contests

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "KO" (knockout) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reads
    -0.78
    comments
    -0.73
    relation
    -0.72
    mberg
    -0.70
    hist
    -0.65
    pressure
    -0.63
    dimension
    -0.63
    behavior
    -0.62
     stead
    -0.62
    icone
    -0.62
    POSITIVE LOGITS
     KO
    1.26
    KO
    1.19
     knockout
    0.87
    xon
    0.85
    BIL
    0.83
    lean
    0.80
    STON
    0.77
    tsky
    0.77
    UGH
    0.75
    TION
    0.74
    Act Density 0.006%

    No Known Activations