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

    Neuronpedia

    INDEX
    Explanations

    words related to knockouts

    oai_token-act-pair · gpt-3.5-turbo

    references to "knockout" or "KO" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.72
     attRot
    -0.71
    Struct
    -0.67
    Charges
    -0.66
    External
    -0.66
    hid
    -0.66
    Downloadha
    -0.65
    riages
    -0.65
    eff
    -0.65
    Disc
    -0.65
    POSITIVE LOGITS
     KO
    2.58
    KO
    2.53
     knockout
    2.47
    к
    1.96
     choke
    1.63
    ariat
    1.51
     choked
    1.20
     combo
    1.20
     choking
    1.02
     Combo
    0.97
    Act Density 0.037%

    No Known Activations