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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acts of opposition or dissent

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to contraband

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dill
    -0.75
    oths
    -0.73
    HAHAHAHA
    -0.73
    eson
    -0.71
     Twain
    -0.71
    externalActionCode
    -0.70
    DragonMagazine
    -0.67
    Introduced
    -0.67
    ard
    -0.67
    isode
    -0.66
    POSITIVE LOGITS
    aband
    0.89
    ricular
    0.88
    bable
    0.86
    dain
    0.84
    itions
    0.82
    itialized
    0.80
    ition
    0.77
    İĭ
    0.76
    clusively
    0.76
    vised
    0.75
    Act Density 0.022%

    No Known Activations