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

    Neuronpedia

    INDEX
    Explanations

    words related to defiance or refusal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refused."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.86
    groups
    -0.81
    =-=-=-=-=-=-=-=-
    -0.78
    ammy
    -0.76
    psc
    -0.75
    Assembly
    -0.71
    ICAN
    -0.70
    amate
    -0.69
    rium
    -0.69
    otor
    -0.69
    POSITIVE LOGITS
    ĸļ
    0.88
     vehemently
    0.86
     miser
    0.83
     refuse
    0.82
     refused
    0.78
     refuses
    0.78
     admission
    0.77
     refusal
    0.76
     unanimously
    0.74
     refusing
    0.73
    Act Density 0.011%

    No Known Activations