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

    Neuronpedia

    INDEX
    Explanations

    resistance or defiance towards authority or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of resistance or refusal in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.91
    gow
    -0.85
    estone
    -0.84
    istical
    -0.77
    mberg
    -0.74
    à¤
    -0.74
     Tycoon
    -0.72
     Springs
    -0.68
    çīĪ
    -0.68
    CAST
    -0.67
    POSITIVE LOGITS
     temptation
    0.97
     resisting
    0.86
    itely
    0.80
     tempt
    0.79
     stren
    0.79
     resistance
    0.78
     adm
    0.75
    encia
    0.75
     juices
    0.75
     vehemently
    0.74
    Act Density 0.023%

    No Known Activations