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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the act of refusing

    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
    of
    -0.75
    Gener
    -0.73
    erning
    -0.73
    where
    -0.72
    bred
    -0.69
    Inst
    -0.67
     Miscellaneous
    -0.67
    OF
    -0.67
    itar
    -0.66
    psc
    -0.66
    POSITIVE LOGITS
     unanimously
    0.98
     unsuccessfully
    0.90
     vehemently
    0.82
    ĸļ
    0.81
    CLASSIFIED
    0.80
    ¿½
    0.76
     aback
    0.75
     sworn
    0.75
     repeatedly
    0.75
     rehe
    0.72
    Act Density 0.047%

    No Known Activations