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

    Neuronpedia

    INDEX
    Explanations

    terms related to refusals and denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.63
    omoto
    -0.61
    +#+#
    -0.58
    Resultados
    -0.57
    addAttribute
    -0.56
     насељу
    -0.56
     AppCompat
    -0.56
    artament
    -0.56
    addComponent
    -0.55
    blogspot
    -0.55
    POSITIVE LOGITS
     refusal
    1.38
     Refuse
    1.30
     denial
    1.26
     refusing
    1.25
     denies
    1.22
     denied
    1.19
     refuse
    1.19
     refuser
    1.17
     refuses
    1.17
     deny
    1.16
    Act Density 0.229%

    No Known Activations