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

    Neuronpedia

    INDEX
    Explanations

    terms related to denial or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rejection
    -0.78
    Erreferentziak
    -0.75
    Rejection
    -0.74
     rejection
    -0.70
     Reject
    -0.70
     Rejected
    -0.68
    تقاوى
    -0.67
    قایناق‌لار
    -0.67
    throwaway
    -0.67
     rejet
    -0.66
    POSITIVE LOGITS
    math
    1.01
     deny
    0.98
     denied
    0.86
     denying
    0.85
     denies
    0.77
     denial
    0.68
    Math
    0.66
     math
    0.63
    WebServlet
    0.61
     Math
    0.59
    Act Density 0.119%

    No Known Activations