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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "refuse" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    refuse to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ISNI
    -0.64
    InputBorder
    -0.64
    bootstrapcdn
    -0.56
     getItemId
    -0.55
     isle
    -0.53
    NewUrlParser
    -0.52
    contentPadding
    -0.52
    NameInMap
    -0.52
    IOM
    -0.52
    XmlAccessorType
    -0.52
    POSITIVE LOGITS
     refuse
    1.35
     refusal
    1.30
     refused
    1.30
     refuses
    1.26
     refusing
    1.20
     Refuse
    1.17
     refus
    1.12
     refuser
    0.97
     refusé
    0.91
     rifi
    0.87
    Act Density 0.011%

    No Known Activations