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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs indicating refusal or inability

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

    refusal or lack of permission/support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nextProps
    -0.54
    cookieParser
    -0.54
    OrNil
    -0.52
    rungsseite
    -0.48
    transQ
    -0.47
    ntlet
    -0.47
    owment
    -0.47
    FieldDescriptor
    -0.47
     ActionListener
    -0.46
    craper
    -0.46
    POSITIVE LOGITS
     refused
    0.41
     refuses
    0.41
     للمعارف
    0.41
     refusé
    0.40
    OGND
    0.36
     refuse
    0.36
     refusing
    0.35
    extrême
    0.35
    pozy
    0.35
     unwilling
    0.34
    Act Density 0.086%

    No Known Activations