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

    Neuronpedia

    INDEX
    Explanations

    phrases related to refusal or non-compliance

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

    refusal to accept or allow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DST
    -0.45
    tagena
    -0.42
     تانيه
    -0.40
     occasional
    -0.40
    getManager
    -0.40
     pointers
    -0.39
     thiện
    -0.39
    ajuku
    -0.39
     tartalomajánló
    -0.39
     simplifié
    -0.39
    POSITIVE LOGITS
     kasarigan
    0.41
     MainAxisSize
    0.41
     оригіналу
    0.40
    ibid
    0.40
     BoxDecoration
    0.39
     kuulu
    0.38
     keber
    0.38
     pitä
    0.37
     ujednoznacz
    0.37
     pétrole
    0.37
    Act Density 0.064%

    No Known Activations