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

    Neuronpedia

    INDEX
    Explanations

    references to abuse, particularly in legal and personal contexts

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

    abuse of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yarnpkg
    -0.43
    ChildScrollView
    -0.41
    ftagPool
    -0.40
    rativo
    -0.39
    findpost
    -0.39
    ederen
    -0.39
    zeitig
    -0.38
     étrangère
    -0.38
    LookAnd
    -0.38
    gyz
    -0.38
    POSITIVE LOGITS
     Abuse
    0.81
    Abuse
    0.80
     abuse
    0.74
    abuse
    0.71
     abuses
    0.65
     abusers
    0.65
     abusing
    0.64
     abused
    0.64
     abuser
    0.60
     abus
    0.54
    Act Density 0.008%

    No Known Activations