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

    Neuronpedia

    INDEX
    Explanations

    statements related to ethics and morality in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itas
    -0.18
    SupportedContent
    -0.18
    _Lean
    -0.16
    asje
    -0.16
    cisi
    -0.16
    .jquery
    -0.15
    jspx
    -0.15
    ,exports
    -0.15
    TestCategory
    -0.15
    eyse
    -0.15
    POSITIVE LOGITS
     cul
    0.16
    bt
    0.16
    ÑĢоз
    0.15
    val
    0.14
     t
    0.14
     Fe
    0.14
     excess
    0.14
    T
    0.14
    y
    0.14
    ck
    0.14
    Act Density 0.023%

    No Known Activations