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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress, contribution, or demonstration of results in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.56
    الحياه
    -0.51
    ThroughAttribute
    -0.45
    锆
    -0.45
    itzung
    -0.44
     INTERESAR
    -0.43
     kaynağından
    -0.42
     Gear
    -0.42
     Stick
    -0.42
     ***!
    -0.42
    POSITIVE LOGITS
    SharedCtor
    0.48
     stället
    0.45
    AutoField
    0.43
    횟
    0.41
     удалось
    0.41
    withIdentifier
    0.40
    EditorBrowsable
    0.40
     Räume
    0.40
     Daarom
    0.38
     enabled
    0.38
    Act Density 0.071%

    No Known Activations