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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing instructional language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    йлер
    -0.50
    EDEFAULT
    -0.49
    <eos>
    -0.48
    InlineData
    -0.48
    nikov
    -0.47
    leur
    -0.47
    hilangan
    -0.46
    Pri
    -0.44
    えている
    -0.44
    sterna
    -0.44
    POSITIVE LOGITS
     Paglinawan
    0.79
     للمعارف
    0.78
     للاسماء
    0.76
     Signalez
    0.71
    lapsingToolbar
    0.70
     وتسجيلات
    0.69
    SequentialGroup
    0.68
    олові
    0.67
    ToSave
    0.66
     Himo
    0.64
    Act Density 0.187%

    No Known Activations