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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables typically used in equations and formulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.76
     صوتيه
    -0.65
    BeginContext
    -0.62
     ModelExpression
    -0.59
    ValueStyle
    -0.58
     ujednoznacz
    -0.58
     kasarigan
    -0.57
     snippetHide
    -0.57
    :✨
    -0.56
     للاسماء
    -0.56
    POSITIVE LOGITS
    a
    1.55
     а
    1.41
     a
    1.30
    а
    1.01
    ａ
    0.88
     α
    0.82
    ア
    0.82
     aa
    0.82
    𝑎
    0.73
    aa
    0.64
    Act Density 1.375%

    No Known Activations