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

    Neuronpedia

    INDEX
    Explanations

    the beginning of paragraphs or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proposition
    -0.51
    proposition
    -0.49
     Ferne
    -0.49
     State
    -0.48
     tắc
    -0.45
    elenco
    -0.45
    State
    -0.45
    flage
    -0.42
     Estado
    -0.42
    wegen
    -0.41
    POSITIVE LOGITS
     Strongly
    1.01
    Strongly
    0.94
     ModelExpression
    0.79
    حوالہ
    0.74
    strongly
    0.73
    IsMutable
    0.73
    참고
    0.72
    BeginInit
    0.69
     strongly
    0.68
     nakalista
    0.67
    Act Density 0.000%

    No Known Activations