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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and numerical comparisons across various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aver
    -0.19
     averaging
    -0.15
    Rated
    -0.15
     incur
    -0.14
    بط
    -0.14
    iska
    -0.14
    avier
    -0.14
    uilder
    -0.13
     averaged
    -0.13
     Äįlán
    -0.13
    POSITIVE LOGITS
     figure
    0.76
    figure
    0.56
     figures
    0.49
    -figure
    0.44
     figura
    0.41
    figures
    0.40
     Figure
    0.38
    _figure
    0.36
     Figures
    0.35
    .figure
    0.35
    Act Density 0.298%

    No Known Activations