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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -0.17
    aver
    -0.17
    iform
    -0.14
    ulo
    -0.14
     Rated
    -0.14
     Tim
    -0.14
    tem
    -0.13
     Grades
    -0.13
    reater
    -0.13
    ERA
    -0.13
    POSITIVE LOGITS
     figure
    0.82
    figure
    0.61
     figures
    0.47
    -figure
    0.46
     number
    0.45
     Figure
    0.42
     figura
    0.42
    figures
    0.40
     mark
    0.39
    .figure
    0.38
    Act Density 0.251%

    No Known Activations