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

    Neuronpedia

    INDEX
    Explanations

    quantitative values or comparisons related to a specified metric

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and counts of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gewater
    -0.61
    ··
    -0.59
    inelli
    -0.59
    lace
    -0.56
    rament
    -0.55
    sein
    -0.54
    tainment
    -0.54
    LER
    -0.53
    vision
    -0.53
    ERSON
    -0.53
    POSITIVE LOGITS
     of
    1.14
    Of
    0.78
     Of
    0.75
    of
    0.72
     thereof
    0.71
     OF
    0.69
     enrolled
    0.66
     killed
    0.66
     who
    0.64
     sampled
    0.64
    Act Density 0.073%

    No Known Activations