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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     charm
    -0.74
    wagen
    -0.73
     tradem
    -0.71
     comprom
    -0.66
    ifiable
    -0.66
     spont
    -0.64
     vanity
    -0.63
     nodd
    -0.62
     Seym
    -0.61
     immersion
    -0.61
    POSITIVE LOGITS
    taboola
    0.90
    ::::::::
    0.88
    \-
    0.83
    align
    0.82
     ][
    0.80
    à¼
    0.80
    ĸļ
    0.79
    ::::
    0.77
    -.
    0.77
    actionDate
    0.75
    Act Density 1.711%

    No Known Activations