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

    Neuronpedia

    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, especially periods, indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.78
    ãĥ¼ãĥĨ
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.75
     plantation
    -0.68
    arettes
    -0.61
    ierra
    -0.59
     seams
    -0.59
     chained
    -0.59
     equival
    -0.58
     Tycoon
    -0.57
    POSITIVE LOGITS
    ...]
    1.41
    âĢ¦]
    1.28
    Pg
    1.26
    ?]
    1.11
    !]
    0.98
    REDACTED
    0.98
    ](
    0.91
    actionDate
    0.91
    sic
    0.91
    Footnote
    0.89
    Act Density 0.031%

    No Known Activations