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

    Neuronpedia

    INDEX
    Explanations

    quotations or dialogue in sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas followed by quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.74
     Seym
    -0.71
     antioxid
    -0.67
    ebin
    -0.66
    ieri
    -0.65
    anmar
    -0.65
    ingu
    -0.64
     challeng
    -0.64
    egu
    -0.61
     administr
    -0.61
    POSITIVE LOGITS
     reads
    0.93
    aunder
    0.69
     writes
    0.68
     she
    0.66
    ————
    0.63
     replied
    0.63
     wrote
    0.63
    thumbnails
    0.62
    tesy
    0.62
    Marginal
    0.62
    Act Density 0.069%

    No Known Activations