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

    Neuronpedia

    INDEX
    Explanations

    numerals followed by punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their contents along with their numerical designations within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azon
    -0.77
    iences
    -0.75
    ciating
    -0.73
    shr
    -0.67
    itory
    -0.67
    bos
    -0.67
    edi
    -0.66
    ween
    -0.66
    uron
    -0.66
    rounded
    -0.64
    POSITIVE LOGITS
     IMAGES
    0.72
     Parables
    0.70
     Rings
    0.68
    é¾
    0.66
     [+
    0.64
     ESV
    0.64
     Ibid
    0.62
     ILCS
    0.62
    BuyableInstoreAndOnline
    0.62
    )].
    0.62
    Act Density 0.099%

    No Known Activations