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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or business documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brill
    -0.88
     stead
    -0.80
    brance
    -0.66
     outwe
    -0.63
    mares
    -0.62
     adm
    -0.60
    selves
    -0.60
     thous
    -0.60
     wedd
    -0.60
     inconsist
    -0.59
    POSITIVE LOGITS
    Writer
    0.83
    rite
    0.78
     Spiral
    0.75
    lime
    0.70
    Pak
    0.70
    knit
    0.69
    ruct
    0.67
    arial
    0.67
    Correct
    0.66
    Chapter
    0.66
    Act Density 0.000%

    No Known Activations