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

    Neuronpedia

    INDEX
    Explanations

    specific numbers or statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to reported cases or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.68
    aban
    -0.64
    bara
    -0.62
    anamo
    -0.62
    folk
    -0.61
    jen
    -0.61
     theirs
    -0.61
    sole
    -0.60
    abi
    -0.59
    especially
    -0.59
    POSITIVE LOGITS
     consecutive
    0.98
     percent
    0.92
     total
    0.89
    %
    0.88
     tonnes
    0.85
     pounds
    0.83
     pairs
    0.82
     fewer
    0.79
     kilograms
    0.79
     entries
    0.79
    Act Density 0.274%

    No Known Activations