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

    Neuronpedia

    INDEX
    Explanations

    comma-separated entities or phrases related to publications or releases

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and book-release-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.74
    quist
    -0.64
    olved
    -0.64
    cience
    -0.63
     aisle
    -0.63
    vel
    -0.62
    uce
    -0.62
    pec
    -0.61
     plank
    -0.61
    tsky
    -0.61
    POSITIVE LOGITS
     namely
    1.29
     albeit
    1.03
     viz
    0.98
     which
    0.94
     respectively
    0.89
     consisting
    0.87
     although
    0.87
     however
    0.87
     comprising
    0.83
     including
    0.82
    Act Density 0.517%

    No Known Activations