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

    Neuronpedia

    INDEX
    Explanations

    telephone numbers or numerical codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics related to a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.80
     ultras
    -0.67
    mers
    -0.60
    mere
    -0.60
    aths
    -0.59
    assic
    -0.59
    bury
    -0.59
    wick
    -0.58
     jaws
    -0.58
    burg
    -0.58
    POSITIVE LOGITS
    304
    0.79
    249
    0.75
    309
    0.74
    106
    0.74
    154
    0.73
    1027
    0.72
    246
    0.72
    199
    0.72
    308
    0.72
    454
    0.72
    Act Density 0.211%

    No Known Activations