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

    Neuronpedia

    INDEX
    Explanations

    mentions of technical parameters or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to parameters in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.80
     coli
    -0.73
    BY
    -0.71
    lyn
    -0.70
    á½
    -0.69
    ï¸
    -0.69
    minster
    -0.68
    bery
    -0.67
    Ń
    -0.66
    cler
    -0.66
    POSITIVE LOGITS
     parameters
    0.99
    eters
    0.99
    ilitary
    0.93
    eter
    0.85
    ities
    0.85
    ised
    0.85
    ized
    0.83
    ulated
    0.80
    esthetic
    0.79
     annexed
    0.79
    Act Density 0.012%

    No Known Activations