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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantitative data

    oai_token-act-pair · gpt-3.5-turbo

    numeric values representing significant quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awed
    -0.89
    anooga
    -0.87
    awaru
    -0.83
    rotein
    -0.80
    rophe
    -0.79
    ramid
    -0.79
    ledged
    -0.79
    amaru
    -0.78
    ysical
    -0.77
    raltar
    -0.74
    POSITIVE LOGITS
    nd
    1.38
    181
    0.84
     thirds
    0.84
    160
    0.83
    502
    0.83
    80
    0.82
    152
    0.82
    186
    0.80
    162
    0.79
    132
    0.78
    Act Density 0.050%

    No Known Activations