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

    Neuronpedia

    INDEX
    Explanations

    fractions in cooking recipes

    oai_token-act-pair · gpt-3.5-turbo

    fractional measurements used in cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fletcher
    -0.72
     Elliott
    -0.69
    hower
    -0.66
     Morg
    -0.65
     Comet
    -0.65
     Syl
    -0.65
     Alv
    -0.64
     Daly
    -0.63
     Dragonbound
    -0.62
     Emin
    -0.62
    POSITIVE LOGITS
    ËĪ
    0.99
    oct
    0.93
    4
    0.90
    12
    0.89
    16
    0.88
    27
    0.87
    1000
    0.87
    13
    0.85
    8000
    0.85
    11
    0.84
    Act Density 0.026%

    No Known Activations