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

    Neuronpedia

    INDEX
    Explanations

    recipe ingredients with specific measurements

    oai_token-act-pair · gpt-3.5-turbo

    fractions and measurements typically used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fletcher
    -0.77
     Elliott
    -0.71
     lines
    -0.68
    hower
    -0.66
     Cantor
    -0.65
     Vaughan
    -0.65
     Daly
    -0.64
     Bain
    -0.62
    achus
    -0.62
     usher
    -0.62
    POSITIVE LOGITS
    ËĪ
    1.09
    oct
    1.00
    carbon
    0.93
    pmwiki
    0.89
    opal
    0.86
    20
    0.84
    Flickr
    0.83
    4
    0.83
    1000
    0.82
    5
    0.82
    Act Density 0.023%

    No Known Activations