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

    Neuronpedia

    INDEX
    Explanations

    fractions and measurements in recipe instructions

    oai_token-act-pair · gpt-3.5-turbo

    fractions and measurements related to recipe ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daly
    -0.64
     adm
    -0.63
     Morg
    -0.62
     gorilla
    -0.61
     vulnerable
    -0.60
     Syl
    -0.60
     Wes
    -0.60
     Vi
    -0.59
     Cele
    -0.59
     promising
    -0.59
    POSITIVE LOGITS
    oct
    0.96
    1000
    0.95
    4
    0.90
    opal
    0.89
    2
    0.89
    8000
    0.89
    3
    0.86
    ËĪ
    0.85
    \/\/
    0.83
    800
    0.82
    Act Density 0.031%

    No Known Activations