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

    Neuronpedia

    INDEX
    Explanations

    nuts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of nuts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.77
     Glas
    -0.70
     Volunteers
    -0.67
     Stall
    -0.67
    pless
    -0.66
    rio
    -0.64
    nered
    -0.63
    agall
    -0.61
    fax
    -0.61
     Rapp
    -0.61
    POSITIVE LOGITS
     nuts
    1.04
    hots
    0.82
    zyme
    0.82
     brittle
    0.81
    hed
    0.80
    nuts
    0.78
    omes
    0.74
    OME
    0.74
     bacon
    0.73
     Haram
    0.73
    Act Density 0.020%

    No Known Activations