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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nuts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    naire
    -0.75
     Esper
    -0.69
     Vaj
    -0.69
    interstitial
    -0.66
     Stevenson
    -0.63
     Warsaw
    -0.62
     payable
    -0.62
    oping
    -0.61
     Plat
    -0.61
     Horses
    -0.60
    POSITIVE LOGITS
    ritional
    1.60
    rient
    1.50
    meg
    1.44
    rients
    1.42
    rition
    1.39
    tall
    1.15
    ricia
    1.06
    ella
    0.99
    tier
    0.97
    bush
    0.95
    Act Density 0.064%

    No Known Activations