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

    Neuronpedia

    INDEX
    Explanations

    references to drinking alcohol or other beverages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Weldon
    -0.74
    esgue
    -0.71
    มาย
    -0.69
    sites
    -0.64
    chong
    -0.64
    sis
    -0.63
     Peta
    -0.63
     nido
    -0.62
     Executes
    -0.62
    ridad
    -0.62
    POSITIVE LOGITS
     drink
    1.60
     Drink
    1.58
    Drink
    1.52
     drinking
    1.50
    drink
    1.49
     DRINK
    1.47
     drinks
    1.44
     Drinking
    1.38
     drank
    1.34
    Drinking
    1.32
    Act Density 0.123%

    No Known Activations