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

    Neuronpedia

    INDEX
    Explanations

    words related to drinking and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.05
     Weldon
    -0.80
     escul
    -0.80
    ,:);
    -0.78
     Egli
    -0.78
     Stag
    -0.78
     épis
    -0.78
    )++;
    -0.78
    UserScript
    -0.77
     hâte
    -0.77
    POSITIVE LOGITS
     drinks
    1.63
     drink
    1.56
     Drink
    1.51
    Drink
    1.47
     Drinks
    1.43
    Drinks
    1.36
    drinks
    1.36
    drink
    1.33
     DRINK
    1.31
     drinking
    1.13
    Act Density 0.092%

    No Known Activations