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

    Neuronpedia

    INDEX
    Explanations

    references to dinner and related dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.78
    inguez
    -0.72
    ließlich
    -0.72
    nds
    -0.69
    })));
    -0.68
    müş
    -0.68
    robial
    -0.67
    cluse
    -0.66
     exud
    -0.66
    utenants
    -0.63
    POSITIVE LOGITS
     dinner
    2.15
     Dinner
    2.07
     DINNER
    2.02
     dinners
    1.91
    dinner
    1.90
    Dinner
    1.88
     dîner
    1.33
     supper
    1.15
     Supper
    1.07
     Din
    1.07
    Act Density 0.055%

    No Known Activations