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

    Neuronpedia

    INDEX
    Explanations

    terms related to eating habits and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     censi
    -0.80
     }));
    -0.79
    ']))
    -0.78
     Prou
    -0.78
    ρίου
    -0.77
    IMI
    -0.76
     McCullough
    -0.73
    hii
    -0.72
     necesar
    -0.71
    '])){
    -0.68
    POSITIVE LOGITS
     eat
    1.73
     eaten
    1.59
     EAT
    1.59
     eats
    1.52
     Eat
    1.50
     eating
    1.49
    Eat
    1.42
     Eating
    1.39
    Eating
    1.38
     ate
    1.35
    Act Density 0.073%

    No Known Activations