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

    Neuronpedia

    INDEX
    Explanations

    references to eating and drinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    eating and drinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.57
    fjspx
    -0.53
    Atsauces
    -0.53
    glGen
    -0.53
    WithIOException
    -0.52
     geſch
    -0.50
    tagPool
    -0.49
    ")));
    -0.49
    CreateModel
    -0.48
    featureID
    -0.48
    POSITIVE LOGITS
     consumption
    0.52
     eating
    0.52
     consumed
    0.50
     eaten
    0.49
    Eating
    0.47
     Eating
    0.45
     CONSUM
    0.45
     consommation
    0.42
    Consumption
    0.42
     devoured
    0.41
    Act Density 0.018%

    No Known Activations