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

    Neuronpedia

    INDEX
    Explanations

    references to eating and drinking behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbene
    -0.74
    uttosto
    -0.69
     Deum
    -0.68
     désol
    -0.67
     giudi
    -0.66
     Processors
    -0.65
     vettore
    -0.64
    muerzo
    -0.63
     auroit
    -0.62
     illustrazione
    -0.62
    POSITIVE LOGITS
     drinking
    1.46
     eating
    1.44
     Drinking
    1.24
     Eating
    1.18
     riding
    1.15
     shooting
    1.14
    eating
    1.13
     sleeping
    1.11
    drinking
    1.10
     cooking
    1.09
    Act Density 0.219%

    No Known Activations