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

    Neuronpedia

    INDEX
    Explanations

    undercooked and prepared food items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     salute
    -0.72
     millenn
    -0.71
     wave
    -0.68
    PDATE
    -0.67
     lyn
    -0.65
     jealous
    -0.63
     physique
    -0.63
    itans
    -0.63
     preacher
    -0.63
     semantic
    -0.62
    POSITIVE LOGITS
    cooked
    2.71
    performing
    1.62
    obl
    1.37
    sense
    1.04
    alcohol
    1.03
    hur
    0.98
    capacity
    0.88
     unexpectedly
    0.86
    flu
    0.85
    xc
    0.84
    Act Density 0.043%

    No Known Activations