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

    Neuronpedia

    INDEX
    Explanations

    recipes or cooking instructions containing specific foods

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of recipes, occupations, and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atever
    -0.64
    laughs
    -0.63
    soType
    -0.60
     eternity
    -0.60
     Knowing
    -0.59
    DragonMagazine
    -0.58
    issance
    -0.57
     Reading
    -0.56
    Enough
    -0.56
    enough
    -0.56
    POSITIVE LOGITS
     involve
    1.18
     contain
    1.11
     are
    1.07
     require
    1.04
     were
    1.03
     originate
    1.01
     have
    1.00
     rely
    0.97
     incorporate
    0.93
     adhere
    0.90
    Act Density 0.332%

    No Known Activations