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

    Neuronpedia

    INDEX
    Explanations

    phrases related to swallowing or ingestion

    oai_token-act-pair · gpt-3.5-turbo

    actions related to consuming or ingesting substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ements
    -0.83
    ////////////////
    -0.78
    ////////
    -0.72
    iances
    -0.68
    isphere
    -0.66
    ohn
    -0.66
    iator
    -0.65
    efeated
    -0.65
    say
    -0.64
    croft
    -0.63
    POSITIVE LOGITS
     gum
    0.87
    ipes
    0.84
     swallow
    0.81
    meat
    0.80
    anut
    0.79
     worms
    0.76
     flakes
    0.75
    cake
    0.74
    IBLE
    0.73
    dragon
    0.72
    Act Density 0.075%

    No Known Activations