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

    Neuronpedia

    INDEX
    Explanations

    the prefix 'non-' that indicates negation or absence

    oai_token-act-pair · gpt-3.5-turbo

    the term "non" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -1.01
     Showdown
    -0.81
     Cobra
    -0.80
     Oaks
    -0.75
     McGee
    -0.75
     Orchestra
    -0.75
     Sparrow
    -0.74
     Plate
    -0.74
     Banner
    -0.73
    hower
    -0.73
    POSITIVE LOGITS
    etheless
    1.13
    chal
    1.04
    fiction
    1.01
    epad
    0.99
    zero
    0.99
    aligned
    0.97
    profit
    0.95
    availability
    0.95
    linear
    0.95
    basic
    0.94
    Act Density 0.032%

    No Known Activations