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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations like subtraction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subtraction or rounding in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.01
    lights
    -0.69
    eer
    -0.69
    gling
    -0.64
    gence
    -0.63
    erver
    -0.62
    ergy
    -0.62
    alogy
    -0.62
     Emirates
    -0.62
    andum
    -0.61
    POSITIVE LOGITS
    ritis
    0.83
    otic
    0.76
    ilet
    0.76
    otics
    0.75
    ropy
    0.73
     Bowman
    0.70
     Byr
    0.69
     Lew
    0.68
    stown
    0.68
    Lew
    0.67
    Act Density 0.062%

    No Known Activations