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

    Neuronpedia

    INDEX
    Explanations

    the mathematical operation of subtraction

    oai_token-act-pair · gpt-3.5-turbo

    references to subtraction or related mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ezekiel
    -0.77
    powered
    -0.72
    Fight
    -0.69
    ride
    -0.69
    Hope
    -0.68
    Rocket
    -0.68
    responsive
    -0.65
    kin
    -0.65
    era
    -0.65
    Attorney
    -0.64
    POSITIVE LOGITS
     subt
    4.24
     subtract
    2.18
     subp
    1.49
     nuance
    1.17
     multiplication
    1.14
     subst
    1.12
     subtitles
    1.10
     nuances
    1.06
     multipl
    1.04
     quot
    1.02
    Act Density 0.017%

    No Known Activations