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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to organizations or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    					↵
    -0.18
    hips
    -0.17
    .future
    -0.16
    foundland
    -0.16
    rug
    -0.15
    itz
    -0.15
    ish
    -0.15
    firm
    -0.15
    erin
    -0.15
    errupted
    -0.14
    POSITIVE LOGITS
    teenth
    0.23
    entimes
    0.20
    erty
    0.20
    ron
    0.17
    oul
    0.16
    dom
    0.16
    tant
    0.16
    ÛĮا
    0.15
    icult
    0.15
    .nih
    0.15
    Act Density 0.595%

    No Known Activations