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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the letter 'm' in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aze
    -0.18
    id
    -0.17
    urd
    -0.16
    ux
    -0.16
    wat
    -0.16
    end
    -0.15
    wins
    -0.15
    b
    -0.15
    and
    -0.15
    agate
    -0.14
    POSITIVE LOGITS
     m
    0.19
    ellow
    0.16
    RGBA
    0.15
    omik
    0.15
    ippo
    0.15
    llu
    0.15
    amarin
    0.14
     Rencontres
    0.14
    aled
    0.14
    layui
    0.14
    Act Density 0.021%

    No Known Activations