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

    Neuronpedia

    INDEX
    Explanations

    tokens and phrases related to numerical or quantitative information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nab
    -0.16
     bal
    -0.15
     compens
    -0.15
    æĬľ
    -0.15
     soc
    -0.15
     AS
    -0.15
    edom
    -0.14
    tar
    -0.14
    ing
    -0.14
     as
    -0.14
    POSITIVE LOGITS
    eca
    0.19
    ĺ
    0.19
    agu
    0.16
    ÑĴ
    0.16
    ãĢģãĢģ
    0.15
    openh
    0.15
    égor
    0.15
    usat
    0.15
    zin
    0.15
    -Identifier
    0.14
    Act Density 0.006%

    No Known Activations