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

    Neuronpedia

    INDEX
    Explanations

    references to bias and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lad
    -0.15
    ahl
    -0.15
    ero
    -0.15
     Rah
    -0.15
    iber
    -0.14
    io
    -0.14
    kap
    -0.14
    pick
    -0.14
    ahu
    -0.14
     Jah
    -0.14
    POSITIVE LOGITS
    ÑĢод
    0.16
    empre
    0.16
    ogg
    0.15
    rana
    0.14
    antlr
    0.14
    rif
    0.14
    گر
    0.14
    ़à¥į
    0.14
    ÑĢд
    0.14
    aland
    0.14
    Act Density 0.011%

    No Known Activations