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

    Neuronpedia

    INDEX
    Explanations

    specific types of content in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.19
    obo
    -0.18
    issa
    -0.17
    å¸ģ
    -0.17
    ovi
    -0.17
    igh
    -0.16
    ìĿĦ
    -0.16
    anda
    -0.16
    imes
    -0.16
    opi
    -0.16
    POSITIVE LOGITS
    ng
    0.20
    lation
    0.19
    ngen
    0.19
    ght
    0.19
    zed
    0.18
    erten
    0.18
    ÅĽmy
    0.18
    اÙģتÙĩ
    0.18
    gn
    0.17
    rical
    0.17
    Act Density 0.113%

    No Known Activations