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

    Neuronpedia

    INDEX
    Explanations

    instances of specific nouns and their variations in different languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ales
    -0.17
    ync
    -0.16
    :animated
    -0.16
    emas
    -0.15
    ohl
    -0.15
    ande
    -0.15
    åŁŁ
    -0.14
    alat
    -0.14
    hs
    -0.14
    fty
    -0.14
    POSITIVE LOGITS
    ude
    0.19
    anian
    0.15
    elen
    0.14
     поÑģ
    0.14
    ÏģιÏĥÏĦ
    0.14
     partition
    0.14
     Springs
    0.14
     Dread
    0.13
    owo
    0.13
     Seeder
    0.13
    Act Density 0.021%

    No Known Activations