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

    Neuronpedia

    INDEX
    Explanations

    references to PDFs and related documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unge
    -0.15
    ade
    -0.15
    aches
    -0.15
    eker
    -0.14
    aven
    -0.14
     Engl
    -0.14
    rng
    -0.14
    ÄĽk
    -0.13
    ustr
    -0.13
    uš
    -0.13
    POSITIVE LOGITS
    s
    0.22
    417
    0.20
    scape
    0.19
    sam
    0.16
    sah
    0.16
    sik
    0.15
    sak
    0.15
    UPI
    0.15
    sil
    0.15
    sand
    0.15
    Act Density 0.014%

    No Known Activations