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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric characters and symbols, indicating a focus on technical or code-like content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bris
    -0.15
    ucus
    -0.14
    翼
    -0.14
    berman
    -0.14
     пÑĢиÑĤ
    -0.13
    ABCDEFGHI
    -0.13
    fty
    -0.13
    ossier
    -0.13
     sac
    -0.13
    ace
    -0.13
    POSITIVE LOGITS
    sville
    0.17
    inars
    0.16
    agues
    0.16
     Chall
    0.15
    .xz
    0.15
    amp
    0.14
    616
    0.14
    å°ļ
    0.13
    >Returns
    0.13
    tons
    0.13
    Act Density 0.037%

    No Known Activations