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

    Neuronpedia

    INDEX
    Explanations

    technical language and specific code-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dür
    -0.17
    otta
    -0.15
    hiro
    -0.15
    uft
    -0.15
    erten
    -0.14
     Moreno
    -0.14
    aggable
    -0.14
    dır
    -0.14
    nea
    -0.14
    bao
    -0.13
    POSITIVE LOGITS
    adius
    0.15
    SYS
    0.15
    nock
    0.14
    IDAD
    0.14
    gid
    0.13
    ill
    0.13
    anship
    0.13
    ame
    0.13
    roids
    0.13
    IQ
    0.13
    Act Density 0.008%

    No Known Activations