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

    Neuronpedia

    INDEX
    Explanations

    terms related to corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ка
    -0.15
    quo
    -0.15
    ctic
    -0.15
    zure
    -0.15
    ãģ¥
    -0.14
    auss
    -0.14
    owler
    -0.14
    ategy
    -0.14
    rama
    -0.14
    _QMARK
    -0.13
    POSITIVE LOGITS
    ogne
    0.16
    untime
    0.15
    imoto
    0.15
    nech
    0.14
     Karn
    0.14
    .management
    0.14
    akash
    0.14
    isle
    0.14
    unami
    0.14
    oko
    0.13
    Act Density 0.009%

    No Known Activations