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

    Neuronpedia

    INDEX
    Explanations

    file paths and directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eza
    -0.15
    _INTR
    -0.15
    peaker
    -0.15
     ç¥
    -0.15
    unken
    -0.15
     Pazar
    -0.15
    ê·¸ëŀĺ
    -0.14
    ÙĪزÙĩ
    -0.14
    sek
    -0.14
    monds
    -0.13
    POSITIVE LOGITS
    omba
    0.16
     airs
    0.15
     airspace
    0.15
    OutputStream
    0.14
     cow
    0.14
    airs
    0.14
     جاÙĨ
    0.14
    riad
    0.14
    InputStream
    0.14
    aviest
    0.13
    Act Density 0.020%

    No Known Activations