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

    Neuronpedia

    INDEX
    Explanations

    references to ongoing projects or initiatives and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downt
    -0.16
    aki
    -0.15
    esis
    -0.15
     kia
    -0.14
     overhead
    -0.14
     baÄŁ
    -0.14
    283
    -0.14
     Hann
    -0.13
    447
    -0.13
    iba
    -0.13
    POSITIVE LOGITS
     ç¯
    0.17
     Ñģб
    0.16
    Ľ
    0.15
     Cove
    0.15
    .vx
    0.15
    cul
    0.15
    ãĤ·ãĤ¢
    0.15
    orro
    0.14
    DBObject
    0.14
    endar
    0.14
    Act Density 0.105%

    No Known Activations