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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating frequency, regularity, or normalcy, especially in contrast to exceptions or irregularities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĸла
    -0.16
    ollen
    -0.14
    ÑģÑĤин
    -0.14
    ãĥ¼ãĥł
    -0.14
     initially
    -0.14
    _ste
    -0.14
    ProgressHUD
    -0.14
    odes
    -0.13
    òi
    -0.13
    .Layer
    -0.13
    POSITIVE LOGITS
     Pitch
    0.17
    Pitch
    0.16
    antro
    0.15
     Hacker
    0.15
     Bruce
    0.15
    ovit
    0.15
    ylon
    0.15
    anda
    0.15
    istrovstvÃŃ
    0.15
    िह
    0.14
    Act Density 0.303%

    No Known Activations