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

    Neuronpedia

    INDEX
    Explanations

    symbols, numbers, and formatting elements commonly used in programming and data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovah
    -0.17
    sian
    -0.15
     ÑĤв
    -0.15
    burgh
    -0.15
    IDER
    -0.14
    adro
    -0.14
    едж
    -0.14
    .Void
    -0.14
     OTHERWISE
    -0.14
    &C
    -0.14
    POSITIVE LOGITS
     third
    0.38
     Third
    0.35
    Third
    0.31
     THIRD
    0.30
    third
    0.29
    -third
    0.29
     thirds
    0.29
    _third
    0.28
    第ä¸ī
    0.28
     第ä¸ī
    0.27
    Act Density 0.265%

    No Known Activations