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

    Neuronpedia

    INDEX
    Explanations

    terms related to statutes and legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erp
    -0.19
    aft
    -0.16
    ñana
    -0.16
    neau
    -0.15
    siz
    -0.15
    ä¸Ī
    -0.15
    ÏĢε
    -0.15
    ahr
    -0.14
    umber
    -0.14
    andum
    -0.14
    POSITIVE LOGITS
    istically
    0.40
    utory
    0.39
    istical
    0.39
    istic
    0.34
    ISTICS
    0.32
    utes
    0.30
    istica
    0.29
    istik
    0.29
    utor
    0.29
    ute
    0.27
    Act Density 0.016%

    No Known Activations