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

    Neuronpedia

    INDEX
    Explanations

    elements and structures related to programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    genes
    -0.17
    abe
    -0.15
    iri
    -0.14
    è¼Ķ
    -0.14
    è¼Ŀ
    -0.14
    _PAYLOAD
    -0.14
    oola
    -0.14
    zel
    -0.14
    ÑĸÑĩнÑĸ
    -0.13
    TestingModule
    -0.13
    POSITIVE LOGITS
    æīĵ
    0.15
     Thornton
    0.15
     scor
    0.14
     bumper
    0.14
     underst
    0.14
     Dub
    0.14
    íĥĿ
    0.14
    Coin
    0.13
     elabor
    0.13
    ieber
    0.13
    Act Density 0.005%

    No Known Activations