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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.16
    ennes
    -0.15
    peror
    -0.14
    dera
    -0.14
    _domains
    -0.14
    doch
    -0.14
     abi
    -0.14
     Ñĩим
    -0.14
    atak
    -0.14
    Ĥ¹
    -0.14
    POSITIVE LOGITS
    urf
    0.14
    EA
    0.14
    uffman
    0.14
     Jeb
    0.14
     Jed
    0.13
    iode
    0.13
    ild
    0.13
    ildo
    0.13
     refr
    0.13
    kes
    0.13
    Act Density 0.106%

    No Known Activations