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

    Neuronpedia

    INDEX
    Explanations

    occurrences of braces and brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raj
    -0.16
    quette
    -0.15
    atego
    -0.15
    Abstract
    -0.15
    upp
    -0.15
    prot
    -0.15
    razy
    -0.14
     Rodrig
    -0.14
    æºĸ
    -0.14
    TOTYPE
    -0.14
    POSITIVE LOGITS
     Momentum
    0.16
    chu
    0.15
     Cous
    0.15
     кал
    0.13
    ItemSelectedListener
    0.13
    ONS
    0.13
    tery
    0.13
     corpor
    0.13
     ener
    0.13
    ói
    0.13
    Act Density 0.017%

    No Known Activations