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

    Neuronpedia

    INDEX
    Explanations

    punctuation and brace characters commonly used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arie
    -0.15
    mith
    -0.15
    stdexcept
    -0.14
    iae
    -0.14
    ëĿ¼ìĿ¸
    -0.14
    WI
    -0.14
    amerate
    -0.13
    rst
    -0.13
     Wheeler
    -0.13
    ssue
    -0.13
    POSITIVE LOGITS
    aca
    0.15
     Vive
    0.15
    ÑĢеб
    0.15
    ij¸
    0.15
    ophe
    0.14
     alike
    0.14
    912
    0.14
     souÄįas
    0.14
    abor
    0.13
    BOR
    0.13
    Act Density 0.012%

    No Known Activations