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

    Neuronpedia

    INDEX
    Explanations

    technical terms and formatting elements related to mathematical equations and tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.18
    uai
    -0.17
    Calibri
    -0.16
    éĻ£
    -0.15
    ister
    -0.15
    ISTER
    -0.14
    arf
    -0.14
    elf
    -0.14
    sted
    -0.14
    coni
    -0.14
    POSITIVE LOGITS
    idot
    0.15
     Åŀah
    0.14
     Kauf
    0.14
    оÑģÑĤи
    0.14
    nah
    0.14
    opsis
    0.13
    bat
    0.13
    pong
    0.13
    :↵↵↵↵↵↵
    0.13
     Watkins
    0.13
    Act Density 0.010%

    No Known Activations