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

    Neuronpedia

    INDEX
    Explanations

    numerical data indicative of statistics or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orne
    -0.17
    Å¡ek
    -0.16
    vů
    -0.15
    USR
    -0.14
    eden
    -0.14
    ÑĪка
    -0.14
     Wilde
    -0.14
    pson
    -0.13
    bian
    -0.13
    ABC
    -0.13
    POSITIVE LOGITS
    ιÏİ
    0.15
    gaard
    0.14
    subclass
    0.14
    žil
    0.14
     guarded
    0.14
    :///
    0.14
    isman
    0.13
    ãĥĪãĥ«
    0.13
    á»Ĩ
    0.13
     "../../../
    0.13
    Act Density 0.259%

    No Known Activations