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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and code-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.58
    (
    -0.57
    מוד
    -0.57
    ,
    -0.57
    ​
    -0.55
    Hig
    -0.54
    extAlignment
    -0.52
    оборот
    -0.52
    [/
    -0.52
    writeHead
    -0.52
    POSITIVE LOGITS
    .$.
    1.24
    __).
    1.23
    $.}
    1.23
    +'.
    1.19
    */].
    1.17
    ("%.
    1.17
    \.
    1.16
    ])).
    1.15
     /\.
    1.15
    +".
    1.15
    Act Density 0.692%

    No Known Activations