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

    Neuronpedia

    INDEX
    Explanations

    programming-related functions and methods within a code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     Majefty
    -1.06
     Efq
    -1.06
     Мексичка
    -1.05
     Houſe
    -1.04
     greateſt
    -1.01
     ―――――
    -1.00
    ſelf
    -0.98
     uſed
    -0.95
    saraba
    -0.95
    POSITIVE LOGITS
    ↵↵
    0.91
     ...
    0.82
    ↵
    0.82
    <eos>
    0.82
    </em>
    0.79
    </blockquote>
    0.73
    ();*/
    0.70
    </i>
    0.66
    [...]
    0.66
    }*/
    0.66
    Act Density 0.399%

    No Known Activations