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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koc
    -0.67
     Weldon
    -0.66
     Loeb
    -0.63
     Grinder
    -0.59
     Hirst
    -0.59
    haran
    -0.58
     kal
    -0.58
    grub
    -0.57
     Walsh
    -0.57
     Faust
    -0.57
    POSITIVE LOGITS
    </blockquote>
    1.80
    \]
    1.14
    findpost
    1.11
    httphttps
    1.07
    )";
    1.03
    }\]
    0.99
    )";
    0.94
    .";
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ContentAsync
    0.86
    Act Density 0.051%

    No Known Activations