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

    Neuronpedia

    INDEX
    Explanations

    formatted text elements, specifically those that emphasize importance or hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.95
    <eos>
    -0.85
    ↵↵↵
    -0.76
    ).
    -0.72
    \\
    -0.71
    ↵
    -0.69
    .
    -0.69
    ↵↵↵↵
    -0.66
                                   
    -0.63
     -
    -0.60
    POSITIVE LOGITS
    Datuak
    1.19
     nahilalakip
    1.12
    NUMX
    1.08
    richTextPanel
    1.03
     Chwiliwch
    1.01
    ->___
    0.99
    ]='\
    0.99
    ՚
    0.98
     $_"
    0.98
     myſelf
    0.98
    Act Density 0.054%

    No Known Activations