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

    Neuronpedia

    INDEX
    Explanations

    numerals and punctuation that indicate lists or bullet points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.16
    ↵
    -0.15
    nt
    -0.14
    ika
    -0.14
    agi
    -0.13
    l
    -0.13
    <br
    -0.13
    ore
    -0.13
    ´s
    -0.13
    i
    -0.13
    POSITIVE LOGITS
    ³³
    0.18
     ...↵↵↵↵
    0.17
    /**↵↵
    0.16
     [...]↵↵
    0.16
    	The
    0.16
    ³³³³³
    0.15
    iversit
    0.15
    ³³³³³³
    0.15
    .Shapes
    0.15
    ï¸
    0.14
    Act Density 0.161%

    No Known Activations