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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols commonly used in digital text and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.74
    oa̍t
    -0.69
    AsUp
    -0.68
    tre
    -0.65
    ară
    -0.65
    dinga
    -0.64
    DoubleQuotes
    -0.64
     gehalten
    -0.63
    </em>
    -0.63
    ceğim
    -0.63
    POSITIVE LOGITS
    &#
    1.37
     '&#
    1.34
     &#
    1.25
    â
    1.18
     â
    1.10
    ;&#
    1.08
    Câ
    0.95
     Câ
    0.83
     Mâ
    0.82
    ="&#
    0.79
    Act Density 0.233%

    No Known Activations