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

    Neuronpedia

    INDEX
    Explanations

    specific formatted text markings, potentially indicating changes in position or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular character or entity symbolized by the character "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decomp
    -0.97
     fortun
    -0.73
     interf
    -0.69
     horizont
    -0.67
     shack
    -0.66
     Codec
    -0.65
     Yor
    -0.64
     assemb
    -0.63
     seiz
    -0.63
     mosaic
    -0.62
    POSITIVE LOGITS
    ¬
    1.18
    ¢
    1.09
    Ļ
    1.09
    Ħ¢
    1.07
    £
    1.06
    ĸ
    1.03
    ¹
    1.00
    Ī
    1.00
    ı
    1.00
    ¡
    0.99
    Act Density 0.333%

    No Known Activations