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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and the structure of the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     okuyayım
    -0.78
     nakalista
    -0.76
     EClass
    -0.72
    parsedMessage
    -0.71
    transQ
    -0.65
    Espèce
    -0.64
     дописавши
    -0.64
    mybatisplus
    -0.64
    UrlResolution
    -0.62
    Manbalar
    -0.62
    POSITIVE LOGITS
    ↵↵
    1.00
     They
    0.90
     These
    0.84
     This
    0.83
     There
    0.80
     It
    0.79
     However
    0.77
     The
    0.74
     }}$.
    0.73
     Also
    0.73
    Act Density 0.553%

    No Known Activations