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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its frequency within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyse
    -0.18
    VERRIDE
    -0.18
    erli
    -0.15
    ginas
    -0.15
    heits
    -0.15
    pixels
    -0.15
    μοÏĤ
    -0.14
    ecko
    -0.14
     bols
    -0.14
    azzi
    -0.14
    POSITIVE LOGITS
     overall
    0.17
     fact
    0.17
     also
    0.17
     Overall
    0.16
    fact
    0.16
    Âł
    0.15
     numeral
    0.15
     Also
    0.15
     Allan
    0.15
    Overall
    0.15
    Act Density 0.094%

    No Known Activations