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

    Neuronpedia

    INDEX
    Explanations

    contractions of words, especially those expressing possession like "don't" and "´"

    oai_token-act-pair · gpt-3.5-turbo

    unusual or distinctive punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acknowled
    -0.83
     iceberg
    -0.71
     congr
    -0.70
     aristocracy
    -0.69
     congratulations
    -0.67
    ATURES
    -0.67
     acknow
    -0.66
    lehem
    -0.66
     ashes
    -0.66
    artifacts
    -0.66
    POSITIVE LOGITS
    Tex
    0.78
    -|
    0.74
    elle
    0.72
    _>
    0.70
    Da
    0.70
    olit
    0.69
    Daddy
    0.69
    SEC
    0.68
    Coach
    0.67
    ë
    0.67
    Act Density 0.000%

    No Known Activations