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

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with a capital letter and followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eye
    -0.74
    Contents
    -0.74
    soType
    -0.72
    iew
    -0.67
    views
    -0.67
    andowski
    -0.67
    ontent
    -0.67
    Examples
    -0.67
    Background
    -0.64
    sticks
    -0.64
    POSITIVE LOGITS
     precursor
    1.01
     subsidiary
    0.90
    hem
    0.89
     fictitious
    0.87
     shadowy
    0.87
     fictional
    0.87
     predecessor
    0.86
     perennial
    0.85
     successor
    0.85
     venerable
    0.85
    Act Density 0.110%

    No Known Activations