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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ud" and its variations, likely indicating a focus on a specific name or term in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     priceless
    -0.56
     Metatron
    -0.55
     Stras
    -0.55
     Tsarnaev
    -0.55
     sands
    -0.55
     Constantin
    -0.54
     plates
    -0.54
     anonymity
    -0.54
     abiding
    -0.54
     scarce
    -0.54
    POSITIVE LOGITS
    geon
    1.59
    geoning
    1.49
    apest
    1.32
    imentary
    1.19
    geons
    1.19
    gel
    1.07
    gets
    1.06
    iquette
    1.05
    ges
    1.04
    gie
    1.02
    Act Density 0.036%

    No Known Activations