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

    references to specific brands, products, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    algia
    -0.77
    bent
    -0.70
    iquette
    -0.69
    bring
    -0.65
    chemy
    -0.64
    axter
    -0.64
    pires
    -0.64
    autions
    -0.63
    comes
    -0.61
    poons
    -0.61
    POSITIVE LOGITS
    .[
    0.88
    +.
    0.87
    .''.
    0.84
    *.
    0.83
    .<
    0.81
     whilst
    0.81
     pursuant
    0.81
    .</
    0.80
     irrespective
    0.80
     whenever
    0.80
    Act Density 0.642%

    No Known Activations