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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize comparative aspects or degrees of something being greater or more significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.87
    ilts
    -0.85
    mates
    -0.83
    mate
    -0.82
    uly
    -0.80
    agra
    -0.77
    vale
    -0.70
    iard
    -0.69
    gio
    -0.69
    only
    -0.68
    POSITIVE LOGITS
     than
    1.40
     complicated
    1.12
     sophisticated
    1.07
     nuanced
    1.05
    than
    1.03
     ambitious
    1.02
     complex
    1.02
     manageable
    1.02
     expensive
    1.01
     forgiving
    0.95
    Act Density 0.074%

    No Known Activations