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

    Neuronpedia

    INDEX
    Explanations

    business-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential, properties, and economic or environmental aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stat
    -0.68
    GA
    -0.67
    Weather
    -0.67
    prep
    -0.66
    itte
    -0.65
    cot
    -0.64
    rir
    -0.64
    ozy
    -0.63
    Spoiler
    -0.62
    stat
    -0.62
    POSITIVE LOGITS
     underlying
    0.80
     associated
    0.80
     emanating
    0.74
     Tuls
    0.74
     surrounding
    0.73
     continuum
    0.73
     inherent
    0.72
     underpin
    0.71
     afforded
    0.70
    jriwal
    0.68
    Act Density 0.226%

    No Known Activations