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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms, especially those related to high performance or risk

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk and capacity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.83
    agi
    -0.79
    ãĤ¨ãĥ«
    -0.78
    adier
    -0.73
    =-=-=-=-
    -0.71
    umi
    -0.71
    ften
    -0.69
    alter
    -0.68
    chy
    -0.67
    IGHTS
    -0.66
    POSITIVE LOGITS
     (>
    0.96
     earners
    0.84
     versions
    0.67
     (<
    0.66
     solutions
    0.65
    imensional
    0.65
     residential
    0.63
     Sodium
    0.63
     computing
    0.63
     interval
    0.62
    Act Density 0.115%

    No Known Activations