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

    Neuronpedia

    INDEX
    Explanations

    comparisons or differences involving health outcomes or socioeconomic factors

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating disparities or differences among groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.70
    Animation
    -0.67
    huge
    -0.67
    iHUD
    -0.67
    Hopefully
    -0.65
    atis
    -0.64
     ¯
    -0.64
    Hack
    -0.63
     Feeling
    -0.63
    ãĤ¡
    -0.63
    POSITIVE LOGITS
     counterparts
    1.16
     those
    1.13
     controls
    1.05
     comparable
    1.04
     non
    1.02
     unex
    1.02
     untreated
    1.02
     unin
    1.00
     others
    1.00
     nont
    1.00
    Act Density 0.145%

    No Known Activations