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

    Neuronpedia

    INDEX
    Explanations

    statistics and data related to various social and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    statistics and data related to crime and societal factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whim
    -0.70
     rebirth
    -0.67
     graft
    -0.66
     cloning
    -0.64
     extrad
    -0.64
     sabotage
    -0.62
     resurrect
    -0.61
     cac
    -0.59
     tink
    -0.59
     revel
    -0.59
    POSITIVE LOGITS
    adjusted
    0.94
     Median
    0.92
     Average
    0.91
     averaged
    0.91
     (âĪĴ
    0.90
     median
    0.88
     Percentage
    0.87
     (%
    0.85
    Average
    0.85
     statistically
    0.85
    Act Density 1.382%

    No Known Activations