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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by "@" symbol

    oai_token-act-pair · gpt-3.5-turbo

    social media handles or mentions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boko
    -0.93
    ADRA
    -0.91
     strawberries
    -0.84
    Marginal
    -0.83
     crops
    -0.79
    adra
    -0.78
    ļéĨĴ
    -0.78
    esta
    -0.78
     caucuses
    -0.77
     Beacon
    -0.77
    POSITIVE LOGITS
     Mike
    2.02
    Mike
    1.96
     Michael
    1.94
    Michael
    1.86
     MIC
    1.28
     MJ
    1.26
    MIC
    1.23
    ichael
    1.06
     Mick
    1.04
    MJ
    1.02
    Act Density 0.180%

    No Known Activations