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

    Neuronpedia

    INDEX
    Explanations

    references to legal standards and thresholds for evidence in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.91
    tagHelperRunner
    -0.88
    transQ
    -0.88
     مشين
    -0.85
     defaultstate
    -0.83
     OFDb
    -0.83
     myſelf
    -0.81
    Autoritní
    -0.81
    aarrggbb
    -0.80
    RegressionTest
    -0.79
    POSITIVE LOGITS
     entire
    0.63
     could
    0.58
    ServiceModel
    0.55
     it
    0.53
    ↵↵
    0.50
    romole
    0.49
     a
    0.49
     make
    0.49
    flü
    0.48
     de
    0.48
    Act Density 0.152%

    No Known Activations