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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of reports and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reported
    -0.79
     reported
    -0.77
    reported
    -0.74
     Reported
    -0.71
    Reports
    -0.70
     Reports
    -0.65
    reports
    -0.65
    Report
    -0.64
     reports
    -0.64
    REPORT
    -0.61
    POSITIVE LOGITS
    orial
    0.69
    NameInMap
    0.59
     card
    0.57
    WebVitals
    0.56
    exitRule
    0.54
     Card
    0.51
    featureID
    0.50
     Cardoso
    0.50
    card
    0.46
    ORIAL
    0.46
    Act Density 0.104%

    No Known Activations