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

    Neuronpedia

    INDEX
    Explanations

    references to reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clay
    -0.60
    lowed
    -0.57
    ANTAGES
    -0.57
     Zweig
    -0.57
    patreon
    -0.57
     onlyOwner
    -0.56
    OGEN
    -0.56
     magne
    -0.55
    malle
    -0.55
     Egy
    -0.55
    POSITIVE LOGITS
     report
    3.10
    Report
    2.96
     Report
    2.95
    report
    2.81
     REPORT
    2.77
     reports
    2.66
     Reports
    2.60
    REPORT
    2.53
    reports
    2.43
    Reports
    2.41
    Act Density 0.055%

    No Known Activations