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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roland
    -0.15
    ÙĪدة
    -0.14
    redo
    -0.14
    SizeMode
    -0.14
    uffy
    -0.13
    /popper
    -0.13
    asant
    -0.13
    rollo
    -0.13
    quirrel
    -0.13
     stripslashes
    -0.12
    POSITIVE LOGITS
     report
    1.17
     reports
    1.03
     Report
    0.99
    report
    0.97
     REPORT
    0.92
    -report
    0.91
    Report
    0.91
     reporting
    0.89
     Reports
    0.89
    .report
    0.87
    Act Density 0.219%

    No Known Activations