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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the effects and impacts of various substances or interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nelly
    -0.17
    ankan
    -0.16
    WA
    -0.16
    odule
    -0.15
    .DefaultCellStyle
    -0.15
    umper
    -0.14
     $($
    -0.14
    ãĤ´ãĥª
    -0.14
    ection
    -0.14
    ิà¸ģ
    -0.14
    POSITIVE LOGITS
    mite
    0.15
    çĻº
    0.15
    icos
    0.15
     Sawyer
    0.15
    71
    0.14
    ç·Ĵ
    0.14
     legalized
    0.14
    ros
    0.14
    CS
    0.13
    orda
    0.13
    Act Density 0.037%

    No Known Activations