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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and references to entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quiv
    -0.15
    жи
    -0.15
    194
    -0.14
    ITIONS
    -0.14
    743
    -0.14
    aler
    -0.14
    228
    -0.14
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.14
    173
    -0.14
    403
    -0.14
    POSITIVE LOGITS
    pei
    0.16
     Roths
    0.14
    Breadcrumb
    0.14
    eed
    0.14
    -League
    0.14
    ÑģÑĤеÑĢ
    0.14
    _RTC
    0.14
    eneg
    0.13
    eltas
    0.13
    isted
    0.13
    Act Density 0.005%

    No Known Activations