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

    Neuronpedia

    INDEX
    Explanations

    references to orders, honors, or titles of nobility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.17
    argas
    -0.16
    ãģĭãģĹ
    -0.16
    mai
    -0.14
    eus
    -0.14
    eon
    -0.14
    zb
    -0.14
    ali
    -0.14
    apes
    -0.14
    omi
    -0.14
    POSITIVE LOGITS
     Reform
    0.17
    verty
    0.14
    iasi
    0.14
    ÑĮе
    0.14
    agne
    0.14
    oksen
    0.13
    γη
    0.13
    acey
    0.13
    [#
    0.13
     Crescent
    0.13
    Act Density 0.006%

    No Known Activations