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

    Neuronpedia

    INDEX
    Explanations

    references to actions and states associated with usage and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ucwords
    -0.15
    ubber
    -0.14
    velle
    -0.14
    SKIP
    -0.13
     wardrobe
    -0.13
    ainer
    -0.13
    дÑĥ
    -0.13
     capitalized
    -0.13
    ÙĪÙĦا
    -0.13
    .LA
    -0.13
    POSITIVE LOGITS
    #
    0.16
     Aç
    0.15
    igon
    0.15
     Plantae
    0.15
    ilion
    0.15
     Exped
    0.15
    reed
    0.14
    igu
    0.14
    CanBe
    0.14
     Butter
    0.14
    Act Density 0.031%

    No Known Activations