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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant actions or state declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DefaultValue
    -0.15
    icolon
    -0.14
    ynos
    -0.14
    abela
    -0.14
    EPHIR
    -0.14
    æİĴ
    -0.14
    Enumeration
    -0.14
    aning
    -0.13
    309
    -0.13
    145
    -0.13
    POSITIVE LOGITS
    éħ¸
    0.16
    ocha
    0.15
    leen
    0.14
     ec
    0.14
    vit
    0.14
    ocus
    0.14
     nonatomic
    0.13
    ãĥ¼ãĥł
    0.13
    -force
    0.13
     invisible
    0.13
    Act Density 0.015%

    No Known Activations