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

    Neuronpedia

    INDEX
    Explanations

    numerical values and associated descriptors or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.20
     coron
    -0.16
    zk
    -0.16
     via
    -0.15
     меÑĤалли
    -0.15
     Polish
    -0.15
    via
    -0.15
    én
    -0.15
    unas
    -0.15
    pire
    -0.14
    POSITIVE LOGITS
     Ñ
    0.19
    Ñĺ
    0.18
    ÑĻ
    0.17
    Ðĭ
    0.16
     Äij
    0.16
    ufe
    0.16
    Äij
    0.15
    alice
    0.15
     uveden
    0.15
    ÑĴ
    0.15
    Act Density 0.029%

    No Known Activations