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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns or terms related to organizations, places, and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atsby
    -0.20
    ãĥ¼ãĥ¬
    -0.17
    achten
    -0.15
    آ
    -0.15
    acia
    -0.15
    zan
    -0.15
    annel
    -0.15
    æīĺ
    -0.15
    iddet
    -0.14
    ón
    -0.14
    POSITIVE LOGITS
    kke
    0.17
    ota
    0.16
    ansen
    0.16
    ew
    0.16
    ANGED
    0.15
     Prem
    0.14
    ToStr
    0.14
    eba
    0.14
    LayoutConstraint
    0.14
    kd
    0.14
    Act Density 0.045%

    No Known Activations