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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atak
    -0.16
    opol
    -0.15
     OTHERWISE
    -0.15
    izzy
    -0.15
    hton
    -0.15
     Emma
    -0.14
    ushman
    -0.14
     ADDR
    -0.14
    alls
    -0.14
    obre
    -0.14
    POSITIVE LOGITS
    åIJ
    0.15
    AGO
    0.14
    reich
    0.14
    ãĥ¼ãĤ¯
    0.14
    wer
    0.13
     OBJ
    0.13
    cke
    0.13
    мÑı
    0.13
    iversite
    0.13
    UnitTest
    0.13
    Act Density 0.047%

    No Known Activations