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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and terms indicating quantity or variability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Winning
    -0.15
    tractive
    -0.15
    659
    -0.14
    ught
    -0.13
    cek
    -0.13
    oucher
    -0.13
    ip
    -0.13
     bahwa
    -0.13
     kromÄĽ
    -0.13
    uren
    -0.13
    POSITIVE LOGITS
     being
    0.23
     with
    0.23
     having
    0.22
     them
    0.21
     ÙħÙĨÙĩا
    0.20
     davon
    0.20
     коÑĤоÑĢÑĭÑħ
    0.19
     ones
    0.19
     which
    0.18
     without
    0.18
    Act Density 0.097%

    No Known Activations