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

    Neuronpedia

    INDEX
    Explanations

    introductory elements of discussions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Squares
    -0.86
     Krie
    -0.81
    ágeno
    -0.80
    httphttps
    -0.80
     squares
    -0.80
    égek
    -0.79
    movq
    -0.78
    期刊论文
    -0.74
    crapers
    -0.73
    hopped
    -0.73
    POSITIVE LOGITS
    nt
    1.26
     NT
    1.09
    NT
    1.06
     Munt
    1.01
    UNT
    1.01
    unt
    0.96
     nt
    0.94
     UNT
    0.92
    önt
    0.89
     Kunt
    0.87
    Act Density 0.054%

    No Known Activations