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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures, particularly in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /wp
    -0.15
    Äĥr
    -0.14
    arat
    -0.14
    ^^^^
    -0.14
    enburg
    -0.14
    æĿ¡
    -0.14
    ighting
    -0.13
    rouw
    -0.13
    UCE
    -0.13
     rat
    -0.13
    POSITIVE LOGITS
    ÏĢά
    0.16
     Berk
    0.15
    ạo
    0.14
     Dodd
    0.14
    -UA
    0.14
    ãĥĶãĥ¼
    0.13
    osate
    0.13
    .!
    0.13
     Grü
    0.13
    iff
    0.13
    Act Density 0.395%

    No Known Activations