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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    judge
    -0.15
    dit
    -0.15
    nor
    -0.15
    boru
    -0.15
    ãģ£ãģ±
    -0.15
    çĶ
    -0.14
    cus
    -0.14
    ä¸įäºĨ
    -0.14
    closure
    -0.14
    zem
    -0.14
    POSITIVE LOGITS
    ..
    0.15
    377
    0.14
    âĨIJ
    0.14
     Heritage
    0.14
    enville
    0.13
     Muk
    0.13
    ut
    0.13
     Chandler
    0.13
     I
    0.12
    �
    0.12
    Act Density 0.105%

    No Known Activations