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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or similar patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģи
    -0.17
    گاب
    -0.16
    ewidth
    -0.15
     Folk
    -0.15
    eko
    -0.14
    æĪ¸
    -0.14
    ohan
    -0.14
    iani
    -0.14
    eus
    -0.14
     Herz
    -0.14
    POSITIVE LOGITS
    www
    0.25
    III
    0.24
    ffffff
    0.23
    inn
    0.22
    ieee
    0.22
    iii
    0.22
     iii
    0.22
    CCCCCC
    0.21
    II
    0.21
    err
    0.21
    Act Density 0.022%

    No Known Activations