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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .DataAccess
    -0.15
    bil
    -0.15
    inctions
    -0.14
    بÙĦ
    -0.14
     Ki
    -0.14
    deaux
    -0.14
    etail
    -0.13
    èm
    -0.13
    nings
    -0.13
    igkeit
    -0.13
    POSITIVE LOGITS
    452
    0.17
     xanh
    0.14
     crunch
    0.14
    MLE
    0.14
    COPE
    0.14
    tains
    0.13
    κει
    0.13
     prest
    0.13
    ucher
    0.13
    plist
    0.13
    Act Density 0.267%

    No Known Activations