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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    köz
    -0.52
     villaggio
    -0.52
    2
    -0.50
     just
    -0.50
     käytt
    -0.50
     something
    -0.48
     åt
    -0.47
    —
    -0.47
     vaiz
    -0.47
     qualcosa
    -0.46
    POSITIVE LOGITS
    (',',
    1.03
    (",",
    0.97
    ,:),
    0.97
    ,",
    0.92
     :,
    0.92
    ,-,
    0.91
    .$,
    0.89
    !("{}",
    0.88
    ,',
    0.87
     (_,
    0.87
    Act Density 0.788%

    No Known Activations