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

    Neuronpedia

    INDEX
    Explanations

    mentions of internet protocol addresses and peak values in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vit
    -0.62
     tas
    -0.59
     déchir
    -0.59
    λέον
    -0.57
     détach
    -0.57
    OMET
    -0.56
     tirantes
    -0.55
     smtplib
    -0.55
    πάν
    -0.55
     aveug
    -0.54
    POSITIVE LOGITS
     متعلقه
    0.83
    مصادر
    0.63
     och
    0.62
     للمعارف
    0.61
    ไม้
    0.59
    phosa
    0.58
     OFDb
    0.56
    مراجع
    0.56
     Minaj
    0.55
     IP
    0.54
    Act Density 0.071%

    No Known Activations