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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate problems or issues with technology or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.52
    Personendaten
    -0.49
     aikaa
    -0.48
     autorytatywna
    -0.47
     stanovnika
    -0.47
     Numerade
    -0.47
     مشين
    -0.46
    RegistryLite
    -0.46
    ďaka
    -0.45
    Tembelea
    -0.45
    POSITIVE LOGITS
     exasper
    0.43
     madd
    0.42
     infuriating
    0.42
     weird
    0.41
    TextAppearance
    0.41
     wierd
    0.40
     annoying
    0.39
    weird
    0.38
    perfectly
    0.38
     sickening
    0.38
    Act Density 0.335%

    No Known Activations