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

    Neuronpedia

    INDEX
    Explanations

    phrases related to damage and safety hazards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.54
     claimed
    -0.47
    Šaltiniai
    -0.45
    ufficient
    -0.45
     Shepherd
    -0.44
     Paseo
    -0.43
    RegistryLite
    -0.43
     tapa
    -0.42
     claim
    -0.42
    umeur
    -0.41
    POSITIVE LOGITS
    WebVitals
    0.86
     للمعارف
    0.80
    TargetException
    0.72
     typelib
    0.62
     désolés
    0.60
     if
    0.58
    存于互联网档案馆
    0.56
     bientôt
    0.55
     محفوظة
    0.54
     appartiennent
    0.54
    Act Density 0.433%

    No Known Activations