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

    Neuronpedia

    INDEX
    Explanations

    key phrases that suggest uncertainty or hidden complexities in topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oprot
    -0.61
     noires
    -0.60
    EndProject
    -0.59
    ViewFeatures
    -0.59
    onViewCreated
    -0.59
     actuelles
    -0.58
     actuels
    -0.58
     organisée
    -0.57
     ExecuteAsync
    -0.56
    Rhestr
    -0.56
    POSITIVE LOGITS
     surla
    0.62
     occasional
    0.62
     aquela
    0.61
     aquele
    0.55
     proverbial
    0.52
     longed
    0.52
     elusive
    0.50
     nagging
    0.50
    icky
    0.48
     big
    0.47
    Act Density 0.156%

    No Known Activations