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

    Neuronpedia

    INDEX
    Explanations

    references to control groups and experimental controls in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.90
     الرياضيه
    -0.79
     متعلقه
    -0.75
    ValueStyle
    -0.75
    XmlAccessorType
    -0.74
    XmlAccessType
    -0.74
    FormTagHelper
    -0.68
    BufferException
    -0.68
    Personensuche
    -0.67
     насељу
    -0.65
    POSITIVE LOGITS
     blank
    0.61
    OrWhiteSpace
    0.55
     Nada
    0.55
    Nada
    0.51
     silence
    0.51
     plain
    0.49
    zeros
    0.49
     kawaida
    0.48
     untreated
    0.48
     Blank
    0.47
    Act Density 1.013%

    No Known Activations