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

    Neuronpedia

    INDEX
    Explanations

    mentions of knowledge and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GONNA
    -0.75
     gonna
    -0.64
     Tuf
    -0.62
     Appellants
    -0.62
     blest
    -0.61
    foglal
    -0.59
    guson
    -0.58
     sinner
    -0.57
     defy
    -0.57
     sitcom
    -0.57
    POSITIVE LOGITS
     knowledge
    3.50
    knowledge
    3.10
     Knowledge
    3.04
    Knowledge
    2.94
     KNOWLEDGE
    2.63
     knowled
    2.11
     conocimiento
    2.08
     conocimientos
    1.97
     conhecimento
    1.94
     connaissances
    1.91
    Act Density 0.038%

    No Known Activations