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

    Neuronpedia

    INDEX
    Explanations

    words related to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GONNA
    -0.68
     sinner
    -0.66
     gonna
    -0.63
     blest
    -0.63
     Appellants
    -0.62
    arrows
    -0.60
     rehabilitate
    -0.59
     democracia
    -0.59
    guson
    -0.58
     Larsson
    -0.58
    POSITIVE LOGITS
     knowledge
    2.60
    knowledge
    2.36
     Knowledge
    2.31
    Knowledge
    2.22
     KNOWLEDGE
    1.96
     knowled
    1.77
    NOWLEDGE
    1.58
     conocimientos
    1.53
     connaissances
    1.52
     conocimiento
    1.50
    Act Density 0.065%

    No Known Activations