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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sinner
    -0.69
    Mui
    -0.67
     GONNA
    -0.67
     calyx
    -0.64
     dictadura
    -0.64
     democracia
    -0.62
     Curran
    -0.61
     Oester
    -0.61
     rebels
    -0.60
     gereken
    -0.58
    POSITIVE LOGITS
     knowledge
    1.61
     Knowledge
    1.48
    knowledge
    1.47
    Knowledge
    1.43
     KNOWLEDGE
    1.20
     knowled
    1.17
    NOWLEDGE
    1.15
     conocimientos
    1.04
     kennis
    0.99
     connaissances
    0.94
    Act Density 0.064%

    No Known Activations