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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methods and findings in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.15
     itſelf
    -1.11
     myſelf
    -1.05
     ſeveral
    -1.02
     ſtate
    -1.01
     Majefty
    -1.01
     fubject
    -1.01
     pleaſure
    -1.01
     Efq
    -0.99
     Reſ
    -0.99
    POSITIVE LOGITS
     the
    1.03
     
    0.76
     a
    0.74
     The
    0.68
     an
    0.63
     Par
    0.59
    ↵↵
    0.59
    :
    0.59
     (
    0.58
    ,
    0.55
    Act Density 0.613%

    No Known Activations