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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and their associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.13
     themſelves
    -1.11
     pleaſure
    -1.11
     itſelf
    -1.09
    出版年
    -1.09
     Jefus
    -1.06
     Majefty
    -1.03
     raiſ
    -1.02
     laſt
    -0.99
     ſmall
    -0.99
    POSITIVE LOGITS
    ’
    0.55
     
    0.49
    '
    0.47
     https
    0.45
    <eos>
    0.44
     (
    0.44
     by
    0.44
    HasForeignKey
    0.44
     “
    0.43
    :
    0.43
    Act Density 0.210%

    No Known Activations