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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.72
    -
    -0.69
     to
    -0.69
     al
    -0.64
     in
    -0.63
     for
    -0.61
     at
    -0.59
     (
    -0.59
    :
    -0.59
     is
    -0.57
    POSITIVE LOGITS
     myſelf
    1.38
     Jefus
    1.21
     Majefty
    1.20
     itſelf
    1.20
     Houſe
    1.19
     ſeveral
    1.17
     Reſ
    1.17
    ſelves
    1.17
    ſelf
    1.16
     themſelves
    1.16
    Act Density 0.009%

    No Known Activations