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

    Neuronpedia

    INDEX
    Explanations

    references to historical writings and their authors, highlighting themes of freedom and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.99
     
    -0.98
     "
    -0.96
     T
    -0.93
     L
    -0.90
    e
    -0.90
     P
    -0.89
     p
    -0.88
    '
    -0.88
     A
    -0.87
    POSITIVE LOGITS
     myſelf
    2.22
     itſelf
    2.14
     himſelf
    2.02
     ainfi
    2.02
     themſelves
    1.97
     againſt
    1.93
     Jefus
    1.90
     whoſe
    1.90
     Majefty
    1.88
     ſeveral
    1.88
    Act Density 8.310%

    No Known Activations