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

    Neuronpedia

    INDEX
    Explanations

    references to emotional impact and character dynamics in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.00
     ſever
    -1.00
     Majefty
    -0.99
     purpoſe
    -0.98
    ſelves
    -0.96
     Anſ
    -0.94
     itſelf
    -0.94
     Monfieur
    -0.92
     Jefus
    -0.91
     Reſ
    -0.91
    POSITIVE LOGITS
     n
    0.51
     p
    0.48
     k
    0.45
    ↵↵
    0.45
     in
    0.45
    ModelAttribute
    0.43
     
    0.43
    .
    0.43
    0.42
     u
    0.42
    Act Density 0.383%
    No Known Activations