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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code related to programming frameworks and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.81
      
    -0.74
     in
    -0.74
     "
    -0.66
     and
    -0.64
     […]
    -0.64
     /
    -0.60
     int
    -0.60
     of
    -0.60
     on
    -0.59
    POSITIVE LOGITS
     myſelf
    1.67
     pleaſure
    1.60
    ſelf
    1.56
     Anſ
    1.53
     purpoſe
    1.51
     ſeveral
    1.50
     Reſ
    1.50
     itſelf
    1.49
     Monfieur
    1.46
     Majefty
    1.46
    Act Density 7.422%

    No Known Activations