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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions or realizations and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.89
     myſelf
    -0.79
     Majefty
    -0.77
     iſt
    -0.77
     pleaſure
    -0.75
     ainfi
    -0.74
     purpoſe
    -0.73
     whoſe
    -0.72
     itſelf
    -0.72
     defaultstate
    -0.72
    POSITIVE LOGITS
     dawned
    0.52
     hit
    0.50
     soudain
    0.49
    EnableWeb
    0.46
    withIdentifier
    0.43
     Bon
    0.42
    aarrggbb
    0.42
     realise
    0.41
     madre
    0.40
     true
    0.40
    Act Density 0.184%

    No Known Activations