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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '){
    -0.56
    "){
    -0.54
     D
    -0.54
     De
    -0.52
     pat
    -0.50
    verwijspagina
    -0.50
     venuto
    -0.48
     lasciato
    -0.48
    an
    -0.48
    D
    -0.48
    POSITIVE LOGITS
     itſelf
    1.10
     themſelves
    0.97
     pleaſure
    0.95
     Monfieur
    0.93
     Jefus
    0.93
     himſelf
    0.93
     Anſ
    0.92
     Majefty
    0.92
     poffe
    0.91
     iſt
    0.91
    Act Density 1.206%

    No Known Activations