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

    Neuronpedia

    INDEX
    Explanations

    elements that signal the start of a new section or topic in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.97
     Diſ
    -0.97
     pleaſure
    -0.96
     Monfieur
    -0.94
     ſta
    -0.94
     himſelf
    -0.92
     myſelf
    -0.91
     ſever
    -0.90
     themſelves
    -0.90
     Jefus
    -0.90
    POSITIVE LOGITS
     оригіналу
    0.65
    しつつ
    0.61
     of
    0.57
    IndentedString
    0.54
     autorytatywna
    0.53
    Билгалдахарш
    0.51
    live
    0.50
     cél
    0.48
     toward
    0.48
     auprès
    0.48
    Act Density 0.320%

    No Known Activations