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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.84
     >=",
    -0.84
     propOrder
    -0.83
     ddelweddau
    -0.81
     jScrollPane
    -0.80
    IContainer
    -0.78
     Efq
    -0.78
     kasarigan
    -0.78
    IndentedString
    -0.75
    Alike
    -0.75
    POSITIVE LOGITS
     sonra
    0.49
     kı
    0.43
     demek
    0.42
     peintures
    0.42
     malattie
    0.40
     liné
    0.40
     estric
    0.40
     dessins
    0.39
     astuces
    0.38
     espiral
    0.38
    Act Density 0.767%

    No Known Activations