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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or phrases indicating pauses or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.57
     X
    -0.56
    ,
    -0.56
     Q
    -0.54
     Z
    -0.51
     U
    -0.51
    ;
    -0.50
     Smart
    -0.49
     J
    -0.49
     S
    -0.49
    POSITIVE LOGITS
     الرياضيه
    0.90
     itſelf
    0.88
    TagMode
    0.87
    Hochspringen
    0.82
     EconPapers
    0.82
    IsMutable
    0.81
    CloseOperation
    0.80
     theſe
    0.78
     мәкал
    0.78
    Geplaatst
    0.77
    Act Density 0.155%

    No Known Activations