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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures related to quantities or proportions, particularly focusing on the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XK
    -0.87
     purpoſe
    -0.78
     Laplacian
    -0.77
     Majefty
    -0.73
     pleaſure
    -0.72
     Efq
    -0.72
     quæ
    -0.72
     fevere
    -0.69
     itſelf
    -0.69
     Labrador
    -0.68
    POSITIVE LOGITS
    OutOf
    1.26
     outta
    1.23
     INTO
    0.90
     Into
    0.86
     into
    0.83
     Dooley
    0.80
     the
    0.76
    Into
    0.74
     vanuit
    0.73
    THROUGH
    0.73
    Act Density 0.046%

    No Known Activations