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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Capitalized first letters after periods

    np_acts-logits-general · gemini-2.0-flash

    author initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بيها
    -0.94
     مشين
    -0.92
     doubtnut
    -0.89
     pleaſure
    -0.88
     Partagez
    -0.87
    extAlignment
    -0.81
     ―――――
    -0.81
     متعلقه
    -0.80
     ſtre
    -0.80
     purpoſe
    -0.79
    POSITIVE LOGITS
     S
    0.74
     J
    0.73
     B
    0.72
     M
    0.71
     L
    0.68
     V
    0.67
     Y
    0.66
     G
    0.66
     N
    0.65
     D
    0.65
    Act Density 0.150%

    No Known Activations