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

    Neuronpedia

    INDEX
    Explanations

    special characters (such as arrows) followed by letters in a continuous sequence

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters indicating emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     microphone
    -0.63
     minim
    -0.60
     GPS
    -0.60
    ozy
    -0.60
     trainers
    -0.60
     pastry
    -0.58
     microphones
    -0.58
     Ukrain
    -0.58
     shack
    -0.57
     horizont
    -0.57
    POSITIVE LOGITS
    £
    1.01
    ¡
    1.01
    Ĵ
    0.95
    ķ
    0.89
    ¢
    0.87
    ¤
    0.87
    IJ
    0.87
    ª
    0.86
    Ĭ
    0.86
    ı
    0.85
    Act Density 0.389%

    No Known Activations