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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with a specific symbol followed by a combination of letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    a specific character that appears repeatedly in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.72
     hors
    -0.64
     RIS
    -0.63
     pastry
    -0.62
     fortun
    -0.61
     trainers
    -0.60
     shack
    -0.59
    ozy
    -0.58
     Seym
    -0.58
     Palest
    -0.57
    POSITIVE LOGITS
    ¢
    0.98
    ¡
    0.97
    ¤
    0.93
    £
    0.89
    ª
    0.89
    ħ
    0.88
    Ļ
    0.87
    Ĭ
    0.86
    ı
    0.83
    ķ
    0.83
    Act Density 0.409%

    No Known Activations