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

    Neuronpedia

    INDEX
    Explanations

    characters from a foreign language script

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols often used in digital or coded text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jericho
    -0.75
     panel
    -0.71
     Iron
    -0.71
     Ib
    -0.69
     Rum
    -0.69
     Ant
    -0.68
     demos
    -0.67
     Irving
    -0.67
     Bailey
    -0.67
     faction
    -0.66
    POSITIVE LOGITS
    à¤
    4.19
    à¥
    3.64
    ा
    3.47
     à¤
    2.98
    à¨
    1.97
    à¦
    1.94
    à©
    1.79
    à
    1.76
    Ü
    1.76
    Ö
    1.67
    Act Density 0.003%

    No Known Activations