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

    Neuronpedia

    INDEX
    Explanations

    words with non-ASCII characters, specifically focused on the character 'ä'

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols that include the letter "ä."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORED
    -0.92
     Sussex
    -0.72
     Jericho
    -0.66
     rooting
    -0.65
     Asians
    -0.65
     Bullets
    -0.64
     Mayweather
    -0.62
     cavity
    -0.59
     Notting
    -0.59
    IFIED
    -0.59
    POSITIVE LOGITS
    ä
    1.39
    inen
    1.21
    ternity
    1.03
    ¢
    1.02
    ·
    0.99
    ö
    0.98
    ë
    0.95
    ¯¯¯¯
    0.94
    0.92
    ¹
    0.90
    Act Density 0.009%

    No Known Activations