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

    Neuronpedia

    INDEX
    Explanations

    unicode character representations for accented letters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <strong>
    -0.70
    5
    -0.67
    2
    -0.64
    6
    -0.63
    0
    -0.62
     похо
    -0.62
    7
    -0.62
    ule
    -0.61
    9
    -0.60
    al
    -0.60
    POSITIVE LOGITS
     Erdoğan
    1.00
    Portail
    0.97
    hitheatre
    0.95
     doughnuts
    0.94
    Rüyada
    0.94
    0.93
    })`
    0.93
     Nestlé
    0.92
    ]='\
    0.92
     Bogotá
    0.92
    Act Density 0.681%

    No Known Activations