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

    Neuronpedia

    INDEX
    Explanations

    aspects relating to mathematical notation or expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Cord
    -0.87
     POS
    -0.85
    มาณ
    -0.83
    Zimmer
    -0.81
    ので
    -0.81
    tiel
    -0.79
     samar
    -0.79
     kob
    -0.78
     KENN
    -0.78
    obos
    -0.77
    POSITIVE LOGITS
    ,\
    1.14
    },\
    0.82
    Portail
    0.81
     Whi
    0.80
    ',\
    0.80
    ),\
    0.79
     Portail
    0.77
    .\
    0.76
    Whi
    0.76
     للمعارف
    0.73
    Act Density 0.148%

    No Known Activations