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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.96
     רבה
    -0.87
    Datuak
    -0.86
    TintMode
    -0.81
     nahilalakip
    -0.81
     contextLoads
    -0.81
    )";
    -0.80
     אשר
    -0.79
    EndContext
    -0.78
     Pristupljeno
    -0.77
    POSITIVE LOGITS
     everybody
    1.06
    Everybody
    1.00
     somebody
    0.94
     Everybody
    0.92
     people
    0.90
     stuff
    0.88
    Somebody
    0.84
    everybody
    0.83
     Somebody
    0.80
    Nobody
    0.75
    Act Density 2.845%

    No Known Activations