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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observation and examination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.60
     gekomen
    -0.60
    anair
    -0.56
     NSCoder
    -0.56
     FontWeight
    -0.56
     democrática
    -0.54
     OkHttpClient
    -0.54
     AppBundle
    -0.52
     añadido
    -0.51
     oreilles
    -0.50
    POSITIVE LOGITS
     how
    0.90
     beautiful
    0.72
     scenes
    0.69
     firsthand
    0.67
     faces
    0.66
     cómo
    0.65
     progress
    0.65
     scene
    0.62
     bagaimana
    0.59
     smiling
    0.59
    Act Density 0.250%

    No Known Activations