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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to design and appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UniformLocation
    -0.62
     noDo
    -0.61
     jdbcTemplate
    -0.61
    GEBURTSDATUM
    -0.60
     colitis
    -0.60
    StandardCharsets
    -0.57
     Jimi
    -0.57
     Yunnan
    -0.56
     patches
    -0.56
     Theſe
    -0.55
    POSITIVE LOGITS
     shape
    1.24
     Shape
    1.05
     shapes
    1.03
     SHAPE
    1.02
    shape
    1.02
     silhouette
    0.94
    shapes
    0.91
    hape
    0.90
     silueta
    0.89
    Shape
    0.88
    Act Density 0.382%

    No Known Activations