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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual and various protocol versions in technology discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    i
    -0.88
    o
    -0.85
    т
    -0.75
     Georg
    -0.75
    a
    -0.75
    Georg
    -0.74
     Zer
    -0.68
    кра
    -0.67
    ست
    -0.65
    jel
    -0.65
    POSITIVE LOGITS
     становника
    0.96
     pido
    0.96
     CreateTagHelper
    0.94
    postolic
    0.93
    StructEnd
    0.91
     Tubes
    0.90
    lemény
    0.90
     tubes
    0.89
     chariots
    0.89
     Amos
    0.88
    Act Density 0.291%

    No Known Activations