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

    Neuronpedia

    INDEX
    Explanations

    document or code structure elements, especially relating to programming syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    principalTable
    -0.82
    GEBURTSDATUM
    -0.72
    +#+#
    -0.72
     kasarigan
    -0.69
    ⓧ
    -0.69
    thâu
    -0.67
    rijfs
    -0.64
    Hozzáférés
    -0.64
     Мексичка
    -0.63
    MIDDLEWARE
    -0.60
    POSITIVE LOGITS
     الرياضيه
    0.66
    :
    0.47
    Tikang
    0.46
    ism
    0.44
    .:
    0.44
    ️
    0.43
    lankton
    0.43
     nawr
    0.43
     déput
    0.42
     GENERATED
    0.42
    Act Density 0.997%

    No Known Activations