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

    Neuronpedia

    INDEX
    Explanations

    occurrences of whitespace or spacing in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ={<
    -0.71
    ंदीखरीदारी
    -0.70
     gynhyrchwyd
    -0.67
    Planes
    -0.65
     Seif
    -0.65
     Silas
    -0.62
    畿
    -0.62
    acağı
    -0.61
    fore
    -0.60
    んでも
    -0.60
    POSITIVE LOGITS
    hspace
    1.58
     GenerationType
    0.91
    جستارهای
    0.88
     переписи
    0.72
     Spra
    0.67
     Kars
    0.67
     getAge
    0.67
     Auvergne
    0.66
     PUSTAKA
    0.65
     Pries
    0.65
    Act Density 0.003%

    No Known Activations