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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    an
    2.27
    is
    2.07
    as
    1.91
    el
    1.89
    ان
    1.75
    ated
    1.74
     pran
    1.71
    al
    1.70
     relato
    1.69
    ary
    1.66
    POSITIVE LOGITS
    tension
    1.91
    cough
    1.87
    𝒾
    1.74
    CCNC
    1.72
    <unused43>
    1.72
    𝙸
    1.70
     angustato
    1.63
    equilibrium
    1.61
     CFRP
    1.60
     aandacht
    1.60
    Act Density 0.000%

    No Known Activations