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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <unused285>
    1.32
    <unused464>
    1.29
    ১০
    1.27
    ১৮
    1.27
    <unused1151>
    1.25
    <unused1633>
    1.24
    ১৯
    1.24
    <unused1661>
    1.24
    <unused1879>
    1.21
    Forty
    1.20
    POSITIVE LOGITS
    ,
    1.02
     (
    0.97
    ↵↵
    0.94
    ↵
    0.81
     nada
    0.77
     aus
    0.75
    0.74
     (“
    0.72
    .
    0.68
     no
    0.67
    Act Density 0.013%

    No Known Activations