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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <unused1209>
    1.21
    <unused602>
    1.21
    fqsen
    1.19
    <unused932>
    1.18
    <unused971>
    1.18
    <unused1835>
    1.18
    <unused1194>
    1.17
    <unused989>
    1.16
    <unused1837>
    1.16
    <unused1075>
    1.16
    POSITIVE LOGITS
     B
    0.82
    B
    0.78
     T
    0.76
     US
    0.75
     H
    0.74
     deux
    0.74
     mencionado
    0.73
     para
    0.73
     tiga
    0.72
     quatro
    0.71
    Act Density 0.000%

    No Known Activations