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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.52
     many
    0.48
     H
    0.48
    T
    0.47
    S
    0.45
     name
    0.45
     T
    0.43
     A
    0.42
    bit
    0.41
     unge
    0.41
    POSITIVE LOGITS
     mechanisms
    1.09
     strategies
    1.08
    <unused1837>
    1.02
    <unused1969>
    0.99
     techniques
    0.99
    <unused1833>
    0.99
    <unused2097>
    0.99
    <unused1653>
    0.98
    <unused1196>
    0.98
    <unused1055>
    0.98
    Act Density 5.246%

    No Known Activations