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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fermionic
    0.60
     Disqus
    0.59
     idempot
    0.57
    🤨
    0.57
     spurious
    0.56
     globular
    0.56
     undet
    0.54
     filamentous
    0.53
     resampling
    0.52
     anisotropic
    0.52
    POSITIVE LOGITS
    7
    0.98
    SAFE
    0.87
    8
    0.86
    HELP
    0.84
    4
    0.81
    9
    0.80
    6
    0.79
     SAFE
    0.78
    CALL
    0.77
     HELP
    0.76
    Act Density 0.126%

    No Known Activations