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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.60
    tagHelperRunner
    -0.57
     ainfi
    -0.55
     ſche
    -0.54
     houſe
    -0.54
     <>",
    -0.53
     OFDb
    -0.52
     pleaſure
    -0.47
     chofe
    -0.46
     éter
    -0.45
    POSITIVE LOGITS
     able
    1.06
     very
    0.73
     quite
    0.73
     unable
    0.70
     extremely
    0.70
     a
    0.66
    حوالہ
    0.65
     considered
    0.64
     aware
    0.63
     willing
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.