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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ahime
    -0.71
    Reply
    -0.71
     minded
    -0.70
    riors
    -0.66
     oppos
    -0.66
    mma
    -0.65
    20439
    -0.62
    NAS
    -0.61
    nai
    -0.61
     actionGroup
    -0.61
    POSITIVE LOGITS
     Dart
    0.72
    agon
    0.70
     Gaz
    0.69
     Fritz
    0.69
     Johannes
    0.67
     BuzzFeed
    0.67
     Fargo
    0.66
     Franken
    0.65
    tale
    0.65
     Bark
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.