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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rences
    -0.77
    REDACTED
    -0.75
    abilia
    -0.75
    meier
    -0.73
    onymous
    -0.73
    ml
    -0.71
    ML
    -0.70
     largeDownload
    -0.70
    CD
    -0.70
    zsche
    -0.68
    POSITIVE LOGITS
    owed
    0.78
     Vive
    0.71
     fres
    0.69
     Dove
    0.61
     celebr
    0.60
     prophets
    0.60
     Veter
    0.60
     Universities
    0.59
     dro
    0.59
     Nurs
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.