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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    emption
    -0.74
    acons
    -0.74
    onement
    -0.72
    intent
    -0.72
    pelled
    -0.70
    real
    -0.68
    bek
    -0.66
    cod
    -0.66
    Mars
    -0.65
    eded
    -0.64
    POSITIVE LOGITS
    ICA
    0.65
     spaghetti
    0.64
     insult
    0.62
    UFF
    0.62
     referen
    0.61
     shark
    0.60
    UTC
    0.59
     disaster
    0.58
     hemorrh
    0.58
     XD
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.