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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rious
    -0.77
     bulk
    -0.72
    una
    -0.63
    Roaming
    -0.62
     burner
    -0.61
     clicked
    -0.61
     roaming
    -0.59
     cell
    -0.58
     lane
    -0.57
    usercontent
    -0.57
    POSITIVE LOGITS
    etheless
    0.90
     challeng
    0.80
     Constantin
    0.77
     skelet
    0.76
    forth
    0.74
    merce
    0.72
    ciation
    0.71
    iosyn
    0.69
    iann
    0.68
     Mub
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.