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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.72
    rification
    -0.72
    atives
    -0.66
    âĢİ
    -0.66
     è£ıè¦ļéĨĴ
    -0.65
    College
    -0.65
     projecting
    -0.64
     recess
    -0.63
     Recover
    -0.61
    ãĥ¤
    -0.61
    POSITIVE LOGITS
     mu
    0.75
    ano
    0.67
     Zhou
    0.65
    tained
    0.65
    iren
    0.63
    pled
    0.61
    tains
    0.61
     bottleneck
    0.60
    uses
    0.59
     Blumenthal
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.