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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sten
    -0.71
    ampa
    -0.67
    wart
    -0.67
    ieri
    -0.67
     puppet
    -0.66
     lear
    -0.65
     grievance
    -0.65
     impeachment
    -0.65
    hend
    -0.64
     trusted
    -0.64
    POSITIVE LOGITS
    isSpecialOrderable
    0.83
    CONCLUS
    0.73
    æĸ¹
    0.67
    ORY
    0.67
    ãĤ¯
    0.66
    RESULTS
    0.65
    Fra
    0.65
     Ethiop
    0.64
    soType
    0.63
    closure
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.