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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pong
    -0.07
    urgeon
    -0.07
    ÃŁ
    -0.06
     Verg
    -0.06
    ãĥ³ãĥī
    -0.06
    ิà¹ī
    -0.06
    odd
    -0.06
    ấ
    -0.06
     comfort
    -0.06
     Trend
    -0.06
    POSITIVE LOGITS
    ouver
    0.08
    iaux
    0.08
    bbe
    0.07
    شتÙĩ
    0.07
    AAD
    0.07
    scan
    0.07
     totally
    0.07
     humans
    0.06
    ilib
    0.06
    omp
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.