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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dems
    -0.07
     resc
    -0.07
    tif
    -0.07
     district
    -0.07
    🌶
    -0.07
    -sector
    -0.06
    encrypted
    -0.06
    _STATE
    -0.06
    atisfaction
    -0.06
    ideal
    -0.06
    POSITIVE LOGITS
     Aleppo
    0.08
    ẓ
    0.07
    Enlarge
    0.07
    ,assign
    0.07
     маш
    0.07
    RETURN
    0.06
     outro
    0.06
     parsley
    0.06
    .numberOfLines
    0.06
    뤄
    0.06
    Act Density 0.002%

    No Known Activations