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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Reps
    -0.78
    clusive
    -0.75
    illery
    -0.72
     Russians
    -0.71
     Tatt
    -0.70
     vodka
    -0.67
     Pom
    -0.66
     Tap
    -0.65
     Uzbek
    -0.63
     Moj
    -0.63
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.78
    Interstitial
    0.75
    ÃĥÃĤ
    0.74
     exting
    0.73
    imar
    0.72
    ãĤ¨ãĥ«
    0.70
    stros
    0.69
     tremend
    0.69
    vertisement
    0.69
     occas
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.