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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cial
    -0.92
    merce
    -0.78
    Interstitial
    -0.75
    interstitial
    -0.73
    swick
    -0.73
    cially
    -0.72
    nw
    -0.72
    LV
    -0.70
    nell
    -0.69
     Genius
    -0.67
    POSITIVE LOGITS
     cutoff
    0.72
     veto
    0.72
     coerc
    0.72
     stakes
    0.70
     membership
    0.69
     prosec
    0.68
     rul
    0.68
    anamo
    0.65
     backing
    0.65
     steering
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.