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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anamo
    -0.80
     HRC
    -0.73
     HUD
    -0.70
    HUD
    -0.66
     contracting
    -0.63
     plasma
    -0.62
     conversions
    -0.61
     reception
    -0.60
     HHS
    -0.60
     absorption
    -0.60
    POSITIVE LOGITS
    bes
    0.82
    KT
    0.79
    peer
    0.78
    undo
    0.78
    orig
    0.77
    hement
    0.75
    wcsstore
    0.74
    overe
    0.73
    lisher
    0.71
    BIT
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.