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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     smokes
    -0.67
    lag
    -0.65
    Hung
    -0.65
    Gun
    -0.65
     MFT
    -0.64
    Nev
    -0.64
     ORDER
    -0.62
     warr
    -0.61
    MAN
    -0.60
     Gun
    -0.59
    POSITIVE LOGITS
    utation
    0.77
    eca
    0.75
    atten
    0.72
     unfocusedRange
    0.71
    ikawa
    0.70
    asking
    0.66
    patch
    0.64
     reuse
    0.63
    ixture
    0.63
    posium
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.