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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lihood
    -0.94
     Phi
    -0.76
     Coch
    -0.70
     Strategy
    -0.68
     Spiel
    -0.67
     Sark
    -0.67
     Cond
    -0.67
    atorium
    -0.67
     McCann
    -0.66
    ormal
    -0.64
    POSITIVE LOGITS
    Ire
    0.71
    ackle
    0.69
    rupted
    0.69
    200000
    0.69
    Disable
    0.68
    toggle
    0.66
    rival
    0.66
    cles
    0.65
    umen
    0.65
    paralle
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.