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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ield
    -0.76
    arent
    -0.72
     Sabha
    -0.71
     Verd
    -0.68
     Bundy
    -0.67
     Zup
    -0.67
    xtap
    -0.66
    ortium
    -0.65
    RIP
    -0.64
     sidx
    -0.64
    POSITIVE LOGITS
    fits
    0.77
     sweating
    0.74
    fit
    0.72
    fitting
    0.71
     healed
    0.70
    wolves
    0.67
     seen
    0.66
     disinfect
    0.65
     born
    0.65
     decomp
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.