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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     condem
    -0.73
     Liter
    -0.69
    misc
    -0.66
     Genie
    -0.66
    zeb
    -0.64
     Inquisition
    -0.63
    annie
    -0.61
    UX
    -0.61
    ETF
    -0.60
    Todd
    -0.60
    POSITIVE LOGITS
     while
    0.83
    while
    0.78
     respectively
    0.75
     concurrently
    0.72
    hetically
    0.70
     simultaneously
    0.69
    ¾
    0.69
    itles
    0.65
    everal
    0.62
    isively
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.