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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mathemat
    -0.83
    milo
    -0.79
     obser
    -0.78
    conom
    -0.76
     clauses
    -0.75
    vre
    -0.75
     veter
    -0.75
    etheless
    -0.72
    VO
    -0.72
    agall
    -0.71
    POSITIVE LOGITS
     Hole
    0.76
     Cort
    0.72
     Sands
    0.71
     Nasa
    0.71
     Nirvana
    0.67
     Cir
    0.66
    Trend
    0.65
     Temp
    0.63
    omy
    0.63
     Nicole
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.