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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Palest
    -0.71
     Blasio
    -0.68
     Streets
    -0.66
    Effective
    -0.65
     Borders
    -0.65
    phant
    -0.64
    address
    -0.64
     Drawn
    -0.64
     Spectrum
    -0.62
     Instr
    -0.61
    POSITIVE LOGITS
    ikan
    0.75
    keyes
    0.72
    mith
    0.71
    ogue
    0.71
     biod
    0.70
    acca
    0.65
    hare
    0.65
    iqueness
    0.64
     masse
    0.64
     depress
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.