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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iris
    -0.75
    dL
    -0.74
     subtract
    -0.69
    WN
    -0.67
    tell
    -0.67
    inav
    -0.66
    ulz
    -0.65
    ymes
    -0.64
    arus
    -0.64
    rites
    -0.63
    POSITIVE LOGITS
    owship
    0.72
     widest
    0.70
     flares
    0.68
     holster
    0.66
     transport
    0.65
     grooming
    0.63
     ranch
    0.62
    soever
    0.62
     flared
    0.61
     fres
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.