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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.73
    livious
    -0.70
    hesda
    -0.64
     accommodation
    -0.64
    ware
    -0.63
    arget
    -0.63
    arten
    -0.63
    Ford
    -0.61
    Attempts
    -0.60
    ttp
    -0.60
    POSITIVE LOGITS
    okin
    0.75
     Vaugh
    0.73
    ipel
    0.69
    iaries
    0.69
    ercise
    0.68
    depending
    0.66
    OVA
    0.65
     vary
    0.65
    Rated
    0.64
    quart
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.