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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seminars
    -0.76
     PUBLIC
    -0.72
     Vanity
    -0.66
     doctrines
    -0.65
    eatures
    -0.64
    detail
    -0.64
    enegger
    -0.63
    irez
    -0.63
    terms
    -0.62
    anooga
    -0.60
    POSITIVE LOGITS
     Gamer
    0.72
    IED
    0.72
    cker
    0.67
     Grimm
    0.67
     Proceed
    0.67
    alian
    0.62
    agh
    0.62
    ysc
    0.61
     Alchemist
    0.60
    akable
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.