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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.84
    士
    -0.73
     Luffy
    -0.73
     contrace
    -0.72
    geist
    -0.72
    tumblr
    -0.70
    berus
    -0.67
    978
    -0.66
    AGES
    -0.65
     vulner
    -0.64
    POSITIVE LOGITS
     overall
    0.70
     entire
    0.69
     latter
    0.68
    rule
    0.64
    itives
    0.64
     entirety
    0.64
    production
    0.64
    tan
    0.62
     usual
    0.62
     staggered
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.