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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mortal
    -0.75
     unlucky
    -0.70
     foul
    -0.66
     killer
    -0.65
     filthy
    -0.64
     submission
    -0.64
     strike
    -0.63
     coworkers
    -0.62
     unmanned
    -0.62
     hob
    -0.62
    POSITIVE LOGITS
    ĸļ
    1.11
    arov
    0.78
    borough
    0.76
    Ban
    0.73
    toc
    0.72
    OUP
    0.70
    ONT
    0.70
    Pin
    0.70
    Allows
    0.69
    aret
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.