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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wana
    -0.78
    ecast
    -0.76
    elaide
    -0.72
    league
    -0.70
    bery
    -0.69
    ventus
    -0.67
    artifacts
    -0.67
    inance
    -0.66
     livest
    -0.65
    orno
    -0.65
    POSITIVE LOGITS
    kson
    0.68
    spin
    0.67
     tune
    0.63
    ãĤ¼
    0.63
    -$
    0.63
    Laughs
    0.63
    felt
    0.61
    meier
    0.61
     hinges
    0.61
    kell
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.