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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    agos
    -0.82
    Daddy
    -0.72
     scissors
    -0.70
    interstitial
    -0.67
     itch
    -0.66
    okin
    -0.63
     verbally
    -0.63
     ridden
    -0.63
    ober
    -0.63
    kid
    -0.62
    POSITIVE LOGITS
    missions
    0.71
    onductor
    0.69
     conclud
    0.67
    Sov
    0.65
     LIM
    0.64
     Background
    0.64
     ãĤµ
    0.63
    vale
    0.61
     Forensic
    0.61
     guarantees
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.