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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ban
    -0.73
    âĿ
    -0.63
    Fla
    -0.62
    Ko
    -0.60
    ivo
    -0.60
    liam
    -0.60
    iazep
    -0.59
     [&
    -0.59
     Cary
    -0.59
    mega
    -0.58
    POSITIVE LOGITS
    unda
    0.67
    laugh
    0.67
    eping
    0.63
    pour
    0.63
    cipled
    0.61
    pired
    0.60
     Dealer
    0.60
    gered
    0.60
     Abedin
    0.60
    ueless
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.