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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Frie
    -0.74
    £ı
    -0.72
    IRO
    -0.71
    lp
    -0.70
     urgently
    -0.67
    recent
    -0.64
    NPR
    -0.63
    ------
    -0.61
    GY
    -0.60
    EMA
    -0.60
    POSITIVE LOGITS
    apter
    0.71
    orus
    0.71
    etheus
    0.65
    ulet
    0.65
    hedon
    0.64
    azaki
    0.64
     Abedin
    0.63
     treason
    0.62
    isexual
    0.62
    roma
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.