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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    «ĺ
    -0.85
    天
    -0.83
    ¥µ
    -0.82
    Ü
    -0.80
    »Ĵ
    -0.78
    Ń·
    -0.77
    \/\/
    -0.74
    thora
    -0.73
    htar
    -0.70
    Īè
    -0.69
    POSITIVE LOGITS
    illon
    0.74
     Ambro
    0.74
     Elliott
    0.66
     emb
    0.63
     Perez
    0.62
    ensor
    0.61
    dated
    0.61
     Cly
    0.61
    RP
    0.61
    Issue
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.