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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     longing
    0.70
    ers
    0.67
    胝
    0.65
    iness
    0.63
    Back
    0.63
    ih
    0.63
    Pine
    0.62
     feelings
    0.61
    のない
    0.60
    r
    0.60
    POSITIVE LOGITS
     Në
    1.00
    gé
    0.97
     XXX
    0.94
     Рим
    0.91
    henderit
    0.91
    GG
    0.91
    fts
    0.89
     세율
    0.89
    GX
    0.87
    GV
    0.87
    Act Density 0.000%

    No Known Activations