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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    i
    0.57
    da
    0.52
     Trailer
    0.52
    Background
    0.51
     the
    0.50
    De
    0.50
    f
    0.50
    Hob
    0.50
    ี
    0.49
    Conflict
    0.48
    POSITIVE LOGITS
    𝕝
    0.59
     témoign
    0.58
     حسين
    0.57
    vorsch
    0.57
    리티
    0.57
     epistle
    0.57
     nyní
    0.56
     ruhig
    0.55
     früheren
    0.55
     nových
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.