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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ihe
    1.67
    र्गत
    1.64
     abate
    1.62
    ぜひ
    1.62
     podido
    1.61
    וריה
    1.56
    screenshots
    1.56
     trypsin
    1.55
     पति
    1.53
    𝕞
    1.51
    POSITIVE LOGITS
    isChecked
    1.79
    1.59
     ktor
    1.55
    \}=
    1.54
    gm
    1.54
    د
    1.53
    ogia
    1.52
    \}=\
    1.49
    ها
    1.48
     intake
    1.48
    Act Density 0.001%

    No Known Activations