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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝚐
    1.28
     compelling
    1.27
     gratifying
    1.26
     contemplated
    1.26
     tailored
    1.25
    𝚎
    1.24
     disregard
    1.22
    🄰
    1.20
     submersible
    1.20
    𝚖
    1.19
    POSITIVE LOGITS
    en
    1.28
    ds
    1.27
    س
    1.26
    RA
    1.17
    hört
    1.16
    TI
    1.13
    maps
    1.13
    aik
    1.12
    वानी
    1.10
    sz
    1.08
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.