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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    1.28
     niew
    1.19
    etti
    1.18
     то
    1.18
    溢
    1.15
    iksaan
    1.09
     lapisan
    1.09
     nur
    1.09
     ся
    1.09
    endaten
    1.08
    POSITIVE LOGITS
    in
    1.42
    ры
    1.23
    _{-}\
    1.19
     alternately
    1.18
    aying
    1.18
    نا
    1.12
    𝒆
    1.09
    _{+}\
    1.09
     Callie
    1.08
    وە
    1.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.