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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ç»ıæŁ¥
    -0.28
     Took
    -0.27
    ets
    -0.27
    zos
    -0.26
    æijĨ
    -0.26
    eth
    -0.26
    others
    -0.25
     пÑĢедназ
    -0.25
    âĤĵ
    -0.25
     Others
    -0.24
    POSITIVE LOGITS
    å¿Ļ
    0.30
     her
    0.27
    æĬ½åĩº
    0.26
     races
    0.26
     integr
    0.25
     per
    0.25
    ogi
    0.24
    uman
    0.24
     BaseModel
    0.24
    isman
    0.23
    Act Density 0.006%

    No Known Activations

    This feature has no known activations.