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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Const
    0.42
    CONST
    0.39
     longo
    0.38
    охра
    0.38
    irani
    0.38
    oléon
    0.38
    嵬
    0.38
    )$\\
    0.37
     orphaned
    0.37
    iram
    0.37
    POSITIVE LOGITS
     YouTube
    0.44
     videot
    0.43
     On
    0.42
     Vimeo
    0.42
    同年
    0.41
     Youtube
    0.40
     www
    0.40
     TikTok
    0.40
     video
    0.39
     Linkedin
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.