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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .hasMore
    -0.08
    #ga
    -0.07
    _Return
    -0.07
    (ident
    -0.07
     Kad
    -0.07
    .Are
    -0.07
    DataProvider
    -0.07
     kob
    -0.07
     Tokens
    -0.07
    (ver
    -0.07
    POSITIVE LOGITS
    舟
    0.08
    alış
    0.07
    Prefab
    0.07
    angelo
    0.07
    alus
    0.06
    inspace
    0.06
    一只手
    0.06
    pole
    0.06
     intense
    0.06
    实例
    0.06
    Act Density 0.027%

    No Known Activations