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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arthed
    -0.83
    choes
    -0.83
    antha
    -0.77
    GoldMagikarp
    -0.75
    ¥µ
    -0.72
    prus
    -0.72
    ©¶æ
    -0.72
    thumbnails
    -0.70
    kefeller
    -0.69
    artifacts
    -0.68
    POSITIVE LOGITS
    ,
    1.19
    .
    0.97
    ,...
    0.95
    ,-
    0.93
    ,.
    0.86
    ,[
    0.85
    .,
    0.83
    ;
    0.76
    !,
    0.74
    .(
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.