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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    [],
    -0.08
    💞
    -0.07
    _$_
    -0.07
    Placeholder
    -0.07
    .timing
    -0.07
    .preference
    -0.07
    ﳎ
    -0.06
    ,uint
    -0.06
    骛
    -0.06
    精力
    -0.06
    POSITIVE LOGITS
     zonder
    0.07
     outf
    0.07
    gua
    0.07
     piel
    0.07
     Unt
    0.07
     Painter
    0.07
    董
    0.06
    _deposit
    0.06
     tàn
    0.06
     Plain
    0.06
    Act Density 0.053%

    No Known Activations