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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _MethodInfo
    -0.08
     kişi
    -0.07
    らず
    -0.07
    forget
    -0.07
     información
    -0.07
     %+
    -0.07
    Beer
    -0.07
    �
    -0.07
     sonst
    -0.06
    Direct
    -0.06
    POSITIVE LOGITS
    런
    0.07
    PARAM
    0.06
     Lia
    0.06
     AA
    0.06
    标注
    0.06
    }`}↵
    0.06
     ";↵
    0.06
    ⍋
    0.06
    拦
    0.06
    stackpath
    0.06
    Act Density 0.112%

    No Known Activations