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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Sn
    -0.07
     stag
    -0.07
    _extraction
    -0.07
    樨
    -0.07
    antt
    -0.07
    二十年
    -0.07
     stret
    -0.07
    _need
    -0.06
     Golf
    -0.06
     unheard
    -0.06
    POSITIVE LOGITS
    .resolve
    0.07
     />↵
    0.07
    ');//
    0.07
     Davies
    0.07
     haciendo
    0.07
    ComputedStyle
    0.07
    内置
    0.07
    ))]↵
    0.07
    ')}}
    0.06
    먹
    0.06
    Act Density 0.003%

    No Known Activations