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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dil
    -0.08
    <Menu
    -0.07
     Borders
    -0.07
     Bordeaux
    -0.07
     Manning
    -0.07
     }}"↵
    -0.07
    午
    -0.07
    bij
    -0.07
     Cocktail
    -0.07
     Mitar
    -0.07
    POSITIVE LOGITS
    和技术
    0.07
    (hw
    0.07
    _sess
    0.07
     prog
    0.07
    ￥
    0.07
    /image
    0.06
    긔
    0.06
    动机
    0.06
    تقليد
    0.06
     specs
    0.06
    Act Density 0.000%

    No Known Activations