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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Knight
    -0.08
     Ecuador
    -0.07
     Event
    -0.07
     Ronald
    -0.07
     adaptive
    -0.07
     waterfall
    -0.07
    _domain
    -0.07
     airline
    -0.07
     sworn
    -0.07
    顶级
    -0.07
    POSITIVE LOGITS
    isa
    0.08
    我在
    0.07
    蓄
    0.06
     bless
    0.06
     מבוס
    0.06
     "{
    0.06
    YM
    0.06
    js
    0.06
     saw
    0.06
     Jess
    0.06
    Act Density 0.001%

    No Known Activations