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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oled
    -0.07
     summers
    -0.07
     cues
    -0.07
     kol
    -0.07
     coz
    -0.07
     dereg
    -0.07
     chunks
    -0.07
     supplement
    -0.07
    扃
    -0.06
    ystone
    -0.06
    POSITIVE LOGITS
     ACT
    0.07
    实验室
    0.07
    Calls
    0.07
     Quân
    0.06
    위
    0.06
     agents
    0.06
    企业家
    0.06
    我家
    0.06
    สะสม
    0.06
     הפ
    0.06
    Act Density 0.093%

    No Known Activations