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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    юр
    -0.07
     ha
    -0.07
     disgusting
    -0.07
     trag
    -0.07
    oul
    -0.07
     Today
    -0.06
    ☚
    -0.06
    bben
    -0.06
    esus
    -0.06
    啐
    -0.06
    POSITIVE LOGITS
    ILITY
    0.08
    Ջ
    0.08
    成份
    0.07
     Installation
    0.07
     ties
    0.07
    鹰
    0.07
    झ
    0.06
     Mud
    0.06
    𫘜
    0.06
    投资基金
    0.06
    Act Density 0.001%

    No Known Activations