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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     jerseys
    -0.07
    们都
    -0.07
    郗
    -0.07
     whispers
    -0.07
     jade
    -0.07
    _bind
    -0.06
    Donald
    -0.06
    loud
    -0.06
    fetch
    -0.06
    于是
    -0.06
    POSITIVE LOGITS
    Political
    0.08
    风光
    0.07
     проблем
    0.07
    -po
    0.07
    𝘽
    0.07
    datap
    0.07
    心态
    0.07
    ctime
    0.06
    zeigen
    0.06
     Beste
    0.06
    Act Density 0.009%

    No Known Activations