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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝒸
    -0.08
    皇后
    -0.07
     respons
    -0.07
    篷
    -0.07
     verg
    -0.07
     networks
    -0.07
     FK
    -0.07
    $msg
    -0.07
    .zoom
    -0.07
    רת
    -0.07
    POSITIVE LOGITS
     Buying
    0.07
     Trailer
    0.06
     Never
    0.06
    вой
    0.06
    _UPPER
    0.06
     Round
    0.06
    Decre
    0.06
    Never
    0.06
    ⛤
    0.06
    paid
    0.06
    Act Density 0.000%

    No Known Activations