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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     appropriated
    -0.08
     sustain
    -0.08
    melon
    -0.07
     baiser
    -0.07
     avalanche
    -0.07
    Pes
    -0.07
     Bearing
    -0.07
     Mine
    -0.07
    มา
    -0.07
     MIS
    -0.07
    POSITIVE LOGITS
    ]/
    0.06
     chuyện
    0.06
     tracks
    0.06
     Signing
    0.06
    私は
    0.06
    (elements
    0.06
     playing
    0.06
    yaml
    0.06
    .nl
    0.06
    🐫
    0.06
    Act Density 0.001%

    No Known Activations