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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ambigu
    -0.07
    овал
    -0.07
     Bowen
    -0.07
    athy
    -0.07
    HELL
    -0.07
     Sodium
    -0.07
    geo
    -0.06
    Flight
    -0.06
     Ali
    -0.06
    묀
    -0.06
    POSITIVE LOGITS
    .toggle
    0.07
    涨价
    0.07
     centers
    0.07
    =set
    0.06
    tuple
    0.06
    (collection
    0.06
     agg
    0.06
     oc
    0.06
    <tr
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations