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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     difer
    -0.07
     Chance
    -0.07
    ừa
    -0.07
     Caption
    -0.07
     sms
    -0.07
     romance
    -0.06
    膽
    -0.06
    brahim
    -0.06
    -Pack
    -0.06
    \"]
    -0.06
    POSITIVE LOGITS
    jid
    0.06
    ATOM
    0.06
    跻
    0.06
    Changing
    0.06
    旮
    0.06
    带头人
    0.06
    🕉
    0.06
     regulators
    0.06
     upsetting
    0.06
    /co
    0.06
    Act Density 0.034%

    No Known Activations