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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .sem
    -0.08
    (socket
    -0.07
     أهم
    -0.07
    ϛ
    -0.07
     Thường
    -0.07
     Ко
    -0.07
    =request
    -0.07
    振り
    -0.07
    .req
    -0.07
     Advance
    -0.07
    POSITIVE LOGITS
     out
    0.11
     Out
    0.10
    out
    0.10
    ,out
    0.08
    outs
    0.08
     outpatient
    0.08
    .out
    0.08
    -out
    0.07
    וצ
    0.07
    _out
    0.07
    Act Density 0.189%

    No Known Activations