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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ots
    -0.08
    磋商
    -0.07
    eks
    -0.07
    uma
    -0.06
    孩童
    -0.06
    anto
    -0.06
    HCI
    -0.06
    ati
    -0.06
    ав
    -0.06
    ":[{"
    -0.06
    POSITIVE LOGITS
     basename
    0.08
    xAB
    0.08
    깍
    0.08
    锖
    0.07
    Projection
    0.07
    永遠
    0.07
     canc
    0.07
    #![
    0.07
    _workspace
    0.07
     ','.
    0.07
    Act Density 0.026%

    No Known Activations