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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     голове
    0.62
     demoral
    0.57
     да
    0.56
     restrained
    0.55
     discouraged
    0.55
     состояния
    0.55
     pledged
    0.54
    y
    0.53
     thwarted
    0.53
    ină
    0.51
    POSITIVE LOGITS
    osp
    0.51
    номи
    0.50
    0.49
    ور
    0.48
    רו
    0.48
    पुरम
    0.47
     croissant
    0.47
    夥
    0.46
    Original
    0.46
    篷
    0.46
    Act Density 0.000%

    No Known Activations