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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     According
    0.88
     Panels
    0.82
     Чи
    0.82
     Perks
    0.79
     Matches
    0.78
     Послед
    0.78
    الغ
    0.74
    率は
    0.73
     alej
    0.73
     الغ
    0.73
    POSITIVE LOGITS
    ie
    0.72
    __
    0.71
     nigh
    0.68
    ৃতা
    0.67
    p
    0.67
    ach
    0.67
    ed
    0.65
    xb
    0.65
    ts
    0.64
     pathology
    0.64
    Act Density 0.003%

    No Known Activations