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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     consumes
    0.89
    ሖ
    0.85
     spitting
    0.83
    ്
    0.82
    PTMR
    0.81
     yě
    0.81
    ิจ
    0.80
     publishes
    0.80
     ashore
    0.80
     decommission
    0.80
    POSITIVE LOGITS
    name
    0.82
    ce
    0.76
    та
    0.75
     привод
    0.73
    sl
    0.72
    0.71
     b
    0.70
    ul
    0.69
    pdf
    0.68
    course
    0.68
    Act Density 0.000%

    No Known Activations