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

    Neuronpedia

    INDEX
    Explanations

    numbers related to political polls and election results

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rology
    -0.81
    OOL
    -0.71
    ctors
    -0.68
    gee
    -0.68
    ework
    -0.67
    details
    -0.67
    lict
    -0.66
    oidal
    -0.66
    arus
    -0.65
    ufact
    -0.64
    POSITIVE LOGITS
     apiece
    1.01
     margin
    0.79
     difference
    0.72
     (-
    0.72
     increments
    0.69
     (~
    0.69
     (+
    0.68
     elevation
    0.67
     separating
    0.65
     mark
    0.64
    Act Density 0.018%

    No Known Activations