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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics related to sociopolitical topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -0.85
     gaily
    -0.79
     exasper
    -0.77
     disagre
    -0.77
     tolerably
    -0.76
     vainly
    -0.76
     shenan
    -0.72
     intersper
    -0.72
     nobly
    -0.71
     indescri
    -0.70
    POSITIVE LOGITS
     utop
    0.81
     gymnas
    0.75
     attes
    0.70
     spion
    0.70
     ideolog
    0.69
     BIBSYS
    0.69
     soggior
    0.68
     bronz
    0.68
     Wikisource
    0.68
     solidar
    0.67
    Act Density 0.041%

    No Known Activations