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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nant
    -0.80
     istan
    -0.78
     sii
    -0.76
     tsi
    -0.74
     lele
    -0.73
     soggior
    -0.72
     cance
    -0.70
     fides
    -0.70
     kasa
    -0.70
     sena
    -0.70
    POSITIVE LOGITS
     which
    0.60
     whom
    0.56
     whose
    0.54
    which
    0.52
     Apesar
    0.51
    whom
    0.49
    Which
    0.47
    whose
    0.47
     whatever
    0.47
    PARTIC
    0.46
    Act Density 0.279%

    No Known Activations