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

    Neuronpedia

    INDEX
    Explanations

    information related to public criticism or controversial actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -0.69
     vexed
    -0.52
     indescri
    -0.51
    Bibliographie
    -0.50
     Warszawie
    -0.49
     viszont
    -0.49
     phénomènes
    -0.49
     impelled
    -0.47
     Normdatei
    -0.47
     Wirklichkeit
    -0.46
    POSITIVE LOGITS
     utop
    1.06
     incess
    1.01
     majest
    0.94
     sappi
    0.93
     priva
    0.88
     palet
    0.88
     ordina
    0.88
     monaster
    0.85
     beren
    0.83
     solidar
    0.82
    Act Density 0.253%

    No Known Activations