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

    Neuronpedia

    INDEX
    Explanations

    spam-related text and directives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unparalleled
    -0.72
    terday
    -0.67
    ãĥĥãĥĪ
    -0.66
     unprecedented
    -0.66
     remarkably
    -0.62
    ãĥĩãĤ£
    -0.60
    edom
    -0.58
    arthed
    -0.57
     remarkable
    -0.57
    albeit
    -0.57
    POSITIVE LOGITS
     anymore
    1.57
     nor
    1.26
     yourselves
    1.02
     unless
    0.97
     ;)
    0.96
     yourself
    0.96
     lest
    0.92
     unnecessarily
    0.91
     whatsoever
    0.91
     EVER
    0.90
    Act Density 0.611%

    No Known Activations