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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Translation
    -0.73
    Els
    -0.68
    ãĥ¼ãĥĨ
    -0.67
    $.
    -0.66
    é¾įå
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    Ô
    -0.59
    +.
    -0.58
    ãĤ¯
    -0.56
    Sov
    -0.56
    POSITIVE LOGITS
     announced
    0.86
     reacted
    0.84
     celebrates
    0.76
     awoke
    0.75
     announces
    0.74
     unveiled
    0.74
     apologised
    0.73
     warned
    0.73
     expects
    0.72
     reportedly
    0.72
    Act Density 0.769%

    No Known Activations