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

    Neuronpedia

    INDEX
    Explanations

    mentions of advice and opinions from various sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express advice and opinions from authoritative sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.83
    ĸļ
    -0.79
    surprisingly
    -0.72
    ãĤ¨ãĥ«
    -0.71
    RPG
    -0.69
    edit
    -0.69
    é¾
    -0.66
     âĨij
    -0.63
    isu
    -0.63
     Tsu
    -0.63
    POSITIVE LOGITS
     bipartisan
    1.13
     [
    1.12
     Congressman
    1.09
    Secretary
    1.07
    elected
    1.04
     Senator
    1.01
     âĢ¦"
    1.00
     ..."
    1.00
     Republican
    0.98
     democr
    0.97
    Act Density 1.040%

    No Known Activations