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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating personal beliefs or opinions on governmental matters

    oai_token-act-pair · gpt-3.5-turbo

    statements related to opinions on what the government ought to do

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ZI
    -0.71
     Fra
    -0.67
    atile
    -0.66
     ROS
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
     Puzzle
    -0.64
    reality
    -0.64
     Saiyan
    -0.63
    locked
    -0.63
    GGGGGGGG
    -0.61
    POSITIVE LOGITS
    ered
    1.11
     be
    1.00
    ering
    0.89
    ©¶æ
    0.83
    nt
    0.83
     ideally
    0.81
     beware
    0.81
    bes
    0.79
    ĪĴ
    0.78
     aspire
    0.77
    Act Density 0.066%

    No Known Activations