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

    Neuronpedia

    INDEX
    Explanations

    words related to imperatives with a condition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "re"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.79
    pedia
    -0.72
     Exit
    -0.69
    egu
    -0.66
    ð
    -0.66
     SetTextColor
    -0.66
     rests
    -0.65
     Reef
    -0.64
    clerosis
    -0.64
     Trends
    -0.64
    POSITIVE LOGITS
     unsure
    1.13
     willing
    1.02
     bothered
    0.98
     gonna
    0.95
     lucky
    0.94
     interested
    0.94
     unlucky
    0.91
     inclined
    0.91
     dissatisfied
    0.90
     kidding
    0.90
    Act Density 0.033%

    No Known Activations