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

    Neuronpedia

    INDEX
    Explanations

    references to political events and actions related to foreign countries

    oai_token-act-pair · gpt-3.5-turbo

    topics related to politics and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.67
    aeper
    -0.65
     recip
    -0.64
     inconsist
    -0.61
    successfully
    -0.61
    maxwell
    -0.60
     contrace
    -0.58
    raq
    -0.57
     resil
    -0.56
     extensively
    -0.56
    POSITIVE LOGITS
     someday
    1.20
     looming
    1.08
     if
    1.05
     tomorrow
    0.99
     next
    0.95
     slated
    0.95
    morrow
    0.95
     forthcoming
    0.91
     unless
    0.90
     hereafter
    0.84
    Act Density 0.668%

    No Known Activations