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

    Neuronpedia

    INDEX
    Explanations

    descriptions of people, particularly focusing on actions they are involved in

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or individuals involved in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.70
    Bound
    -0.68
    cially
    -0.68
    atever
    -0.62
     Madness
    -0.61
     Bound
    -0.59
     Dome
    -0.59
     Domain
    -0.59
    igslist
    -0.58
    this
    -0.58
    POSITIVE LOGITS
    folk
    0.85
    '
    0.75
     were
    0.73
     parted
    0.72
    ']
    0.72
     wore
    0.71
     proceeded
    0.71
     resorted
    0.70
     complied
    0.69
     laughed
    0.69
    Act Density 0.238%

    No Known Activations