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

    Neuronpedia

    INDEX
    Explanations

    information related to legal and medical incidents, involving actions, people, and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding denials and allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kindred
    -0.73
    Favorite
    -0.64
     millenn
    -0.62
     Millenn
    -0.61
    erenn
    -0.60
     ancest
    -0.60
    kefeller
    -0.59
     conquest
    -0.59
     decad
    -0.59
     niche
    -0.58
    POSITIVE LOGITS
     apologised
    0.82
     refund
    0.80
     reopened
    0.73
     apologise
    0.67
     retracted
    0.67
     reopen
    0.67
     reinstated
    0.66
     screenshots
    0.66
     confirmed
    0.66
     sacked
    0.64
    Act Density 1.303%

    No Known Activations