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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pneum
    -0.77
     ordinance
    -0.74
    senal
    -0.73
     aspir
    -0.73
     Vie
    -0.71
     insanity
    -0.69
     ordinances
    -0.69
     unsus
    -0.68
     revol
    -0.66
     Episcopal
    -0.66
    POSITIVE LOGITS
    #$
    1.24
    realDonaldTrump
    1.10
    wik
    1.03
    facebook
    0.98
    link
    0.91
    twitter
    0.90
    login
    0.90
    deck
    0.87
    username
    0.87
    sung
    0.87
    Act Density 0.023%

    No Known Activations