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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by "@"

    oai_token-act-pair · gpt-3.5-turbo

    Twitter handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pneum
    -0.76
     ordinance
    -0.71
     Malk
    -0.70
     Vie
    -0.69
     elect
    -0.68
    senal
    -0.68
     conversions
    -0.68
     aspir
    -0.67
     defic
    -0.67
     Sakuya
    -0.66
    POSITIVE LOGITS
    #$
    1.39
    realDonaldTrump
    1.07
    wik
    0.91
     "@
    0.90
    @@@@@@@@
    0.89
    home
    0.88
    cn
    0.86
    Home
    0.84
    YouTube
    0.83
    aic
    0.82
    Act Density 0.014%

    No Known Activations