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

    Neuronpedia

    INDEX
    Explanations

    phrases with mentions of news organizations and publications

    oai_token-act-pair · gpt-3.5-turbo

    instances of newspaper names and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.68
     cav
    -0.64
    achev
    -0.63
     Sparkle
    -0.62
    gger
    -0.60
     reclaimed
    -0.60
     swoop
    -0.60
    idious
    -0.60
    amiya
    -0.60
     bonding
    -0.59
    POSITIVE LOGITS
    Dispatch
    1.13
    Times
    1.01
    Union
    0.97
    Standard
    0.96
    Merc
    0.93
    News
    0.91
    Doctors
    0.90
     Gazette
    0.90
    Mail
    0.89
    Bul
    0.89
    Act Density 0.051%

    No Known Activations