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

    Neuronpedia

    INDEX
    Explanations

    information related to statistics and studies

    oai_token-act-pair · gpt-3.5-turbo

    data and statistics related to health and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.65
    Newsletter
    -0.64
     "_
    -0.62
     mentioned
    -0.62
    efer
    -0.61
    76561
    -0.61
    iations
    -0.59
    ose
    -0.59
     lambda
    -0.58
    iary
    -0.58
    POSITIVE LOGITS
    WASHINGTON
    0.80
     watchdog
    0.77
     bombshell
    0.74
     whistleblower
    0.65
    PROV
    0.64
     constitu
    0.64
    CLUS
    0.63
     damning
    0.63
    FOX
    0.63
    Legendary
    0.63
    Act Density 0.259%

    No Known Activations