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

    Neuronpedia

    INDEX
    Explanations

    email subjects

    oai_token-act-pair · gpt-3.5-turbo

    subjects and headers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jagu
    -0.84
    amaz
    -0.80
     relegation
    -0.78
    REG
    -0.77
     Blaz
    -0.73
     Mortal
    -0.72
     Earthqu
    -0.70
    itans
    -0.70
     Eclipse
    -0.67
     Regener
    -0.66
    POSITIVE LOGITS
     aides
    1.29
     briefings
    1.23
     aide
    1.17
     memos
    1.17
     briefed
    1.14
     advisers
    1.12
    CLASSIFIED
    1.09
     confid
    1.09
     secretaries
    1.02
     Emails
    1.00
    Act Density 0.408%

    No Known Activations