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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stalls
    -0.69
    incial
    -0.66
    ateurs
    -0.64
     ACTIONS
    -0.62
     IDE
    -0.62
    Roaming
    -0.62
    ãĤ¨ãĥ«
    -0.62
     NEXT
    -0.62
    âĶĢâĶĢ
    -0.62
    Disclaimer
    -0.61
    POSITIVE LOGITS
    isner
    1.11
    wright
    1.08
    ullivan
    1.06
    ickson
    1.04
    nyder
    1.03
    atson
    1.00
    iggins
    0.98
    endez
    0.98
    chuk
    0.97
    ixon
    0.97
    Act Density 0.271%

    No Known Activations