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

    Neuronpedia

    INDEX
    Explanations

    document separators, specifically

    oai_token-act-pair · gpt-3.5-turbo

    instances of end-of-text markers or similar breaks in continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.55
     embargo
    -0.50
     established
    -0.50
     amnesty
    -0.49
     obligation
    -0.49
     displacement
    -0.49
     abandon
    -0.49
     initi
    -0.48
     interven
    -0.48
     rushes
    -0.48
    POSITIVE LOGITS
    Untitled
    1.11
    WASHINGTON
    1.08
    Abstract
    1.06
    Description
    1.03
    CLOSE
    1.03
    Overview
    0.99
    CTV
    0.96
    SAN
    0.96
    Welcome
    0.95
    CLE
    0.90
    Act Density 0.135%

    No Known Activations