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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or preparations

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.49
     Hurricanes
    -0.45
    natureconservancy
    -0.40
    EStreamFrame
    -0.40
     Seym
    -0.38
    wcs
    -0.38
     Corpor
    -0.37
     Byrd
    -0.37
     cryst
    -0.37
     Surveillance
    -0.37
    POSITIVE LOGITS
    gers
    0.51
    able
    0.51
    ings
    0.49
    backs
    0.48
    ingly
    0.48
    ables
    0.45
    books
    0.44
    ers
    0.44
    ="#
    0.43
    abl
    0.43
    Act Density 1.418%

    No Known Activations