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

    Neuronpedia

    INDEX
    Explanations

    websites or sources for further information or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a request for additional information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conn
    -0.82
    sonian
    -0.80
    igr
    -0.75
    ÃŃs
    -0.75
    iltr
    -0.73
    rn
    -0.72
    ãĥĺ
    -0.72
    `
    -0.70
    asse
    -0.70
    pour
    -0.69
    POSITIVE LOGITS
     details
    1.31
     directions
    1.06
     answers
    1.04
     instructions
    1.00
     specifics
    1.00
     info
    1.00
     clarification
    0.98
     detailed
    0.98
     updates
    0.97
     more
    0.94
    Act Density 0.104%

    No Known Activations