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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month/year (MM/YYYY)

    oai_token-act-pair · gpt-3.5-turbo

    references to the events of September 11, 2001, particularly in relation to discussions and investigations surrounding the attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reneg
    -0.72
     obst
    -0.69
     distinguishing
    -0.67
     Opportun
    -0.67
     blush
    -0.67
     privile
    -0.66
     repro
    -0.64
     blot
    -0.63
     sul
    -0.63
     carrot
    -0.63
    POSITIVE LOGITS
    11
    1.33
    ROR
    1.06
    2001
    1.02
    1.01
    911
    0.99
    ¹
    0.90
    ISIS
    0.90
    ·
    0.89
    9
    0.88
    12
    0.88
    Act Density 0.020%

    No Known Activations