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

    Neuronpedia

    INDEX
    Explanations

    references to specific historical years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific historical years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.77
    igi
    -0.68
    ony
    -0.67
     Corker
    -0.66
    FILE
    -0.65
    FH
    -0.62
     McN
    -0.61
     Donovan
    -0.61
    arr
    -0.60
    çĶŁ
    -0.60
    POSITIVE LOGITS
     1800
    2.84
     1700
    2.64
     1300
    2.56
     1600
    2.54
     1400
    2.49
     1500
    2.49
     1200
    2.41
     2400
    2.34
     2100
    2.33
     1100
    2.28
    Act Density 0.028%

    No Known Activations