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

    Neuronpedia

    INDEX
    Explanations

    dates related to specific events in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates, particularly in July and August

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.70
    corn
    -0.66
     cumbers
    -0.64
     unnecess
    -0.63
     ancest
    -0.62
     calibr
    -0.61
    fect
    -0.60
     withd
    -0.58
    hyde
    -0.58
     regress
    -0.58
    POSITIVE LOGITS
     31
    1.24
     29
    1.08
     28
    1.03
     26
    1.02
    iano
    1.01
     27
    1.01
     23
    0.99
     Fourth
    0.98
     22
    0.97
     24
    0.96
    Act Density 0.051%

    No Known Activations