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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly the number 60 followed by another number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific frame rate in video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atto
    -0.66
    âĢİ
    -0.66
    ãĥ
    -0.65
    NetMessage
    -0.64
    arians
    -0.63
    dain
    -0.63
    âĿ
    -0.61
    auer
    -0.61
    itive
    -0.61
    forge
    -0.60
    POSITIVE LOGITS
     60
    3.00
     70
    2.22
     90
    2.08
     80
    2.05
     61
    2.03
     120
    2.01
     50
    2.00
     55
    2.00
     62
    1.98
     65
    1.98
    Act Density 0.035%

    No Known Activations