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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts in various currencies

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated numerical values, particularly those related to loss or financial estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rein
    -0.75
     Cros
    -0.73
     ART
    -0.73
     Unch
    -0.65
     behav
    -0.65
     RH
    -0.64
     hots
    -0.63
     Bram
    -0.63
     CJ
    -0.62
     Orb
    -0.61
    POSITIVE LOGITS
    000
    1.76
    500
    1.24
    00
    1.23
    0000
    1.15
    001
    1.13
    200
    1.09
    600
    1.06
    0002
    1.06
    300
    1.06
    1000
    1.05
    Act Density 0.059%

    No Known Activations