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

    Neuronpedia

    INDEX
    Explanations

    numerical values tagged with a specific unit symbol

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, particularly those related to monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.84
    yang
    -0.80
    eering
    -0.76
    ezvous
    -0.75
    endum
    -0.71
    gments
    -0.71
    hran
    -0.70
    orate
    -0.69
    ongyang
    -0.69
    chard
    -0.68
    POSITIVE LOGITS
     ILCS
    1.35
    75
    0.99
    475
    0.89
    80
    0.87
    655
    0.86
    8000
    0.85
    875
    0.85
    680
    0.85
    ength
    0.84
    00000
    0.84
    Act Density 0.025%

    No Known Activations