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

    Neuronpedia

    INDEX
    Explanations

    numerical figures with an emphasis on the number 75 followed by another number

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, particularly monetary amounts or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.86
    ezvous
    -0.81
    eering
    -0.79
    */(
    -0.74
    endum
    -0.74
    evin
    -0.73
    gments
    -0.72
    yang
    -0.70
    ynchronous
    -0.70
    ynthesis
    -0.70
    POSITIVE LOGITS
     ILCS
    1.34
    75
    0.98
    475
    0.90
    8000
    0.89
    875
    0.85
    425
    0.84
    ength
    0.83
    225
    0.83
    %:
    0.82
    655
    0.82
    Act Density 0.027%

    No Known Activations