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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts mentioned in textual content

    oai_token-act-pair · gpt-3.5-turbo

    numerical monetary values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihad
    -0.67
    ucle
    -0.63
    pan
    -0.62
    ibaba
    -0.62
    alties
    -0.62
    nette
    -0.61
    oha
    -0.61
    elly
    -0.61
    alyses
    -0.61
     luck
    -0.60
    POSITIVE LOGITS
    475
    0.84
    425
    0.84
    qqa
    0.80
    rous
    0.75
    DragonMagazine
    0.75
    370
    0.73
    inguished
    0.73
    470
    0.73
    480
    0.72
    375
    0.72
    Act Density 0.031%

    No Known Activations