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

    Neuronpedia

    INDEX
    Explanations

    words related to improvement and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to motivation and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reply
    -0.66
     mysteriously
    -0.65
    aired
    -0.64
    ORY
    -0.62
    uttered
    -0.61
    unknown
    -0.61
    ndra
    -0.61
    oshenko
    -0.61
    ATURE
    -0.60
     inexpl
    -0.60
    POSITIVE LOGITS
     ourselves
    2.02
     our
    1.50
     them
    1.04
     myself
    1.02
     ours
    1.01
     everybody
    1.00
     OUR
    0.91
    Our
    0.91
     accordingly
    0.88
     everything
    0.84
    Act Density 0.505%

    No Known Activations