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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hands-on activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating hands-on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pell
    -0.64
     Jacket
    -0.62
     Coat
    -0.62
     Cruiser
    -0.61
     Shepherd
    -0.60
     circumstance
    -0.60
     Carth
    -0.58
     disturbance
    -0.58
     Ascension
    -0.58
     Shelter
    -0.58
    POSITIVE LOGITS
    everal
    1.36
    sembly
    1.24
    ettings
    1.13
    hell
    1.06
    peed
    1.04
    hift
    0.99
    ource
    0.99
    Downloadha
    0.98
    hire
    0.98
    hot
    0.97
    Act Density 0.066%

    No Known Activations