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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completion or high achievement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating effort or striving, especially in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omnia
    -0.70
    aturday
    -0.69
    rompt
    -0.62
    apsed
    -0.62
     IMAGES
    -0.62
    href
    -0.61
    DERR
    -0.61
    irl
    -0.60
    nant
    -0.60
    duration
    -0.60
    POSITIVE LOGITS
     ducks
    0.84
     bricks
    0.81
     proverbial
    0.78
     pies
    0.78
     cake
    0.77
     hay
    0.77
     punches
    0.77
     rope
    0.75
     carrots
    0.74
     paddle
    0.74
    Act Density 0.619%

    No Known Activations