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

    Neuronpedia

    INDEX
    Explanations

    food items, especially those related to poutine

    oai_token-act-pair · gpt-3.5-turbo

    references to routines and group activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aad
    -0.70
     straw
    -0.65
     dark
    -0.63
     almonds
    -0.61
     saddle
    -0.60
     rainy
    -0.59
    uers
    -0.59
     swipe
    -0.58
    anth
    -0.58
     runaway
    -0.57
    POSITIVE LOGITS
    outine
    0.99
    achu
    0.91
    zynski
    0.78
    SPONSORED
    0.75
    liness
    0.75
    DragonMagazine
    0.74
    hood
    0.74
    ball
    0.72
    vous
    0.71
    enegger
    0.71
    Act Density 0.012%

    No Known Activations