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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific event or show called "Meet"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Meet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.86
    secut
    -0.75
     ende
    -0.74
    vernment
    -0.72
    etheless
    -0.71
     tiss
    -0.68
    secution
    -0.67
    cul
    -0.64
    ¥ŀ
    -0.64
     membranes
    -0.63
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.99
    ings
    0.98
    ups
    0.85
    amorph
    0.85
    INGS
    0.79
    icles
    0.77
    ropolis
    0.76
    up
    0.75
     Meet
    0.75
    Meet
    0.74
    Act Density 0.025%

    No Known Activations