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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cell" followed by numbers from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to cell phones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.78
    merce
    -0.78
     Logged
    -0.74
    laus
    -0.72
    urities
    -0.71
    gettable
    -0.70
    ebin
    -0.69
    ãĥ¤
    -0.68
     Lumpur
    -0.67
    lift
    -0.67
    POSITIVE LOGITS
     cell
    1.19
    phones
    1.08
     cells
    1.05
     Cell
    1.02
    Cell
    1.00
    cell
    0.94
    cells
    0.94
    icides
    0.92
     Cells
    0.88
    estial
    0.85
    Act Density 0.011%

    No Known Activations