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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical structures or objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "deck" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.85
    heric
    -0.78
    eworld
    -0.71
     plur
    -0.71
    phrine
    -0.70
    ternity
    -0.68
    ipient
    -0.68
     tremend
    -0.67
     IMAGES
    -0.66
    bians
    -0.65
    POSITIVE LOGITS
    lists
    1.13
    yard
    1.09
    wright
    1.08
    igans
    0.95
    deck
    0.95
    tower
    0.92
    list
    0.92
     deck
    0.91
    ed
    0.91
    hands
    0.90
    Act Density 0.013%

    No Known Activations