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

    Neuronpedia

    INDEX
    Explanations

    references to blockades or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    827
    -0.17
    ikt
    -0.16
    zion
    -0.16
    ullan
    -0.16
    imli
    -0.15
    isin
    -0.15
    -0.15
    ffects
    -0.15
    fov
    -0.15
    onde
    -0.15
    POSITIVE LOGITS
    buster
    0.40
    busters
    0.38
    aded
    0.38
    ades
    0.35
    quote
    0.35
    age
    0.33
    ages
    0.29
    ading
    0.29
    chains
    0.29
    quotes
    0.27
    Act Density 0.020%

    No Known Activations