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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data privacy and user information handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lick
    -0.15
    imator
    -0.14
    elop
    -0.14
    омен
    -0.13
    rage
    -0.13
    Ľi
    -0.13
     Lair
    -0.13
    .rad
    -0.13
    chine
    -0.13
    ignite
    -0.13
    POSITIVE LOGITS
     store
    0.30
     collect
    0.27
     process
    0.26
     Process
    0.25
    store
    0.23
     collects
    0.23
    collect
    0.22
     stores
    0.22
     disclose
    0.22
    process
    0.21
    Act Density 0.051%

    No Known Activations