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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy and the sharing of personal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olver
    -0.15
    elter
    -0.14
    ìĬ¤íħĮ
    -0.14
    rrha
    -0.14
    ignite
    -0.14
    olor
    -0.14
    омен
    -0.14
    -ли
    -0.14
    èħ¹
    -0.14
    chine
    -0.14
    POSITIVE LOGITS
     store
    0.23
     process
    0.20
     collect
    0.20
    collect
    0.19
    store
    0.19
     Process
    0.19
     proces
    0.19
     collects
    0.19
     disclose
    0.19
     pseud
    0.19
    Act Density 0.038%

    No Known Activations