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

    Neuronpedia

    INDEX
    Explanations

    phrases and sentences that imply knowledge or awareness of illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ur
    -0.15
    igg
    -0.15
    etten
    -0.14
    ants
    -0.14
    ummer
    -0.14
    frames
    -0.14
    issant
    -0.14
    ฤษ
    -0.13
     Tender
    -0.13
    osten
    -0.13
    POSITIVE LOGITS
    μά
    0.15
    eyh
    0.15
    omba
    0.14
    üb
    0.14
    GUID
    0.14
    brane
    0.14
    ($('<
    0.14
    #ab
    0.14
    sage
    0.14
    brands
    0.13
    Act Density 0.122%

    No Known Activations