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

    Neuronpedia

    INDEX
    Explanations

    links in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drops
    -0.18
    ead
    -0.18
    uze
    -0.17
    agini
    -0.16
    bedo
    -0.15
    akat
    -0.14
    ews
    -0.13
     पà¤ķ
    -0.13
    berries
    -0.13
    çĹ
    -0.13
    POSITIVE LOGITS
    енÑĤи
    0.15
    0.15
    inal
    0.14
     Soci
    0.14
    sink
    0.14
    age
    0.14
    rib
    0.14
    yles
    0.14
    AGE
    0.14
    pered
    0.14
    Act Density 0.010%

    No Known Activations