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

    Neuronpedia

    INDEX
    Explanations

    unusual symbols or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upal
    -0.17
    isas
    -0.15
    алом
    -0.15
    -License
    -0.15
    PRS
    -0.14
    oran
    -0.14
    'gc
    -0.14
    ãĥ¼ãĥĭ
    -0.14
    eland
    -0.14
    ständ
    -0.14
    POSITIVE LOGITS
    lay
    0.17
     root
    0.16
     Lay
    0.15
     ball
    0.15
     exposed
    0.15
     hard
    0.15
     Desk
    0.15
    .descriptor
    0.15
     Parties
    0.15
     people
    0.15
    Act Density 0.006%

    No Known Activations