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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ลล
    -0.16
     ########.
    -0.16
    ãģĹãĤĩ
    -0.15
    anja
    -0.14
     Incredible
    -0.14
     Computing
    -0.14
    ép
    -0.14
    öz
    -0.14
    ãn
    -0.13
    lia
    -0.13
    POSITIVE LOGITS
    æľĢè¿ij
    0.17
     prefer
    0.16
    pref
    0.15
     upbringing
    0.14
     gim
    0.14
     whenever
    0.14
     preference
    0.14
    eyen
    0.14
     Main
    0.14
     lately
    0.14
    Act Density 0.232%

    No Known Activations