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

    Neuronpedia

    INDEX
    Explanations

    unique proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.18
    égor
    -0.17
     flattering
    -0.17
    mpi
    -0.15
    ØŃت
    -0.15
    _REFERENCE
    -0.14
    goog
    -0.14
    idlo
    -0.14
    nit
    -0.14
    InBackground
    -0.14
    POSITIVE LOGITS
    efs
    0.15
    976
    0.15
    æĺĩ
    0.15
    Schedulers
    0.15
    ort
    0.15
     rem
    0.14
    anda
    0.14
     Sage
    0.14
    çī
    0.13
    íı°
    0.13
    Act Density 0.057%

    No Known Activations