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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest or curiosity about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asan
    -0.16
    hiba
    -0.16
    ÑĢÑİ
    -0.16
    rito
    -0.14
    ÑĢиÑĤ
    -0.14
    ilded
    -0.13
    кеÑĤ
    -0.13
     ØŃÙĪ
    -0.13
    fortunate
    -0.13
    orpion
    -0.13
    POSITIVE LOGITS
    ATALOG
    0.17
    iero
    0.16
    spark
    0.16
    reed
    0.15
     how
    0.15
     hol
    0.14
     fasc
    0.14
    wang
    0.14
     guar
    0.13
    .logical
    0.13
    Act Density 0.038%

    No Known Activations