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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to structures, materials, and artistic or architectural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jaune
    -0.18
     Finished
    -0.16
     Completed
    -0.15
     finished
    -0.15
    Finished
    -0.14
    ãģĮãģĬ
    -0.14
    elman
    -0.13
    anos
    -0.13
    éł¼
    -0.13
    Filed
    -0.13
    POSITIVE LOGITS
     taken
    0.54
    taken
    0.49
    Taken
    0.43
     Taken
    0.41
     drawn
    0.40
     extracted
    0.35
    _taken
    0.32
     obtained
    0.32
    extract
    0.31
     picked
    0.29
    Act Density 0.549%

    No Known Activations