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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or contribution to a work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycastle
    -0.15
    itur
    -0.15
    unge
    -0.15
    太éĥİ
    -0.15
    ÐĤ
    -0.14
    asion
    -0.14
    ÏĥÏĩ
    -0.14
    à¥Ĥह
    -0.14
    cak
    -0.14
     Scho
    -0.14
    POSITIVE LOGITS
    udo
    0.16
     hol
    0.15
    ÑĢиг
    0.15
    rier
    0.15
    nie
    0.14
     lid
    0.14
    جÛĮ
    0.14
    af
    0.14
    -command
    0.14
     Brook
    0.14
    Act Density 0.192%

    No Known Activations