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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the potential for improvement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ute
    -0.17
    avra
    -0.16
    orthy
    -0.15
     Tie
    -0.14
    å°ģ
    -0.14
     Hog
    -0.14
    nea
    -0.14
    ATCH
    -0.14
    igne
    -0.13
     kiss
    -0.13
    POSITIVE LOGITS
    ull
    0.15
     improvement
    0.15
    alus
    0.14
     èIJ¬
    0.14
    å¼ĺ
    0.14
    สำหร
    0.14
    áze
    0.14
     æ¥Ń
    0.14
    инг
    0.14
    ãĥŀãĥ³
    0.14
    Act Density 0.039%

    No Known Activations