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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges or dialogue between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laden
    -0.17
    ãĥ»ãĥ»ãĥ»↵↵
    -0.14
     æĬķ稿
    -0.14
    ersist
    -0.14
    HeaderCode
    -0.14
    ÙĬراÙĨ
    -0.14
    ibrary
    -0.14
    Ur
    -0.14
    imar
    -0.14
    Vtbl
    -0.13
    POSITIVE LOGITS
    0.18
     -
    0.17
     queer
    0.17
     Flood
    0.15
     ’
    0.15
    rate
    0.15
     backing
    0.15
     Emb
    0.15
    æķ
    0.14
     jap
    0.14
    Act Density 0.013%

    No Known Activations