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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĢij
    -0.17
    ãĥ³ãĥij
    -0.15
    rim
    -0.15
    arra
    -0.14
    qing
    -0.14
    asio
    -0.14
    à¥Įà¤ķ
    -0.14
    ng
    -0.14
    mq
    -0.14
    ar
    -0.14
    POSITIVE LOGITS
    arehouse
    0.19
    icker
    0.19
    aver
    0.18
    igt
    0.18
    evil
    0.18
    ilder
    0.17
    idle
    0.17
    inst
    0.16
    issen
    0.16
    ALTH
    0.16
    Act Density 0.054%

    No Known Activations