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

    Neuronpedia

    INDEX
    Explanations

    conjunction phrases that indicate collaboration or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ",__
    -0.15
    hores
    -0.15
    herits
    -0.14
     ?><?
    -0.14
    flowers
    -0.14
     safeg
    -0.14
    periment
    -0.14
    inux
    -0.13
     ilgi
    -0.13
    à¥ĩप
    -0.13
    POSITIVE LOGITS
    /or
    0.29
    ific
    0.17
    acles
    0.17
    rog
    0.16
    ifice
    0.15
     íĺ¹
    0.15
     indeed
    0.15
    ators
    0.15
     other
    0.14
     allied
    0.14
    Act Density 0.271%

    No Known Activations