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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal or regulatory compliance and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     qu
    -0.24
     Qu
    -0.19
    quin
    -0.16
    Qu
    -0.16
    (qu
    -0.15
    -qu
    -0.15
    /qu
    -0.15
    qu
    -0.15
    _qu
    -0.14
    metro
    -0.14
    POSITIVE LOGITS
     that
    0.39
    -that
    0.36
     dat
    0.35
     tha
    0.34
     hat
    0.34
     tat
    0.34
    "That
    0.32
    hat
    0.32
    “That
    0.31
     th
    0.29
    Act Density 0.071%

    No Known Activations