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

    Neuronpedia

    INDEX
    Explanations

    repeated words or phrases that imply instructions or actions to follow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stevenson
    -0.18
     CLICK
    -0.18
     click
    -0.15
     Click
    -0.15
    uttle
    -0.15
     clicks
    -0.14
    click
    -0.14
    ç·Ĵ
    -0.14
    Click
    -0.14
    -push
    -0.14
    POSITIVE LOGITS
     learn
    0.24
     view
    0.22
    raquo
    0.21
     see
    0.20
    learn
    0.20
    Learn
    0.17
    :view
    0.17
     access
    0.17
     learns
    0.17
    view
    0.16
    Act Density 0.047%

    No Known Activations