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

    Neuronpedia

    INDEX
    Explanations

    specific regulations and changes to rules or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upgraded
    -0.16
    è½®
    -0.14
    ipers
    -0.14
     Projection
    -0.14
     weather
    -0.13
    )prepare
    -0.13
    ulp
    -0.13
    Shutdown
    -0.13
    лиÑĩ
    -0.13
    obil
    -0.13
    POSITIVE LOGITS
     changes
    0.37
     change
    0.32
     Changes
    0.30
    changes
    0.28
    Changes
    0.27
    å¤īæĽ´
    0.27
    change
    0.26
    Change
    0.25
     Change
    0.25
    _change
    0.24
    Act Density 0.384%

    No Known Activations