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

    Neuronpedia

    INDEX
    Explanations

    information related to health and public safety announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favored
    -0.17
     traveled
    -0.17
     behavior
    -0.17
    jem
    -0.15
    ault
    -0.15
    affer
    -0.15
     toward
    -0.15
    SKI
    -0.15
    ander
    -0.15
    oll
    -0.15
    POSITIVE LOGITS
    chemes
    0.17
    Remarks
    0.15
    ï¸
    0.15
    amba
    0.15
    AdapterFactory
    0.15
    оÑģÑĢед
    0.15
    γει
    0.15
     Seks
    0.15
    üml
    0.14
     statistics
    0.14
    Act Density 0.012%

    No Known Activations