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

    Neuronpedia

    INDEX
    Explanations

    references to violent crimes and acts of aggression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ars
    -0.18
    imas
    -0.16
    ai
    -0.16
    esters
    -0.15
    anders
    -0.15
    å¾
    -0.14
    pos
    -0.14
    èįĴ
    -0.14
    atter
    -0.14
    cmp
    -0.13
    POSITIVE LOGITS
     fellow
    0.18
    imore
    0.16
    NavItem
    0.15
    rowsing
    0.15
     Tome
    0.14
     wart
    0.14
    iveness
    0.14
    oran
    0.14
    awe
    0.14
     part
    0.14
    Act Density 0.094%

    No Known Activations