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

    Neuronpedia

    INDEX
    Explanations

    references to notorious historical figures involved in crime or outlaw activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xbf
    -0.17
    iment
    -0.16
     Mil
    -0.15
    inel
    -0.15
    Tube
    -0.14
    ameda
    -0.14
    ppo
    -0.14
    ément
    -0.14
    py
    -0.13
    tube
    -0.13
    POSITIVE LOGITS
    ierce
    0.16
     neutral
    0.16
     Neutral
    0.14
    ENTER
    0.14
    neutral
    0.14
     neutrality
    0.14
    ger
    0.14
    aira
    0.14
    eral
    0.14
     BOOLEAN
    0.13
    Act Density 0.187%

    No Known Activations