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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and issues related to political accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oras
    -0.16
    оÑĢоÑĤ
    -0.15
    ReuseIdentifier
    -0.15
    æ£
    -0.15
    .Suppress
    -0.15
    isor
    -0.14
    cter
    -0.14
    å«
    -0.14
    رد
    -0.14
    leaflet
    -0.14
    POSITIVE LOGITS
     Clinton
    0.29
     State
    0.28
     Benghazi
    0.26
     Hillary
    0.26
    Clinton
    0.25
     Abed
    0.23
    State
    0.23
    Hillary
    0.21
     emails
    0.20
     Secretary
    0.19
    Act Density 0.025%

    No Known Activations