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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical conflicts and targeted violence against specific communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏįÏĢ
    -0.15
    imuth
    -0.15
    153
    -0.14
    475
    -0.13
    ying
    -0.13
     anonymity
    -0.13
     åİŁ
    -0.13
    rych
    -0.13
    .codes
    -0.13
    åİŁ
    -0.13
    POSITIVE LOGITS
    Mgr
    0.16
    Ãłi
    0.14
    uD
    0.14
    ãĥĵãĥ¼
    0.14
    abbit
    0.14
    (od
    0.14
    cdb
    0.14
    ยะ
    0.14
    rescia
    0.13
     Twist
    0.13
    Act Density 0.172%

    No Known Activations