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

    Neuronpedia

    INDEX
    Explanations

    references to events and actions related to protests and strikes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    865
    -0.18
    æģ¯
    -0.17
    èĭ¥
    -0.15
    коÑĤ
    -0.14
    ика
    -0.14
    éĤ¦
    -0.14
     Dept
    -0.14
    913
    -0.14
    getic
    -0.14
    é
    -0.13
    POSITIVE LOGITS
     Al
    0.19
     Jazeera
    0.19
     al
    0.17
     Rin
    0.16
    ofil
    0.15
    CG
    0.14
    ymb
    0.14
    eldom
    0.14
    rix
    0.14
    umas
    0.14
    Act Density 0.008%

    No Known Activations