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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCartney
    -0.16
    ebek
    -0.15
     forg
    -0.15
    ffen
    -0.15
    ij
    -0.14
    auc
    -0.14
    cona
    -0.14
    ²
    -0.14
    \Plugin
    -0.14
    bbing
    -0.14
    POSITIVE LOGITS
    yal
    0.15
    Hor
    0.15
    ates
    0.14
    ads
    0.14
    èį
    0.14
     Hor
    0.14
    ADS
    0.14
    olini
    0.14
    \<^
    0.14
    å±Ģ
    0.13
    Act Density 0.072%

    No Known Activations