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

    Neuronpedia

    INDEX
    Explanations

    references to social media and internet culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bulk
    -0.16
    lý
    -0.15
    eteria
    -0.15
    uÃŃ
    -0.15
    orex
    -0.15
    jav
    -0.15
    ÑıÑĤи
    -0.15
    roat
    -0.15
     Newman
    -0.14
    ạt
    -0.14
    POSITIVE LOGITS
     coping
    0.19
    ably
    0.15
    ладÑĥ
    0.15
     plunge
    0.14
     managed
    0.14
    ogo
    0.14
    -hero
    0.14
    iro
    0.14
    ìŀ
    0.14
     organ
    0.14
    Act Density 0.063%

    No Known Activations