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

    Neuronpedia

    INDEX
    Explanations

    references to essays, articles, and news content related to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻeb
    -0.17
    ãĤ·ãĤ¢
    -0.15
    åĨ
    -0.15
    lessly
    -0.15
    ле
    -0.14
    íݸ
    -0.14
     journals
    -0.14
    ENE
    -0.14
    705
    -0.13
    hart
    -0.13
    POSITIVE LOGITS
    DOG
    0.16
     opposing
    0.14
     diet
    0.14
     Webb
    0.14
    airy
    0.14
     плен
    0.14
     Cycle
    0.14
    827
    0.14
    rado
    0.14
     cycle
    0.13
    Act Density 0.046%

    No Known Activations