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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of written content or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÑĤÑĥÑĤ
    -0.16
    :this
    -0.16
    té
    -0.15
    æѤ
    -0.14
    ostat
    -0.14
    ilon
    -0.14
    (this
    -0.13
    ãģĵãģ®
    -0.13
    essed
    -0.13
    this
    -0.13
    POSITIVE LOGITS
     we
    0.25
     you
    0.20
     which
    0.17
     learn
    0.17
     titled
    0.17
    learn
    0.17
     besides
    0.16
    æĪij们
    0.15
     learns
    0.15
     Ø¢ÙħدÙĩ
    0.15
    Act Density 0.111%

    No Known Activations