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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency conjunctions and connecting words in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oli
    -0.16
    ãĥ³ãĤ¯
    -0.16
    UNUSED
    -0.15
    нÑĮ
    -0.14
    οÏįÏĤ
    -0.14
    olit
    -0.14
    ivent
    -0.14
    ols
    -0.14
    ocha
    -0.14
    upon
    -0.13
    POSITIVE LOGITS
    otte
    0.19
    insky
    0.17
    ritch
    0.15
    ottle
    0.15
    .hu
    0.15
     nackte
    0.15
     sana
    0.14
    æ¸Ī
    0.14
    kuk
    0.14
    zilla
    0.14
    Act Density 0.011%

    No Known Activations