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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" or similar demonstrative pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.17
    ahl
    -0.16
    ily
    -0.16
    sus
    -0.15
    idis
    -0.14
    ç
    -0.14
     çł
    -0.14
     Catch
    -0.14
    isposable
    -0.14
    åĴ²
    -0.14
    POSITIVE LOGITS
    oretical
    0.16
    oret
    0.15
    coma
    0.15
    lamaz
    0.14
     latter
    0.14
    座
    0.14
    :///
    0.14
    aca
    0.14
    mtx
    0.14
    ÃŃg
    0.13
    Act Density 0.113%

    No Known Activations