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

    Neuronpedia

    INDEX
    Explanations

    references to previous research, citations, and authorship in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     læng
    -0.44
     ſever
    -0.43
     faſt
    -0.41
     reaſon
    -0.40
     ſer
    -0.40
     preſent
    -0.39
     ſur
    -0.39
     giuri
    -0.38
     poussière
    -0.37
    ſelf
    -0.37
    POSITIVE LOGITS
     مرئيه
    0.62
    前任
    0.59
     يتيمه
    0.57
    Биография
    0.56
    IUrlHelper
    0.55
     setError
    0.52
     Dr
    0.52
    ########.
    0.51
    几位
    0.50
    gone
    0.49
    Act Density 0.057%

    No Known Activations