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

    Neuronpedia

    INDEX
    Explanations

    statistical increases or changes in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    change from previous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вікісторінку
    -0.62
     snippetHide
    -0.61
    DockStyle
    -0.60
    pushFollow
    -0.59
     مرئيه
    -0.59
     queſta
    -0.59
    TestingModule
    -0.58
     Majefty
    -0.57
     muualla
    -0.57
     Houſe
    -0.57
    POSITIVE LOGITS
     previous
    0.43
     previously
    0.36
     sebelumnya
    0.35
    previous
    0.34
     since
    0.30
     Previous
    0.29
    Previously
    0.29
    previously
    0.29
    complexContent
    0.29
     recognition
    0.29
    Act Density 0.027%

    No Known Activations