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

    Neuronpedia

    INDEX
    Explanations

    references to materials and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.17
    edList
    -0.17
    orf
    -0.17
    oran
    -0.16
    hud
    -0.16
    ed
    -0.15
    ho
    -0.15
    hi
    -0.15
    aged
    -0.15
    itories
    -0.14
    POSITIVE LOGITS
    thew
    0.32
    uration
    0.32
    ernal
    0.30
    ilda
    0.29
    ting
    0.26
    ernity
    0.26
    rimon
    0.24
    inee
    0.24
    ematic
    0.23
    adors
    0.23
    Act Density 0.014%

    No Known Activations