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

    Neuronpedia

    INDEX
    Explanations

    references to research activities and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.17
    stones
    -0.16
    tery
    -0.15
    çĦ¶
    -0.15
    /part
    -0.14
    bird
    -0.14
    ouch
    -0.14
     nhiên
    -0.14
    ahun
    -0.14
    orous
    -0.14
    POSITIVE LOGITS
    /testing
    0.17
    s
    0.16
    ERSHEY
    0.16
    ÙĦ
    0.15
    Gate
    0.15
    rin
    0.15
    elling
    0.14
    mong
    0.14
    aurant
    0.14
    οÏį
    0.14
    Act Density 0.046%

    No Known Activations