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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and data anonymity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rips
    -0.17
    rikes
    -0.15
    ÏĦε
    -0.15
     Blades
    -0.14
    ensual
    -0.14
    erior
    -0.14
    ripp
    -0.14
    219
    -0.14
    ä»°
    -0.14
    istrovstvÃŃ
    -0.14
    POSITIVE LOGITS
    KEN
    0.14
    顯
    0.14
    ulle
    0.14
     Truman
    0.14
    ken
    0.14
    à¥įयव
    0.14
    stm
    0.13
     Listening
    0.13
    By
    0.13
     Protected
    0.13
    Act Density 0.014%

    No Known Activations