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

    Neuronpedia

    INDEX
    Explanations

    references to public records requests and governmental accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oland
    -0.15
    nez
    -0.15
    erras
    -0.14
     sugars
    -0.14
    alink
    -0.13
    offer
    -0.13
     Rand
    -0.13
    airy
    -0.13
    -0.13
    æĪĴ
    -0.13
    POSITIVE LOGITS
     FO
    0.44
     Freedom
    0.36
    FO
    0.34
    Freedom
    0.31
     Fo
    0.30
    Fo
    0.29
     records
    0.28
     fo
    0.28
     Records
    0.28
    fo
    0.26
    Act Density 0.020%

    No Known Activations