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

    Neuronpedia

    INDEX
    Explanations

    references to privacy and the concept of privatization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steller
    -0.18
    ebo
    -0.17
    aines
    -0.16
    aliz
    -0.15
    stras
    -0.15
    nergy
    -0.14
     Fuller
    -0.14
    ÙĪØ·
    -0.14
    agh
    -0.14
    anson
    -0.14
    POSITIVE LOGITS
    ilege
    0.31
    ileged
    0.31
     priv
    0.30
     Priv
    0.29
    ileges
    0.27
    lege
    0.24
     privilege
    0.22
    (priv
    0.22
    iled
    0.22
    Priv
    0.22
    Act Density 0.007%

    No Known Activations