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

    Neuronpedia

    INDEX
    Explanations

    terms associated with accountability and transparency in governance or legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chg
    -0.15
    GBK
    -0.15
    okin
    -0.15
     Orth
    -0.14
    oman
    -0.14
     Towers
    -0.14
    egas
    -0.13
     Nes
    -0.13
    Orth
    -0.13
     Nan
    -0.13
    POSITIVE LOGITS
     EFF
    0.48
    EFF
    0.44
     eff
    0.28
    _eff
    0.26
    eff
    0.25
    -eff
    0.24
     privacy
    0.24
     Privacy
    0.23
    EF
    0.22
    EFA
    0.22
    Act Density 0.042%

    No Known Activations