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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power dynamics and governmental authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥģ
    -0.14
     Jacqu
    -0.14
    Wave
    -0.14
     Isles
    -0.14
    iland
    -0.14
     Volunteers
    -0.14
    ÑģÑıÑĤ
    -0.13
    .BorderFactory
    -0.13
    eworthy
    -0.13
    wave
    -0.13
    POSITIVE LOGITS
     branch
    0.32
     executive
    0.31
     separation
    0.30
    branch
    0.29
     Executive
    0.28
     branches
    0.27
     Branch
    0.27
    Executive
    0.27
    branches
    0.26
     nhánh
    0.26
    Act Density 0.048%

    No Known Activations