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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms explicitly related to politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elden
    -0.19
    hazi
    -0.17
    kın
    -0.16
    ederland
    -0.15
    piry
    -0.15
    inel
    -0.14
    /div
    -0.14
    olar
    -0.14
    amilia
    -0.14
    lation
    -0.13
    POSITIVE LOGITS
    /legal
    0.18
    -economic
    0.16
    noinspection
    0.14
    -media
    0.14
     extrad
    0.14
    -admin
    0.14
    rosse
    0.13
    _cpus
    0.13
    _bh
    0.13
    sher
    0.13
    Act Density 0.036%

    No Known Activations