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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alama
    -0.17
    çģ°
    -0.16
    GBK
    -0.14
    enic
    -0.14
    Matchers
    -0.14
    strain
    -0.14
    ulumi
    -0.14
    upe
    -0.14
    lsi
    -0.13
    uchos
    -0.13
    POSITIVE LOGITS
    504
    0.20
    Utility
    0.17
     Fletcher
    0.16
     Utility
    0.16
     Tak
    0.15
    è£
    0.15
    ick
    0.15
    ãĥ«ãĥĪ
    0.15
     Corruption
    0.14
     Religion
    0.14
    Act Density 0.021%

    No Known Activations