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

    Neuronpedia

    INDEX
    Explanations

    expressions of political sentiment or actions related to governmental functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihar
    -0.14
    rych
    -0.14
     vere
    -0.14
    PasswordEncoder
    -0.14
    دÙĪد
    -0.14
     åı¤
    -0.14
    ë¹Ī
    -0.14
    LEC
    -0.14
    éĸ
    -0.13
    ади
    -0.13
    POSITIVE LOGITS
     plots
    0.24
     Zion
    0.23
     conspir
    0.21
     Zionist
    0.21
     Tak
    0.21
     intrig
    0.20
     colonial
    0.20
     plot
    0.19
     US
    0.19
     occupation
    0.18
    Act Density 0.049%

    No Known Activations