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

    Neuronpedia

    INDEX
    Explanations

    references to political or social groups and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Employer
    -0.15
     Priest
    -0.15
    antom
    -0.15
    Ñĸз
    -0.14
    .gov
    -0.14
    iyan
    -0.14
    _MIC
    -0.13
     Bend
    -0.13
     Pri
    -0.13
    лиз
    -0.13
    POSITIVE LOGITS
     Billy
    0.36
    Billy
    0.33
     Fur
    0.30
     Graham
    0.28
     Southern
    0.25
     fur
    0.24
    Southern
    0.23
     Bal
    0.20
    fur
    0.19
    BG
    0.18
    Act Density 0.002%

    No Known Activations