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

    Neuronpedia

    INDEX
    Explanations

    references to government and governance-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quan
    -0.16
    å«
    -0.16
    nem
    -0.15
    yu
    -0.15
    nelle
    -0.15
    ulk
    -0.14
     dikke
    -0.14
    rox
    -0.14
    олеÑĤ
    -0.14
    bai
    -0.14
    POSITIVE LOGITS
    ToLocal
    0.16
    strap
    0.16
     Bodies
    0.15
     bodies
    0.15
    .za
    0.15
    alls
    0.15
    ment
    0.15
    ARIANT
    0.15
    aget
    0.15
     Medina
    0.15
    Act Density 0.025%

    No Known Activations