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

    Neuronpedia

    INDEX
    Explanations

    references to political roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     насељу
    -0.53
    modb
    -0.47
    hring
    -0.46
    ilstein
    -0.46
    ughter
    -0.45
     beneficiaries
    -0.45
    ambiguation
    -0.45
    Ethnicity
    -0.44
    RenderAtEndOf
    -0.43
     crossorigin
    -0.42
    POSITIVE LOGITS
     secret
    0.88
     Secret
    0.85
    secret
    0.82
    Secret
    0.81
     presidents
    0.80
     Vice
    0.78
     president
    0.78
    Vice
    0.76
     SECRET
    0.76
     President
    0.75
    Act Density 0.138%

    No Known Activations