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

    Neuronpedia

    INDEX
    Explanations

    references to official statements or legal and political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.62
    SBATCH
    -0.45
    Threading
    -0.45
    HasAnnotation
    -0.44
    Rhestr
    -0.44
    dziew
    -0.44
    Cubit
    -0.43
    tě
    -0.42
    ưa
    -0.42
     разбира
    -0.42
    POSITIVE LOGITS
     saying
    1.62
     said
    1.53
     berkata
    1.42
    Said
    1.40
     says
    1.39
    said
    1.36
    saying
    1.35
     say
    1.34
     Said
    1.31
     Says
    1.27
    Act Density 0.208%

    No Known Activations