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

    Neuronpedia

    INDEX
    Explanations

    government websites

    oai_token-act-pair · gpt-3.5-turbo

    references to government websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rye
    -0.67
     Blaze
    -0.67
     Apostle
    -0.65
    Rust
    -0.64
    ById
    -0.64
     admirable
    -0.62
     Cats
    -0.61
     mighty
    -0.60
     virtues
    -0.60
    Bone
    -0.60
    POSITIVE LOGITS
    gov
    1.36
    rolet
    0.92
    ulnerability
    0.90
    vernment
    0.89
    iets
    0.88
    ulkan
    0.87
    lov
    0.87
    etsk
    0.86
    puters
    0.86
    lishes
    0.86
    Act Density 0.003%

    No Known Activations