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

    Neuronpedia

    INDEX
    Explanations

    references to specific times and scheduling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.86
    ########.
    -0.69
     woke
    -0.62
     waking
    -0.58
    expandindo
    -0.58
    новништво
    -0.58
    ::__
    -0.57
     awoke
    -0.56
     brancas
    -0.55
     AssemblyProduct
    -0.55
    POSITIVE LOGITS
     evening
    1.30
     afternoon
    1.25
     EVENING
    1.05
     Evening
    1.04
     dinner
    1.04
     afternoons
    1.02
     lunch
    0.99
    Evening
    0.96
    evening
    0.96
     Afternoon
    0.95
    Act Density 0.125%

    No Known Activations