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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time progression or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchs
    -0.16
     INNER
    -0.15
    коз
    -0.15
    oppers
    -0.14
    isen
    -0.14
    ãģĿãģĨãģª
    -0.14
    kr
    -0.14
    ER
    -0.13
    .lu
    -0.13
     Inner
    -0.13
    POSITIVE LOGITS
     buildup
    0.22
     run
    0.21
     upto
    0.21
     build
    0.20
     Run
    0.19
     Build
    0.19
    Run
    0.18
     up
    0.18
    run
    0.17
    -build
    0.17
    Act Density 0.014%

    No Known Activations