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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related adverbs or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulses
    -0.14
    iesel
    -0.14
    immel
    -0.14
    hed
    -0.14
    oref
    -0.14
    ARSER
    -0.14
    valuator
    -0.14
    qrt
    -0.14
    TEGR
    -0.14
    ully
    -0.13
    POSITIVE LOGITS
    stad
    0.15
    brook
    0.15
    ening
    0.14
    iazza
    0.14
    idos
    0.14
    ido
    0.13
    ereo
    0.13
    abra
    0.13
    fra
    0.13
     twice
    0.13
    Act Density 0.042%

    No Known Activations