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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" indicating temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynos
    -0.16
    raç
    -0.14
    zas
    -0.14
    iov
    -0.14
    perience
    -0.14
    602
    -0.14
    nw
    -0.14
    .axis
    -0.14
    izo
    -0.14
    ocy
    -0.14
    POSITIVE LOGITS
     finally
    0.18
    eken
    0.15
     asked
    0.15
     compared
    0.14
     finished
    0.14
    vre
    0.14
    次
    0.14
    azy
    0.14
     shar
    0.14
    åĬ
    0.13
    Act Density 0.226%

    No Known Activations