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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailable
    -0.72
    tein
    -0.70
    ãĥĻ
    -0.66
    arding
    -0.63
     envy
    -0.61
     pulp
    -0.60
    found
    -0.59
    Sel
    -0.58
     reference
    -0.57
    NEWS
    -0.57
    POSITIVE LOGITS
     Thrones
    0.72
     unfold
    0.68
     waning
    0.67
     unfolding
    0.63
    nesota
    0.62
    ember
    0.62
    ï¸
    0.61
    \.
    0.60
     unfolds
    0.59
    !--
    0.59
    Act Density 0.158%

    No Known Activations