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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparing past and present situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate relevance or validity in a current context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onymous
    -0.61
     Deity
    -0.60
     Written
    -0.59
    ifice
    -0.53
     enthusi
    -0.53
    tex
    -0.52
    min
    -0.51
    ilaterally
    -0.51
     Telegram
    -0.51
     embargo
    -0.50
    POSITIVE LOGITS
     now
    1.75
     nowadays
    1.54
    today
    1.50
     today
    1.49
     Now
    1.48
    Today
    1.47
    Now
    1.45
     Today
    1.44
    now
    1.42
     NOW
    1.29
    Act Density 1.104%

    No Known Activations