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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving insight into various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate providing insight or an overview

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    die
    -0.64
    iu
    -0.62
     backed
    -0.61
    onna
    -0.61
     disappeared
    -0.61
    ammers
    -0.61
    ansom
    -0.61
    ickle
    -0.60
     tomat
    -0.59
     disbanded
    -0.59
    POSITIVE LOGITS
     details
    1.04
     specifics
    1.00
     firsthand
    0.95
     particulars
    0.89
     insight
    0.86
     highlights
    0.83
     acquainted
    0.82
     backstory
    0.81
     glimpse
    0.81
     reveals
    0.80
    Act Density 0.573%

    No Known Activations