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

    Neuronpedia

    INDEX
    Explanations

    texts related to essays

    oai_token-act-pair · gpt-3.5-turbo

    mentions of essays and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.75
    Lago
    -0.70
    generic
    -0.70
    bringing
    -0.64
    cling
    -0.64
    sensitive
    -0.63
    eco
    -0.63
    gone
    -0.62
    gotten
    -0.62
    ategory
    -0.62
    POSITIVE LOGITS
     essay
    1.12
     essays
    0.97
    istical
    0.80
    ists
    0.77
    abal
    0.75
    naire
    0.73
    uably
    0.73
    worms
    0.72
    worm
    0.71
     Slam
    0.71
    Act Density 0.009%

    No Known Activations