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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the sequence "na"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "na" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.80
    ienced
    -0.73
    raved
    -0.66
    tails
    -0.65
    UID
    -0.64
    starter
    -0.63
    omez
    -0.63
    mop
    -0.63
    aws
    -0.63
     AQ
    -0.63
    POSITIVE LOGITS
    eus
    1.31
    uthor
    1.16
    isance
    1.00
    vel
    0.98
    ples
    0.96
    wn
    0.91
    fer
    0.83
    ïve
    0.82
    veland
    0.80
    emi
    0.78
    Act Density 0.035%

    No Known Activations