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

    Neuronpedia

    INDEX
    Explanations

    the word "que"

    oai_token-act-pair · gpt-3.5-turbo

    the word "que" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERAL
    -0.84
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    ãĥĩ
    -0.72
    sonian
    -0.71
    opathic
    -0.71
    opathy
    -0.71
    ortium
    -0.69
    ãĥŁ
    -0.69
    cipline
    -0.69
    rition
    -0.69
    POSITIVE LOGITS
     Que
    0.98
    uing
    0.96
    ued
    0.95
    erness
    0.92
     que
    0.88
    que
    0.88
    iu
    0.86
    ep
    0.84
    ues
    0.80
    eps
    0.80
    Act Density 0.009%

    No Known Activations