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

    Neuronpedia

    INDEX
    Explanations

    the word "Popular."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "popular" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.84
     Aviv
    -0.77
    aul
    -0.72
    ural
    -0.67
    thy
    -0.67
    xual
    -0.66
    uth
    -0.66
    aca
    -0.65
     Kear
    -0.64
    ermott
    -0.63
    POSITIVE LOGITS
    ity
    0.98
     Popular
    0.93
    popular
    0.88
    ized
    0.80
    itarian
    0.79
    iatus
    0.74
     popular
    0.71
     majorities
    0.71
    izing
    0.70
     enterprises
    0.70
    Act Density 0.013%

    No Known Activations