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

    Neuronpedia

    INDEX
    Explanations

    phrases related to everybody

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "everybody" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isson
    -0.72
    enh
    -0.72
    inter
    -0.71
     Nanto
    -0.70
    har
    -0.68
    hent
    -0.67
    tumblr
    -0.67
    ean
    -0.66
    heny
    -0.66
    efficient
    -0.65
    POSITIVE LOGITS
     else
    1.12
     everybody
    1.00
    THING
    0.90
     Everybody
    0.85
     imaginable
    0.82
     nomine
    0.81
     enthusi
    0.79
     combust
    0.78
    rats
    0.77
     mathemat
    0.76
    Act Density 0.007%

    No Known Activations