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

    Neuronpedia

    INDEX
    Explanations

    updates or statements in online content

    oai_token-act-pair · gpt-3.5-turbo

    instances of updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.80
    opian
    -0.78
    ãģ®éŃĶ
    -0.78
    urat
    -0.73
    enance
    -0.72
    isable
    -0.71
    lled
    -0.69
    deen
    -0.68
     hemor
    -0.67
     arous
    -0.66
    POSITIVE LOGITS
     Added
    1.37
     Updated
    1.33
     Adds
    1.32
     Looks
    1.24
     Apparently
    1.24
     Shortly
    1.23
     According
    1.20
     Following
    1.17
     Due
    1.17
     Several
    1.14
    Act Density 0.086%

    No Known Activations