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

    Neuronpedia

    INDEX
    Explanations

    verbs in present tense followed by a possessive pronoun

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and adjectives that indicate ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nare
    -0.71
     Azerb
    -0.65
    efficients
    -0.64
    these
    -0.62
    cules
    -0.57
     Fenrir
    -0.57
    NM
    -0.56
     disadvant
    -0.56
     contrace
    -0.56
    ateurs
    -0.56
    POSITIVE LOGITS
     timetable
    0.67
    brance
    0.66
     newsletter
    0.62
     magazine
    0.61
     liberty
    0.61
     livelihood
    0.59
     gallery
    0.58
     calendar
    0.57
    EngineDebug
    0.56
     liability
    0.56
    Act Density 0.541%

    No Known Activations