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

    Neuronpedia

    INDEX
    Explanations

    words related to creativity and originality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to originality and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FY
    -0.71
    çīĪ
    -0.70
     Reported
    -0.70
    ificantly
    -0.69
    USS
    -0.65
     Cosponsors
    -0.64
    recent
    -0.64
    Latest
    -0.64
    ndum
    -0.63
    oday
    -0.63
    POSITIVE LOGITS
     ALWAYS
    0.88
     sometimes
    0.81
     seldom
    0.76
     Happiness
    0.75
     instinctively
    0.74
     always
    0.74
     often
    0.72
     happiness
    0.71
     Sometimes
    0.71
     rarely
    0.70
    Act Density 1.123%

    No Known Activations