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

    Neuronpedia

    INDEX
    Explanations

    attributes related to design and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kadot
    -0.45
     medlems
    -0.41
     paroisse
    -0.40
     قاد
    -0.39
    :+:
    -0.39
     housse
    -0.39
    Membership
    -0.38
     OnTrigger
    -0.38
     antemano
    -0.38
    writerow
    -0.38
    POSITIVE LOGITS
     charm
    1.09
     depth
    1.03
     warmth
    1.00
     charisma
    0.97
     flavor
    0.97
     personality
    0.96
     substance
    0.94
     sophistication
    0.92
     authenticity
    0.91
     sparkle
    0.91
    Act Density 0.387%

    No Known Activations