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

    Neuronpedia

    INDEX
    Explanations

    descriptive features of characters, particularly focusing on physical attributes and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astify
    -0.67
    Хьажоргаш
    -0.57
    ThroughAttribute
    -0.54
    gonic
    -0.54
    prelude
    -0.51
    tetés
    -0.50
    edale
    -0.50
    รุ่น
    -0.49
    felves
    -0.49
     doInBackground
    -0.49
    POSITIVE LOGITS
     personality
    0.95
     charisma
    0.89
     looks
    0.82
     physique
    0.72
     demeanor
    0.72
     manners
    0.70
    personality
    0.69
     smile
    0.67
     personalidad
    0.67
     charm
    0.67
    Act Density 0.277%

    No Known Activations