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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing personal traits and preferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     omin
    -0.71
     scrimmage
    -0.70
     indefinitely
    -0.70
    çķ
    -0.70
     plantations
    -0.67
    apeake
    -0.67
     allegations
    -0.66
     advances
    -0.66
     disappear
    -0.65
    tein
    -0.64
    POSITIVE LOGITS
     myself
    0.98
     believer
    0.95
     obsessed
    0.92
     OCD
    0.92
     lucky
    0.90
     geek
    0.90
     avid
    0.89
     fascinated
    0.88
     obsessive
    0.88
     passionate
    0.86
    Act Density 0.306%

    No Known Activations