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

    Neuronpedia

    INDEX
    Explanations

    references to groups or organizations, specifically clans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to clans and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    piration
    -0.68
    Ö¼
    -0.68
    Jane
    -0.64
     HuffPost
    -0.63
     Patient
    -0.62
    Label
    -0.62
    grades
    -0.61
    ¤
    -0.61
     Continued
    -0.60
     Kear
    -0.60
    POSITIVE LOGITS
     clans
    1.24
     clan
    1.13
    mates
    0.99
    imore
    0.97
    ourage
    0.89
    ieft
    0.84
     elders
    0.84
    members
    0.83
     chiefs
    0.83
     dynasty
    0.75
    Act Density 0.010%

    No Known Activations