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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships, particularly involving stepfamily members

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forecasting
    -0.75
     Simulation
    -0.72
     annexed
    -0.71
     saturated
    -0.71
     borders
    -0.70
     conducive
    -0.69
     UNESCO
    -0.68
     preced
    -0.67
     merit
    -0.66
     crafting
    -0.66
    POSITIVE LOGITS
     sisters
    1.10
    brother
    1.05
     brothers
    1.02
     siblings
    0.99
     girl
    0.98
     daughter
    0.95
     sister
    0.95
     niece
    0.93
     nephew
    0.93
    unts
    0.93
    Act Density 0.375%

    No Known Activations