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

    Neuronpedia

    INDEX
    Explanations

    family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uve
    -0.81
     Trance
    -0.67
    upuncture
    -0.66
    xtap
    -0.64
    spir
    -0.64
    ÄŁ
    -0.61
     differential
    -0.61
     Judgment
    -0.61
     disparity
    -0.60
    ustomed
    -0.60
    POSITIVE LOGITS
    wife
    0.90
     uncle
    0.77
     sister
    0.76
    hood
    0.75
     niece
    0.75
     namesake
    0.75
     predecessors
    0.74
     aunt
    0.74
     nephew
    0.73
     sons
    0.73
    Act Density 0.120%

    No Known Activations