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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to family members

    oai_token-act-pair · gpt-3.5-turbo

    references to family members and relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JECT
    -0.74
    ernaut
    -0.70
    cher
    -0.66
    vey
    -0.66
    wo
    -0.61
     Deploy
    -0.60
    olt
    -0.60
    vc
    -0.60
    Craft
    -0.59
    izational
    -0.59
    POSITIVE LOGITS
     relatives
    3.63
     cousins
    2.13
     siblings
    1.92
     descendants
    1.90
     grandparents
    1.87
     ancestors
    1.86
     cousin
    1.67
     spouses
    1.66
     families
    1.66
     acquaintances
    1.65
    Act Density 0.017%

    No Known Activations