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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Voters
    -0.18
    zyst
    -0.18
     Readers
    -0.17
     readers
    -0.16
    itchens
    -0.15
    Boss
    -0.15
     viewers
    -0.14
    standen
    -0.14
    ома
    -0.14
    ippi
    -0.14
    POSITIVE LOGITS
     members
    0.49
     individuals
    0.42
     relatives
    0.41
     persons
    0.38
    members
    0.36
     friends
    0.36
     loved
    0.35
     characters
    0.35
     Members
    0.35
    -members
    0.33
    Act Density 0.027%

    No Known Activations