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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meaningless
    -0.80
     reversible
    -0.80
    versible
    -0.75
     pointless
    -0.71
     apocalypse
    -0.70
     stagn
    -0.67
     virgin
    -0.66
     stupid
    -0.64
     tomorrow
    -0.64
     mayhem
    -0.63
    POSITIVE LOGITS
     intimately
    0.89
     fond
    0.86
     mentors
    0.83
     Favorite
    0.80
     befriend
    0.80
     mentor
    0.79
     longtime
    0.78
     sidx
    0.78
     knows
    0.77
     classmate
    0.76
    Act Density 0.772%

    No Known Activations