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

    Neuronpedia

    INDEX
    Explanations

    mentions of family relationships, focusing on siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to age relationships and past associations between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Chip
    -0.74
     Canaver
    -0.67
    inctions
    -0.67
    cius
    -0.66
    ð
    -0.66
    Õ
    -0.65
    haus
    -0.63
    hig
    -0.62
    vertising
    -0.62
    @#&
    -0.62
    POSITIVE LOGITS
     selves
    1.40
     counterparts
    1.37
     brethren
    1.26
     surroundings
    1.21
     counterpart
    1.19
     cousin
    1.15
     cousins
    1.14
     predecessors
    1.08
     peers
    1.06
     destiny
    1.05
    Act Density 0.310%

    No Known Activations