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

    Neuronpedia

    INDEX
    Explanations

    narratives about personal relationships and life events involving various individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.77
    herer
    -0.69
     superflu
    -0.68
    lesi
    -0.68
     cutoff
    -0.67
    jriwal
    -0.66
    alions
    -0.64
    uge
    -0.63
     incompet
    -0.63
    cience
    -0.63
    POSITIVE LOGITS
     mutual
    1.38
     friendship
    1.36
     mutually
    1.22
     exchanging
    1.13
    relations
    1.11
     together
    1.10
    CHAT
    1.10
    Relations
    1.09
     rapport
    1.08
     relationship
    1.07
    Act Density 0.736%

    No Known Activations