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

    Neuronpedia

    INDEX
    Explanations

    references to interacting with or being around other people

    oai_token-act-pair · gpt-3.5-turbo

    references to social interactions with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convergence
    -0.76
    ories
    -0.70
     Nanto
    -0.62
    MIT
    -0.60
     deterrence
    -0.60
    tnc
    -0.59
     Industrial
    -0.59
    adobe
    -0.59
    CONCLUS
    -0.59
     modernization
    -0.57
    POSITIVE LOGITS
     whom
    1.14
     else
    1.01
     who
    0.97
    soever
    0.91
    else
    0.85
    folk
    0.83
     intimately
    0.83
    friend
    0.82
    ÃŃs
    0.79
    imity
    0.79
    Act Density 0.321%

    No Known Activations