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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interaction and community building

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    atism
    -0.75
    urrection
    -0.70
    arted
    -0.69
    CONCLUS
    -0.66
    ascus
    -0.66
    osterone
    -0.64
    ãĥ©ãĥ³
    -0.63
     culmination
    -0.62
    constitutional
    -0.62
    ocally
    -0.62
    POSITIVE LOGITS
     who
    0.82
     ;)
    0.80
     :)
    0.80
     else
    0.76
     Disco
    0.76
    friend
    0.74
     Favorite
    0.74
    \'
    0.73
     whom
    0.73
     wifi
    0.71
    Act Density 0.158%

    No Known Activations