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

    Neuronpedia

    INDEX
    Explanations

    words related to interactions with people and social experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assin
    -0.15
    ugin
    -0.15
    aminer
    -0.15
    latin
    -0.14
     tweet
    -0.14
     tweets
    -0.14
     skiing
    -0.14
     ner
    -0.14
    otti
    -0.14
     Tweets
    -0.14
    POSITIVE LOGITS
     Gecko
    0.22
    tuk
    0.20
     Lonely
    0.19
     locals
    0.18
     guides
    0.18
     UNESCO
    0.18
     local
    0.17
     Backpack
    0.17
     bargaining
    0.17
     guide
    0.17
    Act Density 0.209%

    No Known Activations