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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases related to identity and social characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.76
    WriteTagHelper
    -0.73
     ſta
    -0.71
     ***!
    -0.66
     ſte
    -0.66
     snippetHide
    -0.65
     pleaſure
    -0.64
     تضيفلها
    -0.63
    twimg
    -0.63
    enumii
    -0.61
    POSITIVE LOGITS
    reszcie
    0.35
     sesi
    0.28
    สง
    0.28
    Hrsg
    0.28
     is
    0.28
     akhirnya
    0.28
     sik
    0.27
    "/",
    0.27
     sak
    0.26
     "*"
    0.26
    Act Density 0.848%

    No Known Activations