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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "direct" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.53
     Haupt
    -0.40
    :✨
    -0.39
    HttpClientModule
    -0.38
    Identyfik
    -0.37
     insuffisamment
    -0.37
    yntaxException
    -0.36
     verster
    -0.36
     autorytatywna
    -0.35
     ucapnya
    -0.35
    POSITIVE LOGITS
    direct
    0.72
     direct
    0.69
    directed
    0.65
     directed
    0.62
    errHandler
    0.61
    oriented
    0.60
     broadly
    0.59
     esternos
    0.58
     oriented
    0.57
     diretta
    0.57
    Act Density 0.173%

    No Known Activations