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

    Neuronpedia

    INDEX
    Explanations

    structures and elements related to software or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.59
    出版年
    -0.58
    XtraBars
    -0.58
    Хьажоргаш
    -0.58
     Dign
    -0.57
     pourtant
    -0.56
    WriteTagHelper
    -0.55
     Pourtant
    -0.55
    发表于
    -0.53
     hoạch
    -0.52
    POSITIVE LOGITS
     automatically
    0.80
     prompt
    0.76
    automatically
    0.73
     prompted
    0.70
     Apare
    0.69
     instantly
    0.68
     immediately
    0.65
     prompts
    0.65
     confirmation
    0.64
     automatic
    0.63
    Act Density 0.212%

    No Known Activations