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

    Neuronpedia

    INDEX
    Explanations

    programming-related definitions or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noDo
    -0.88
    AndEndTag
    -0.86
    /**
    -0.85
     nahilalakip
    -0.84
     arşivlendi
    -0.84
    \{\\
    -0.84
    aarrggbb
    -0.84
     ligiloj
    -0.79
    Personensuche
    -0.79
     CreateTagHelper
    -0.77
    POSITIVE LOGITS
     symptoms
    0.62
     experience
    0.61
     symptom
    0.57
     symbol
    0.57
     
    0.54
    ,
    0.52
     experiences
    0.52
    .
    0.50
    1
    0.50
    ard
    0.49
    Act Density 0.335%

    No Known Activations