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

    Neuronpedia

    INDEX
    Explanations

    variable or field names in code, particularly those related to "name"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of variable names, particularly those related to user or item attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.79
    )";
    -0.77
     {},
    -0.76
     {}\
    -0.76
    /#{
    -0.76
    ;">
    -0.76
     [],
    -0.75
    {}/
    -0.74
    UIControlState
    -0.73
    ^(@)
    -0.72
    POSITIVE LOGITS
     name
    1.64
     Name
    1.57
    name
    1.53
     NAME
    1.52
    Name
    1.45
     names
    1.45
    NAME
    1.38
     Names
    1.36
    names
    1.34
    getName
    1.20
    Act Density 0.119%

    No Known Activations