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

    Neuronpedia

    INDEX
    Explanations

    strings that represent quoted text or strings within a code-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.84
    InjectAttribute
    -0.83
     становника
    -0.77
    AddTagHelper
    -0.77
    хьтан
    -0.74
    Tikang
    -0.74
     NSCoder
    -0.73
     ?</
    -0.72
    oneofs
    -0.71
    AsUp
    -0.71
    POSITIVE LOGITS
    “
    0.87
    "
    0.71
    ‘‘
    0.68
    ”
    0.65
    ‘
    0.63
    ’
    0.60
    ../../
    0.60
    「
    0.59
    　　“
    0.59
     (“
    0.59
    Act Density 0.067%

    No Known Activations