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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that follow specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    data types and programming terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tical
    -0.74
    ijah
    -0.70
    waukee
    -0.69
    orthy
    -0.67
    artifacts
    -0.65
     allerg
    -0.64
    aido
    -0.63
    aukee
    -0.63
    ocobo
    -0.62
    uten
    -0.62
    POSITIVE LOGITS
    String
    1.02
    Builder
    0.93
     String
    0.93
    Buffer
    0.87
    Font
    0.85
    Integer
    0.85
    Array
    0.85
    Parameters
    0.79
    ptr
    0.78
    Ptr
    0.77
    Act Density 0.012%

    No Known Activations