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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming and hardware

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

    technical configuration/identifier terms denoting operations, resources, or parameters—often multiword code or config names (e.g., snake_case or spaced technical nouns)

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    pylene
    -0.63
     J
    -0.62
    NewUrlParser
    -0.61
     
    -0.61
    pyl
    -0.58
    ecutable
    -0.57
     G
    -0.56
     City
    -0.55
    onema
    -0.54
    getahuan
    -0.53
    POSITIVE LOGITS
     Theſe
    1.02
    withstanding
    0.93
    theless
    0.91
    ⓧ
    0.90
    expandindo
    0.89
     Diſ
    0.88
     Monfieur
    0.87
     Efq
    0.87
     للمعارف
    0.86
     Perſ
    0.85
    Act Density 1.223%

    No Known Activations