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

    Neuronpedia

    INDEX
    Explanations

    coding patterns and structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    δα
    -0.18
    WN
    -0.16
    iets
    -0.15
    alo
    -0.15
    ño
    -0.15
    rej
    -0.15
    haps
    -0.14
    -0.14
    quit
    -0.14
    ej
    -0.14
    POSITIVE LOGITS
    ohn
    0.15
    acks
    0.14
    ↵  ↵
    0.14
    lok
    0.13
     bend
    0.13
    ãĥªãĤ¢
    0.13
     heading
    0.13
    andle
    0.13
    azer
    0.13
    ESCO
    0.13
    Act Density 0.243%

    No Known Activations