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

    Neuronpedia

    INDEX
    Explanations

    syntactic patterns and structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...
    -0.53
     r
    -0.45
     stand
    -0.45
     an
    -0.45
     -
    -0.44
    </h3>
    -0.43
     “
    -0.41
     k
    -0.40
    ↵
    -0.40
    ....
    -0.38
    POSITIVE LOGITS
     autorytatywna
    1.17
     صوتيه
    1.03
     незавершена
    0.99
    NOPQRST
    0.92
     Efq
    0.90
    MLLoader
    0.90
    principalColumn
    0.88
    SpringBootTest
    0.88
     Waray
    0.87
    Hentet
    0.86
    Act Density 0.067%

    No Known Activations