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

    Neuronpedia

    INDEX
    Explanations

    lines of code that represent expectations or assertions in test cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ODB
    -0.15
    .IsNull
    -0.14
    olly
    -0.14
    \xff
    -0.14
     Spi
    -0.14
    olland
    -0.14
    .lst
    -0.14
    eno
    -0.13
    achu
    -0.13
    aston
    -0.13
    POSITIVE LOGITS
    egis
    0.18
    vů
    0.17
    ung
    0.15
    otope
    0.15
    Subsystem
    0.15
    odo
    0.14
    hind
    0.13
    anford
    0.13
    Anonymous
    0.13
     Yup
    0.13
    Act Density 0.008%

    No Known Activations