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

    Neuronpedia

    INDEX
    Explanations

    instances of testing descriptors in code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Khal
    -0.15
    Unsafe
    -0.14
     past
    -0.14
    èį
    -0.14
     Absolute
    -0.14
    ¤íĶĦ
    -0.14
    óg
    -0.14
    anten
    -0.14
    linger
    -0.13
    amma
    -0.13
    POSITIVE LOGITS
    vented
    0.15
    .todo
    0.15
     skipped
    0.15
     Suc
    0.14
    ypass
    0.14
    cznie
    0.14
    _should
    0.14
    igma
    0.14
    552
    0.14
    werk
    0.14
    Act Density 0.006%

    No Known Activations