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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating caution or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asl
    -0.15
    orks
    -0.14
    SharedPointer
    -0.14
    rians
    -0.14
    iao
    -0.13
    acing
    -0.13
     lev
    -0.13
     wah
    -0.13
    .UnitTesting
    -0.13
    太éĥİ
    -0.13
    POSITIVE LOGITS
    s
    0.21
     others
    0.19
    sage
    0.16
    941
    0.15
    IZES
    0.14
    ades
    0.14
     pods
    0.14
    KeyPressed
    0.14
    oton
    0.14
    erman
    0.14
    Act Density 0.032%

    No Known Activations