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

    Neuronpedia

    INDEX
    Explanations

    mentions of class distinctions or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.17
    jar
    -0.14
    ase
    -0.14
    èĢħ
    -0.14
    registr
    -0.14
    -в
    -0.14
    èĢħçļĦ
    -0.14
    439
    -0.13
    ennes
    -0.13
    313
    -0.13
    POSITIVE LOGITS
    mate
    0.21
     Insecta
    0.20
    ä¼¼
    0.20
    mates
    0.19
    rooms
    0.17
    IPPING
    0.16
    ses
    0.15
    åĪ«
    0.15
    CastException
    0.15
    .updateDynamic
    0.15
    Act Density 0.048%

    No Known Activations