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

    Neuronpedia

    INDEX
    Explanations

    references to examples or case studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ier
    -0.17
    elper
    -0.17
    omo
    -0.16
    stad
    -0.15
    lier
    -0.15
    ering
    -0.15
    ix
    -0.14
    è
    -0.14
    èĢħãģ®
    -0.14
    elsen
    -0.14
    POSITIVE LOGITS
    ãģĪãģ°
    0.20
    /tutorial
    0.18
    OfWork
    0.16
    hlen
    0.16
    arsers
    0.16
    /demo
    0.16
    -fontawesome
    0.15
    ergus
    0.15
    haust
    0.15
    /sample
    0.15
    Act Density 0.034%

    No Known Activations