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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to documentation and procedural details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unte
    -0.19
    cia
    -0.17
    寺
    -0.15
    eczy
    -0.15
    RIX
    -0.15
    stime
    -0.14
    bra
    -0.14
    bru
    -0.14
    aldo
    -0.14
    Raster
    -0.14
    POSITIVE LOGITS
    apol
    0.19
    aps
    0.16
     because
    0.15
    357
    0.15
     conn
    0.15
     based
    0.15
    rys
    0.15
     for
    0.14
     Fitz
    0.14
     extent
    0.14
    Act Density 0.011%

    No Known Activations