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

    Neuronpedia

    INDEX
    Explanations

    terms related to community infrastructure and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifecycle
    -0.18
    rieg
    -0.17
    arella
    -0.15
    madan
    -0.14
    bur
    -0.14
    ANNER
    -0.13
    992
    -0.13
    izens
    -0.13
    ride
    -0.13
    rome
    -0.13
    POSITIVE LOGITS
    utor
    0.15
    ynch
    0.14
    utex
    0.14
    edula
    0.14
     would
    0.14
    anism
    0.13
    would
    0.13
    ยà¸ĩ
    0.13
    ico
    0.13
    plode
    0.13
    Act Density 0.080%

    No Known Activations