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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzle
    -0.17
    aversable
    -0.15
    odon
    -0.14
    ipped
    -0.14
    ueva
    -0.14
    emain
    -0.14
     Crushers
    -0.14
    á»
    -0.14
     eff
    -0.14
    iated
    -0.13
    POSITIVE LOGITS
    rael
    0.16
    lename
    0.15
    omi
    0.15
    ramework
    0.15
     pur
    0.15
    üzel
    0.14
    nels
    0.14
     ÎĮμιλοÏĤ
    0.14
    oldur
    0.14
    ewith
    0.14
    Act Density 0.910%

    No Known Activations