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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "purpose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roy
    -0.15
    lining
    -0.15
    r
    -0.15
    acters
    -0.15
    rec
    -0.15
    ship
    -0.15
    ÅĻet
    -0.14
    roller
    -0.14
    ule
    -0.14
    ERIC
    -0.14
    POSITIVE LOGITS
    ful
    0.23
    fully
    0.21
    lessly
    0.18
    full
    0.18
    FUL
    0.18
    lexport
    0.17
    .scalablytyped
    0.16
     Copp
    0.16
    -built
    0.16
    fulness
    0.15
    Act Density 0.019%

    No Known Activations