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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pile
    -0.16
    way
    -0.15
    pes
    -0.15
    z
    -0.15
    ersed
    -0.14
    .userInteractionEnabled
    -0.14
    ux
    -0.14
    instr
    -0.14
    pir
    -0.13
    imento
    -0.13
    POSITIVE LOGITS
     variety
    0.42
     Variety
    0.30
     range
    0.29
    eron
    0.26
    vari
    0.24
     varieties
    0.23
     wide
    0.23
     various
    0.22
     number
    0.22
     assortment
    0.22
    Act Density 0.381%

    No Known Activations