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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "twenty" or variations referencing the number twenty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hundred
    -0.18
     hundred
    -0.17
    Å¡ÃŃ
    -0.15
    Ïĥει
    -0.15
    uzzer
    -0.15
    abi
    -0.15
    /apt
    -0.15
     Joy
    -0.15
    uw
    -0.14
    ±Ð¾ÑĤ
    -0.14
    POSITIVE LOGITS
    -one
    0.26
    -two
    0.26
    -five
    0.25
    -first
    0.24
    -One
    0.23
    -three
    0.23
    -four
    0.22
    -nine
    0.21
    odd
    0.21
    -eight
    0.20
    Act Density 0.031%

    No Known Activations