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

    Neuronpedia

    INDEX
    Explanations

    references to winning and competitive success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.16
    ¾
    -0.15
    ensively
    -0.15
    avn
    -0.15
    eed
    -0.14
    gaard
    -0.14
    aç
    -0.14
    ish
    -0.14
     ÑĢаÐ
    -0.14
    alar
    -0.14
    POSITIVE LOGITS
    eries
    0.38
    ery
    0.38
    em
    0.27
    ERY
    0.27
    emaker
    0.23
    making
    0.21
    éry
    0.21
     ery
    0.21
    eria
    0.20
    erm
    0.19
    Act Density 0.003%

    No Known Activations