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

    Neuronpedia

    INDEX
    Explanations

    occurrences and representations of the word "eight" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ร
    -0.21
    ëį°
    -0.20
    etal
    -0.18
    ont
    -0.16
    ings
    -0.16
    opic
    -0.16
     Ñģобой
    -0.16
    atable
    -0.15
    hone
    -0.15
    itional
    -0.15
    POSITIVE LOGITS
    eenth
    0.50
    een
    0.40
    ï¸ı
    0.21
    *sizeof
    0.19
    th
    0.18
    ãģ¤ãģ®
    0.18
    chan
    0.18
    ies
    0.17
    yi
    0.17
    -bit
    0.17
    Act Density 0.140%

    No Known Activations