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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote frequency, particularly involving the word "a" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.16
    angu
    -0.16
    idis
    -0.16
    vida
    -0.15
    ays
    -0.15
    QUIT
    -0.14
    ligt
    -0.14
    Occ
    -0.14
    radu
    -0.14
    ied
    -0.14
    POSITIVE LOGITS
     daily
    0.26
     consistent
    0.21
     regular
    0.21
    daily
    0.21
     sho
    0.19
     nightly
    0.19
     whim
    0.18
     rolling
    0.18
     grand
    0.17
     Sho
    0.17
    Act Density 0.043%

    No Known Activations