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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampion
    -0.17
     Reb
    -0.14
    eturn
    -0.14
    =__
    -0.14
     LEN
    -0.14
    eden
    -0.14
    259
    -0.14
    {{{
    -0.13
    icamente
    -0.13
     Gap
    -0.13
    POSITIVE LOGITS
    èĪĴ
    0.17
    IFO
    0.16
    ви
    0.16
    å·±
    0.15
    ãģ¯ãģļ
    0.15
    riz
    0.15
     Inflate
    0.14
    loop
    0.14
    ulo
    0.14
    ousse
    0.14
    Act Density 0.260%

    No Known Activations