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

    Neuronpedia

    INDEX
    Explanations

    second-person pronouns and directives aimed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    second-person pronouns and phrases addressing "you" directly.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    saraba
    -1.09
     cherchés
    -0.99
    SourceChecksum
    -0.96
    
    -0.94
     disambiguazione
    -0.92
     صوتيه
    -0.90
    principalTable
    -0.90
    帖最后由
    -0.88
     Efq
    -0.88
    ########.
    -0.87
    POSITIVE LOGITS
     yourself
    1.48
     your
    1.12
    yourself
    1.10
    your
    0.92
     Yourself
    0.92
    Yourself
    0.86
     YOURSELF
    0.84
     you
    0.81
     yourselves
    0.79
    you
    0.77
    Act Density 0.899%

    No Known Activations