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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific keywords related to structure and organization in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essen
    -0.16
    ahl
    -0.16
    apos
    -0.15
    огÑĢад
    -0.15
    alers
    -0.15
    overy
    -0.15
    inded
    -0.14
    ForResult
    -0.14
     Fold
    -0.14
     Provision
    -0.14
    POSITIVE LOGITS
    нг
    0.16
    ieber
    0.15
    ZONE
    0.14
    ERG
    0.14
    ONEY
    0.14
    HAM
    0.14
    AMED
    0.13
    <=$
    0.13
    iko
    0.13
    igos
    0.13
    Act Density 0.001%

    No Known Activations