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

    Neuronpedia

    INDEX
    Explanations

    components of text related to organization and structure in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pike
    -0.17
     Podcast
    -0.15
     plug
    -0.15
    dech
    -0.14
    Pod
    -0.14
     Pod
    -0.14
     prefixed
    -0.14
     plag
    -0.14
     Pony
    -0.14
    opot
    -0.13
    POSITIVE LOGITS
     paper
    1.13
     Paper
    0.98
    paper
    0.97
    -paper
    0.95
    Paper
    0.95
    _paper
    0.87
     papers
    0.85
    .paper
    0.76
     Papers
    0.73
    纸
    0.73
    Act Density 0.168%

    No Known Activations