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

    Neuronpedia

    INDEX
    Explanations

    text that references surveillance, privacy, and technology-related concerns

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

    questions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.58
     OFDb
    -0.42
     Италијани
    -0.41
    帖最后由
    -0.37
    Discografia
    -0.37
    TagMode
    -0.36
    🔕
    -0.36
    hematics
    -0.36
     mergeFrom
    -0.35
     GenerationType
    -0.33
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.65
    adaptiveStyles
    0.56
    +#+
    0.56
     Efq
    0.50
    "]]
    0.48
     goutte
    0.48
    [@BOS@]
    0.48
    <unused79>
    0.48
    <unused8>
    0.48
    <unused3>
    0.48
    Act Density 0.003%

    No Known Activations