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

    Neuronpedia

    INDEX
    Explanations

    general references to types of descriptions of things

    oai_token-act-pair · gemini-2.0-flash

    terms describing types or kinds

    np_token-act-pair-logits · gpt-4o-mini

    Types/kind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urably
    -0.56
    HtmlAttribute
    -0.54
    Schedulers
    -0.53
    RegistryLite
    -0.49
    octanol
    -0.49
    AndPassword
    -0.49
     saites
    -0.48
     betweenstory
    -0.48
    HandlerContext
    -0.47
    mberg
    -0.46
    POSITIVE LOGITS
     kind
    2.75
     type
    2.70
    kind
    2.27
    type
    2.23
     tipo
    2.20
     kinds
    2.19
     types
    2.16
     sort
    2.13
     Kind
    1.99
     TYPE
    1.99
    Act Density 4.038%

    No Known Activations