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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statements or descriptions in a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.66
     Unch
    -0.62
    anu
    -0.60
    ivot
    -0.60
    estern
    -0.60
    thia
    -0.57
     Flavoring
    -0.57
    folio
    -0.56
     sax
    -0.56
    youtube
    -0.56
    POSITIVE LOGITS
     "#
    0.89
    plates
    0.78
     omin
    0.75
     "(
    0.73
     otherwise
    0.72
     nothing
    0.72
    lems
    0.70
     "+
    0.70
     goodbye
    0.70
    :"
    0.70
    Act Density 0.206%

    No Known Activations