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

    Neuronpedia

    INDEX
    Explanations

    titles or headings within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftu
    -0.91
     tranf
    -0.90
     ftre
    -0.90
    frastructure
    -0.89
     confider
    -0.87
     perfon
    -0.87
     nece
    -0.86
     beft
    -0.84
     santiago
    -0.84
     fign
    -0.81
    POSITIVE LOGITS
     title
    1.53
    title
    1.44
     Title
    1.38
     titles
    1.37
     TITLE
    1.29
    Title
    1.28
    TITLE
    1.26
    titles
    1.22
     Titles
    1.19
    Titles
    1.17
    Act Density 0.072%

    No Known Activations