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

    Neuronpedia

    INDEX
    Explanations

    references to websites or web-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.68
    lasses
    -0.63
    ugal
    -0.62
     increments
    -0.61
     leaps
    -0.61
     neigh
    -0.60
    usions
    -0.60
    licts
    -0.59
    sufficient
    -0.59
     glim
    -0.58
    POSITIVE LOGITS
     website
    3.43
     webpage
    2.71
     websites
    2.50
     Website
    2.48
     site
    2.22
    Website
    2.15
     homepage
    2.15
    bsite
    1.89
     web
    1.77
     blog
    1.76
    Act Density 0.021%

    No Known Activations