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

    Neuronpedia

    INDEX
    Explanations

    unique or special characters and symbols within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =https
    -0.15
     اÙĦÙĩÙĨد
    -0.14
    _PS
    -0.14
     macOS
    -0.14
     ...
    -0.14
    -carousel
    -0.14
    anut
    -0.13
     Patriot
    -0.13
    .px
    -0.13
     impactful
    -0.13
    POSITIVE LOGITS
     Coffee
    0.34
    Coffee
    0.31
     coffee
    0.28
    coffee
    0.26
     Coff
    0.26
     cigarette
    0.25
     cigarettes
    0.24
     espresso
    0.24
     J
    0.23
    igaret
    0.23
    Act Density 0.004%

    No Known Activations