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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "highlight" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (`/
    -0.68
    ImageField
    -0.66
    Bises
    -0.65
     odo
    -0.62
     peor
    -0.61
    FormItem
    -0.61
    исленность
    -0.60
    databind
    -0.60
     Fee
    -0.59
    falen
    -0.59
    POSITIVE LOGITS
     highlight
    1.35
     highlighting
    1.33
     highlights
    1.33
     Highlight
    1.32
    Highlight
    1.24
    highlights
    1.24
     Highlights
    1.23
     highlighted
    1.20
    Highlighted
    1.19
    Highlights
    1.18
    Act Density 0.133%

    No Known Activations