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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "highlight" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (`/
    -0.77
    loem
    -0.71
    databind
    -0.68
     mAdapter
    -0.67
     caseros
    -0.67
    jsonwebtoken
    -0.65
    rils
    -0.65
    исленность
    -0.65
     Polskiego
    -0.63
     geslacht
    -0.63
    POSITIVE LOGITS
     highlight
    1.68
     highlights
    1.65
     Highlight
    1.64
    highlights
    1.58
     Highlights
    1.56
     highlighting
    1.53
    Highlight
    1.47
    Highlights
    1.45
    highlight
    1.45
     highlighted
    1.42
    Act Density 0.088%

    No Known Activations