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

    Neuronpedia

    INDEX
    Explanations

    headlines or news article formatting, specifically focusing on highlighted or emphasized text

    oai_token-act-pair · gpt-3.5-turbo

    colons and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uton
    -0.75
     lease
    -0.74
     reckoning
    -0.73
    etheless
    -0.72
     rule
    -0.70
    ivable
    -0.67
    lag
    -0.64
     traitor
    -0.63
     ignor
    -0.62
     brewer
    -0.61
    POSITIVE LOGITS
    HAM
    0.86
     STORY
    0.85
     WORLD
    0.84
     WATCHED
    0.81
     CONTIN
    0.80
     DRAGON
    0.78
     VIDEOS
    0.78
     FANTASY
    0.76
     WRITE
    0.74
    ONSORED
    0.74
    Act Density 0.054%

    No Known Activations