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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an extreme or critical degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing extremes or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rounder
    -0.79
     Frames
    -0.64
    annis
    -0.61
    ellow
    -0.59
     peeled
    -0.58
    avorite
    -0.58
     Mush
    -0.58
     Chandra
    -0.57
     Corpus
    -0.56
     batted
    -0.56
    POSITIVE LOGITS
     extent
    0.81
    iculty
    0.76
    oples
    0.75
    liest
    0.73
     absurdity
    0.73
    lessness
    0.69
    olicy
    0.69
     approximation
    0.68
     brink
    0.67
    yll
    0.66
    Act Density 0.040%

    No Known Activations