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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing the degree or intensity of an action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iership
    -0.78
    angering
    -0.74
    icide
    -0.72
     needs
    -0.70
    uries
    -0.70
    visory
    -0.68
     hurts
    -0.68
     sucks
    -0.66
    orem
    -0.65
    igate
    -0.64
    POSITIVE LOGITS
     similarities
    0.89
     juxtap
    0.85
     resemblance
    0.80
     similarity
    0.79
     strikingly
    0.78
     contrasting
    0.76
     curiously
    0.72
     reactions
    0.72
     mention
    0.71
     unexpected
    0.70
    Act Density 0.323%

    No Known Activations