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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RELATED
    -0.67
    Sources
    -0.65
     federally
    -0.64
    Trend
    -0.64
    udget
    -0.64
     budgets
    -0.62
     Olympics
    -0.61
    National
    -0.60
     commercially
    -0.60
     multim
    -0.60
    POSITIVE LOGITS
     sighed
    1.08
     glanced
    1.06
     nodded
    1.05
     trembling
    1.04
     glared
    1.03
     glances
    1.00
     muttered
    0.99
     grinned
    0.97
     sigh
    0.97
     crou
    0.97
    Act Density 0.704%

    No Known Activations