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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reasons or causes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographs
    -0.96
    ishers
    -0.79
    tops
    -0.78
    osponsors
    -0.78
     Steps
    -0.76
    grounds
    -0.73
    Contents
    -0.72
    stars
    -0.71
    aces
    -0.71
     Exactly
    -0.71
    POSITIVE LOGITS
     lack
    1.53
     shortage
    1.43
     misunderstanding
    1.23
     spate
    1.22
     tendency
    1.21
     shortfall
    1.21
     slowdown
    1.15
     reluctance
    1.12
     mismatch
    1.12
     discrepancy
    1.10
    Act Density 0.231%

    No Known Activations