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

    Neuronpedia

    INDEX
    Explanations

    cooking-related instructions containing specific durations

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps in a recipe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spons
    -0.75
     sponsoring
    -0.75
     championed
    -0.74
     franch
    -0.71
     sponsor
    -0.71
     forged
    -0.70
     headquartered
    -0.69
     indemn
    -0.68
     subsid
    -0.67
     charter
    -0.67
    POSITIVE LOGITS
     Occasionally
    1.09
    Eventually
    1.08
     Eventually
    1.05
    Decre
    0.91
     gradually
    0.89
    sometimes
    0.89
     hallucinations
    0.88
    until
    0.86
    ravings
    0.85
    Suddenly
    0.82
    Act Density 0.795%

    No Known Activations