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

    Neuronpedia

    INDEX
    Explanations

    notifications and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating alerts or announcements of significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advocates
    -0.65
     proponents
    -0.62
    eatures
    -0.62
    itutional
    -0.61
     championed
    -0.61
    respective
    -0.60
     commercially
    -0.60
     globally
    -0.59
    ricanes
    -0.59
     pioneered
    -0.58
    POSITIVE LOGITS
     hurry
    0.82
     tonight
    0.80
     downstairs
    0.79
     urgent
    0.79
     tomorrow
    0.79
     imminent
    0.76
     err
    0.76
     bothering
    0.75
     upstairs
    0.75
     dinner
    0.72
    Act Density 1.425%

    No Known Activations