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

    Neuronpedia

    INDEX
    Explanations

    directions and spatial relationships

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented phrases describing movement or progression within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     domestically
    -0.73
     unfairly
    -0.73
    netflix
    -0.66
     Berman
    -0.62
     internationally
    -0.61
     flawed
    -0.61
     financially
    -0.61
     unethical
    -0.60
     criminally
    -0.60
     taxpayer
    -0.60
    POSITIVE LOGITS
     moaning
    0.78
     startled
    0.77
     frantic
    0.76
     paused
    0.75
     faint
    0.74
     kneeling
    0.74
     beck
    0.74
     greeted
    0.73
     coughing
    0.72
     blinking
    0.72
    Act Density 0.899%

    No Known Activations