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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistics in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly financial figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.78
     spons
    -0.68
     undermin
    -0.68
     proble
    -0.67
     explan
    -0.65
     additionally
    -0.65
     psychiat
    -0.65
     lett
    -0.65
     behav
    -0.64
     agre
    -0.63
    POSITIVE LOGITS
     Avg
    0.65
    votes
    0.61
     avg
    0.59
     62
    0.58
     Simulation
    0.58
     37
    0.57
     âĨij
    0.57
     77
    0.57
     78
    0.56
    778
    0.56
    Act Density 0.266%

    No Known Activations