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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to companies, organizations, and products

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to decision-making and options within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.63
     straw
    -0.62
     date
    -0.62
     flush
    -0.61
     ditch
    -0.60
     enshr
    -0.60
     remotely
    -0.60
     recourse
    -0.59
     schedule
    -0.58
     peak
    -0.58
    POSITIVE LOGITS
    love
    0.91
     Labs
    0.89
     Management
    0.86
    Maker
    0.83
    Works
    0.82
    ocene
    0.80
     Disorders
    0.80
     Factory
    0.80
     Foods
    0.79
     Matters
    0.78
    Act Density 0.243%

    No Known Activations