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

    Neuronpedia

    INDEX
    Explanations

    words related to academic institutions and fields of study

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and their respective schools or departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amount
    -0.83
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.74
    20439
    -0.71
     liking
    -0.70
     amen
    -0.69
     checkpoints
    -0.66
     hordes
    -0.65
     seams
    -0.64
     stride
    -0.63
    zers
    -0.63
    POSITIVE LOGITS
     Medicine
    1.19
     Management
    1.07
     Engineering
    1.06
     Veterinary
    1.01
     Architecture
    1.01
     Economics
    0.99
     Journalism
    0.98
     Pharm
    0.95
     Psychology
    0.91
     Business
    0.90
    Act Density 0.042%

    No Known Activations