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

    Neuronpedia

    INDEX
    Explanations

    specific character sequences that likely represent a different language or encoding format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apost
    -0.78
    ardless
    -0.74
     wardrobe
    -0.73
     occas
    -0.69
     Creed
    -0.69
     patriotic
    -0.69
     Mog
    -0.68
     patri
    -0.68
    ldom
    -0.67
    atism
    -0.66
    POSITIVE LOGITS
    Researchers
    1.35
    Scientists
    1.30
    DNA
    1.20
    Explore
    1.12
    Science
    1.05
    Testing
    1.02
    MRI
    1.02
    RNA
    1.00
    ccording
    0.98
    Research
    0.96
    Act Density 0.338%

    No Known Activations