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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities (e.g., volume measurements)

    oai_token-act-pair · gpt-3.5-turbo

    quantities of liquid measured in litres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chain
    -0.71
     Cosby
    -0.70
     Alphabet
    -0.69
    ensity
    -0.68
     loft
    -0.68
     chains
    -0.67
    paper
    -0.67
     maj
    -0.65
     Penn
    -0.64
     ner
    -0.62
    POSITIVE LOGITS
     litres
    2.46
     mars
    1.98
    rax
    1.17
    ARS
    1.12
     waterways
    1.11
    venth
    1.11
     hectares
    1.10
     wetlands
    1.00
    mination
    0.99
     ensued
    0.94
    Act Density 0.042%

    No Known Activations