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

    Neuronpedia

    INDEX
    Explanations

    phrases related to remaining or ensuring correctness in technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to stability and consistency in data or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anship
    -0.76
    utical
    -0.74
    lihood
    -0.71
    vernment
    -0.69
    stakes
    -0.69
    utic
    -0.68
    seeking
    -0.67
     Opportunity
    -0.67
     Flavoring
    -0.65
    rouse
    -0.65
    POSITIVE LOGITS
     readable
    1.23
     identical
    1.14
     sorted
    1.13
     grouped
    1.08
     intact
    1.07
     interchangeable
    1.06
     synchronized
    1.06
     cached
    1.05
     unchanged
    1.04
     aligned
    1.03
    Act Density 0.288%

    No Known Activations