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

    Neuronpedia

    INDEX
    Explanations

    superlatives or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and related quantitative descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yond
    -0.73
    lass
    -0.72
    pherd
    -0.70
    ansas
    -0.68
    cakes
    -0.67
    iter
    -0.67
    essment
    -0.66
    aking
    -0.64
    abee
    -0.63
    terday
    -0.62
    POSITIVE LOGITS
     misfortune
    1.25
     advantage
    1.17
     utmost
    1.16
     capability
    1.15
     widest
    1.08
     ability
    1.07
     highest
    1.04
     capacity
    1.02
     largest
    1.01
     distinction
    1.01
    Act Density 0.092%

    No Known Activations