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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" followed by additional information or continuation

    oai_token-act-pair · gpt-3.5-turbo

    phrases with coordination or conjunctions indicating connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azi
    -0.74
    hof
    -0.73
     Picks
    -0.71
    ulz
    -0.71
    nosis
    -0.69
    maxwell
    -0.68
    ipation
    -0.68
    hov
    -0.67
    bia
    -0.67
    eness
    -0.66
    POSITIVE LOGITS
     executed
    1.09
     repaired
    1.09
     photographed
    1.08
     maintained
    1.08
     calibrated
    1.05
     insured
    1.02
     tested
    1.02
     ready
    1.02
     marketed
    1.02
     vetted
    1.02
    Act Density 0.171%

    No Known Activations