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

    Neuronpedia

    INDEX
    Explanations

    comparisons between entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rower
    -0.89
    oire
    -0.83
    ossession
    -0.82
    erva
    -0.82
    utan
    -0.81
    obook
    -0.81
    alian
    -0.79
    ivism
    -0.77
    section
    -0.74
    endment
    -0.73
    POSITIVE LOGITS
     ambassadors
    1.34
     replacements
    1.31
     pillars
    1.26
     extensions
    1.26
     embodiments
    1.25
     heroes
    1.25
     equivalents
    1.23
     pioneers
    1.23
     losers
    1.20
     icons
    1.20
    Act Density 0.381%

    No Known Activations