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

    Neuronpedia

    INDEX
    Explanations

    phrases with a sense of contrast or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    statements that compare or contrast concepts, specifically focusing on what something is not versus what it is

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rower
    -0.91
    etz
    -0.81
    erity
    -0.77
    culosis
    -0.77
    erva
    -0.75
    ittee
    -0.75
    endment
    -0.74
    iere
    -0.73
    west
    -0.71
    onomy
    -0.70
    POSITIVE LOGITS
     reminders
    1.38
     extensions
    1.36
     inventions
    1.32
     ones
    1.31
     replacements
    1.29
     creations
    1.29
     manifestations
    1.28
     indicators
    1.28
     equivalents
    1.27
     relics
    1.27
    Act Density 0.352%

    No Known Activations