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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress and improvements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to progress and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reserved
    -0.76
    umed
    -0.71
    unless
    -0.69
     spoilers
    -0.69
    hate
    -0.69
    isle
    -0.67
     Variant
    -0.67
     Conspiracy
    -0.67
     hates
    -0.66
    ucker
    -0.65
    POSITIVE LOGITS
     successes
    1.48
     achievements
    1.35
     improvements
    1.34
     progress
    1.31
     advancements
    1.31
     accomplishments
    1.28
     improvement
    1.27
     breakthrough
    1.27
     improving
    1.26
     victories
    1.26
    Act Density 0.690%

    No Known Activations