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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compass
    -0.82
     Enhancement
    -0.73
    metadata
    -0.67
    grounds
    -0.67
     Independence
    -0.64
     Kinnikuman
    -0.64
     Millennium
    -0.64
    ements
    -0.61
    wikipedia
    -0.60
     Measures
    -0.59
    POSITIVE LOGITS
     spoil
    1.19
     bother
    1.14
     offend
    1.14
     admit
    1.10
     waste
    1.09
     spend
    1.08
     hear
    1.07
     lose
    1.03
     burden
    1.01
     risk
    1.00
    Act Density 0.087%

    No Known Activations