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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term relationships and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Immutable
    -0.15
    ersistence
    -0.14
    elli
    -0.14
    essler
    -0.14
     closer
    -0.14
     Persistence
    -0.14
    ilon
    -0.14
    oppers
    -0.13
    illos
    -0.13
    ÄŁinden
    -0.13
    POSITIVE LOGITS
     years
    0.43
     generations
    0.37
    years
    0.37
     Years
    0.35
     decades
    0.33
    Years
    0.33
     YEARS
    0.30
    _years
    0.28
    -years
    0.26
     many
    0.25
    Act Density 0.072%

    No Known Activations