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

    Neuronpedia

    INDEX
    Explanations

    references to different types of containers

    oai_token-act-pair · gpt-3.5-turbo

    references to containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mens
    -0.77
    Psych
    -0.75
    Bet
    -0.74
     Earn
    -0.70
     Reeves
    -0.69
     pron
    -0.68
    oly
    -0.68
    philis
    -0.67
     Psych
    -0.66
     Fox
    -0.66
    POSITIVE LOGITS
     container
    3.47
     containers
    3.20
     Container
    2.68
    container
    2.59
    Container
    2.25
    ainers
    1.98
     Docker
    1.65
     docker
    1.56
    docker
    1.45
     vessel
    1.41
    Act Density 0.023%

    No Known Activations