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

    Neuronpedia

    INDEX
    Explanations

    references to physical containers

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.79
    IELD
    -0.77
    romy
    -0.74
    itters
    -0.73
    bole
    -0.73
    choes
    -0.71
    opal
    -0.69
    olulu
    -0.68
    teenth
    -0.68
    DonaldTrump
    -0.67
    POSITIVE LOGITS
     containers
    1.10
    ainers
    1.08
     container
    1.07
     Container
    1.03
     Crate
    0.88
     minimized
    0.85
    icum
    0.78
     vessel
    0.76
    vier
    0.76
     reef
    0.75
    Act Density 0.028%

    No Known Activations