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

    Neuronpedia

    INDEX
    Explanations

    references to physical containers like boxes or vessels

    oai_token-act-pair · gpt-3.5-turbo

    references to containers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IELD
    -0.76
    romy
    -0.72
    doms
    -0.72
    choes
    -0.71
    opal
    -0.71
    reditary
    -0.70
    bole
    -0.70
    olulu
    -0.70
    itters
    -0.70
    oria
    -0.69
    POSITIVE LOGITS
    ainers
    1.10
     containers
    1.05
     container
    1.04
     Container
    0.98
     minimized
    0.89
    vier
    0.78
     Crate
    0.76
    icum
    0.76
     vessel
    0.75
     cellar
    0.73
    Act Density 0.015%

    No Known Activations