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

    Neuronpedia

    INDEX
    Explanations

    words related to items being placed or stored on a shelf

    oai_token-act-pair · gpt-3.5-turbo

    references to storage or display surfaces, particularly shelves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nel
    -0.82
     Emir
    -0.78
    ebus
    -0.71
     Annotations
    -0.67
    REDACTED
    -0.67
     delegated
    -0.63
     annexed
    -0.60
     Tone
    -0.59
     Rounds
    -0.58
    ality
    -0.58
    POSITIVE LOGITS
     shelves
    1.41
     shelf
    1.13
    tops
    0.91
    idges
    0.89
    mates
    0.89
    ings
    0.87
    yards
    0.86
    marks
    0.86
    cloth
    0.86
    ength
    0.80
    Act Density 0.023%

    No Known Activations