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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "packed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "packed" in different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    etheless
    -0.83
    ateur
    -0.78
    odan
    -0.77
    agara
    -0.71
    rant
    -0.70
    alties
    -0.69
    tein
    -0.69
    clair
    -0.69
    context
    -0.68
    gradation
    -0.68
    POSITIVE LOGITS
    packed
    1.01
     crates
    0.90
     bags
    0.86
    boxes
    0.84
     packed
    0.81
     loads
    0.81
    arded
    0.80
     baskets
    0.76
     shelves
    0.76
     suitcase
    0.75
    Act Density 0.026%

    No Known Activations