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

    Neuronpedia

    INDEX
    Explanations

    locations or events that are densely filled with people

    oai_token-act-pair · gpt-3.5-turbo

    instances related to being densely filled or crowded

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.81
    nesota
    -0.74
    odan
    -0.71
    clair
    -0.70
    relations
    -0.67
    tymology
    -0.66
    example
    -0.64
    metics
    -0.64
    wikipedia
    -0.63
    endra
    -0.63
    POSITIVE LOGITS
    packed
    1.09
     packed
    0.88
    boxes
    0.85
     crates
    0.85
     loads
    0.83
    ÃįÃį
    0.82
     bags
    0.82
     packing
    0.79
    packs
    0.76
    loads
    0.76
    Act Density 0.021%

    No Known Activations