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

    Neuronpedia

    INDEX
    Explanations

    references to specific centers or institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Centre" as a reference to various organizations or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agging
    -0.78
    mx
    -0.74
    ods
    -0.72
    earable
    -0.70
    arser
    -0.70
    seys
    -0.69
    aceae
    -0.67
    RESULTS
    -0.67
    rieved
    -0.66
    yll
    -0.64
    POSITIVE LOGITS
    piece
    0.99
    ablishment
    0.85
    pieces
    0.83
    gomery
    0.82
    tenance
    0.76
     Centre
    0.74
    bourg
    0.70
    pling
    0.69
    eus
    0.69
     fielder
    0.69
    Act Density 0.021%

    No Known Activations