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

    Neuronpedia

    INDEX
    Explanations

    symbols indicating credits or related to photos in a news article

    oai_token-act-pair · gpt-3.5-turbo

    elements of newsworthy events or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sails
    -0.70
     armour
    -0.69
     deposits
    -0.64
     Draco
    -0.63
     realised
    -0.63
     endeavour
    -0.62
     Kant
    -0.62
     Bale
    -0.61
    ificate
    -0.61
     Macron
    -0.60
    POSITIVE LOGITS
    WASHINGTON
    1.25
    SAN
    1.10
    GREEN
    1.09
    LOS
    1.08
    NEW
    1.01
    CLE
    1.00
    Correct
    0.98
    SHARE
    0.96
    PROV
    0.89
    PORT
    0.89
    Act Density 0.124%

    No Known Activations