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

    Neuronpedia

    INDEX
    Explanations

    locations or brands of places

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.77
     coron
    -0.72
    alty
    -0.71
     compr
    -0.70
     clipboard
    -0.70
    urable
    -0.70
    enance
    -0.67
    anced
    -0.65
    ascular
    -0.65
     pc
    -0.64
    POSITIVE LOGITS
     Bowl
    1.01
     Boy
    1.00
     Fighters
    0.99
     Boys
    0.98
     Strip
    0.97
     Creek
    0.97
     Shop
    0.97
     Mile
    0.95
     Boat
    0.95
     Dogs
    0.94
    Act Density 0.239%

    No Known Activations