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

    Neuronpedia

    INDEX
    Explanations

    names of places or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations and associated statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meanings
    -0.66
    minist
    -0.64
    zsche
    -0.63
    agonist
    -0.62
     pestic
    -0.61
     careers
    -0.59
     profession
    -0.58
    Copyright
    -0.57
     signature
    -0.57
    ivities
    -0.56
    POSITIVE LOGITS
     alone
    0.75
     Indies
    0.71
    ague
    0.70
     dominates
    0.69
     ..........
    0.67
    's
    0.67
     (.
    0.65
    inia
    0.64
    SEA
    0.64
     fared
    0.63
    Act Density 0.378%

    No Known Activations