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

    Neuronpedia

    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various uses or purposes for places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requires
    -0.77
    UTH
    -0.75
     RELE
    -0.75
    ĸļ
    -0.69
    ernaut
    -0.65
     batches
    -0.64
     warrants
    -0.64
    tle
    -0.63
    iously
    -0.62
    ebus
    -0.61
    POSITIVE LOGITS
    ezvous
    0.80
     dwell
    0.79
    aign
    0.69
     enrol
    0.69
     refuge
    0.69
     desks
    0.69
    enture
    0.68
     discuss
    0.67
    agne
    0.66
    isphere
    0.65
    Act Density 0.095%

    No Known Activations