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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or positioning

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    éről
    -0.50
     része
    -0.46
    ároz
    -0.46
    واسطة
    -0.45
    Források
    -0.45
    engkapi
    -0.44
     gosta
    -0.42
    éhez
    -0.42
    beiter
    -0.42
     edema
    -0.41
    POSITIVE LOGITS
     sappi
    0.89
     lamborghini
    0.80
     swarovski
    0.77
     effe
    0.77
     vespa
    0.77
     cioc
    0.76
     peculi
    0.75
     sopr
    0.74
     eiffel
    0.72
     discogs
    0.72
    Act Density 0.284%

    No Known Activations