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

    Neuronpedia

    INDEX
    Explanations

    references to air-related terms or concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.59
     numberWith
    -0.47
    detal
    -0.44
     Pot
    -0.43
     Tito
    -0.41
    oten
    -0.40
     مشين
    -0.40
     FetchType
    -0.40
     Monument
    -0.40
     Provid
    -0.39
    POSITIVE LOGITS
     air
    1.15
    Air
    1.08
     Air
    1.06
    air
    1.01
     AIR
    0.97
     airs
    0.84
    AIR
    0.81
     airpods
    0.77
    idać
    0.75
    ypeł
    0.74
    Act Density 0.069%

    No Known Activations