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

    Neuronpedia

    INDEX
    Explanations

    references to air and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OnInit
    -0.49
    싶
    -0.47
     resourceCulture
    -0.46
    richTextPanel
    -0.45
    onom
    -0.45
    tste
    -0.45
    abbaye
    -0.44
     keuze
    -0.43
    ologist
    -0.43
     keja
    -0.43
    POSITIVE LOGITS
     air
    1.62
    Air
    1.59
     Air
    1.55
     AIR
    1.52
    AIR
    1.30
    air
    1.29
     Luft
    1.11
     luft
    1.05
    Luft
    1.02
     aire
    1.00
    Act Density 0.098%

    No Known Activations