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

    Neuronpedia

    INDEX
    Explanations

    names containing the sequence "air" with relatively high activations

    oai_token-act-pair · gpt-3.5-turbo

    words related to air

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kuh
    -0.85
     Kern
    -0.75
     Rosenstein
    -0.62
     bang
    -0.62
     Schne
    -0.61
     KY
    -0.59
     Principles
    -0.59
     Heck
    -0.59
    ktop
    -0.58
     CLSID
    -0.57
    POSITIVE LOGITS
    bnb
    1.19
    plane
    0.98
    neau
    0.97
    waves
    0.93
    culosis
    0.85
    dropping
    0.83
    planes
    0.83
    lift
    0.83
    air
    0.80
    adan
    0.78
    Act Density 0.008%

    No Known Activations