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

    Neuronpedia

    INDEX
    Explanations

    numeric measurements, specifically related to volume or quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of volume, particularly in cubic units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakening
    -0.66
    alt
    -0.64
     Heidi
    -0.63
     Esther
    -0.63
    idates
    -0.63
     Bind
    -0.61
    fight
    -0.60
     Allaah
    -0.60
    eve
    -0.60
    intend
    -0.60
    POSITIVE LOGITS
     cubic
    4.01
     sq
    1.44
     square
    1.43
    sq
    1.35
     linear
    1.18
     litres
    1.14
    square
    1.11
     cube
    1.11
     acre
    1.11
     Linear
    1.10
    Act Density 0.023%

    No Known Activations