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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upward movements and heights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uttgart
    -0.60
    endregion
    -0.51
     geli
    -0.50
     directa
    -0.49
    ("/:
    -0.49
    НОСТИ
    -0.48
    marginHorizontal
    -0.48
    Fatalf
    -0.47
    <eos>
    -0.47
     busy
    -0.46
    POSITIVE LOGITS
     heights
    1.30
     height
    1.10
     elevation
    1.09
     raiſ
    1.06
    Heights
    0.99
     Elevation
    0.98
     Height
    0.98
     Above
    0.98
     tallest
    0.97
     upward
    0.96
    Act Density 0.443%

    No Known Activations