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

    Neuronpedia

    INDEX
    Explanations

    the word "mean" in the context of statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADRA
    -0.76
     manag
    -0.75
    dfx
    -0.75
     accomp
    -0.75
    ASED
    -0.74
    taboola
    -0.73
    conservancy
    -0.71
    dyl
    -0.68
    Assembly
    -0.67
    EStreamFrame
    -0.65
    POSITIVE LOGITS
    ings
    1.00
     spirited
    0.95
    liest
    0.85
    ime
    0.81
    estones
    0.81
    est
    0.81
    piece
    0.79
    downs
    0.78
    eness
    0.77
    lihood
    0.77
    Act Density 0.016%

    No Known Activations