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

    Neuronpedia

    INDEX
    Explanations

    numerical data or quantitative measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.09
    2:0.04
    3:0.06
    4:0.03
    5:0.05
    6:0.06
    7:0.04
    8:0.04
    9:0.03
    10:0.05
    11:0.41
    Negative Logits
    _.
    -3.56
    ''.
    -3.44
    ‑
    -3.38
    __
    -3.26
    .''
    -3.23
    .''.
    -3.17
    "—
    -3.08
    .""
    -3.07
     nineteen
    -3.01
    ``
    -2.95
    POSITIVE LOGITS
     etc
    6.22
    etc
    4.47
    …)
    3.88
    ?)
    3.80
    ...)
    3.78
    ?)
    3.67
     ie
    3.63
     &
    3.57
    ?),
    3.49
     hrs
    3.33
    Act Density 0.005%

    No Known Activations