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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and reports from official sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.19
    3:0.29
    4:0.10
    5:0.04
    6:0.03
    7:0.03
    8:0.04
    9:0.06
    10:0.08
    11:0.04
    Negative Logits
    )."
    -1.96
    ),"
    -1.50
    !).
    -1.46
    NPR
    -1.45
    !'"
    -1.43
    ]."
    -1.41
    .""
    -1.40
    ).[
    -1.39
    !)
    -1.39
     Blitz
    -1.38
    POSITIVE LOGITS
     isEnabled
    1.50
     BALL
    1.46
    eni
    1.43
    ui
    1.40
     nutshell
    1.39
    eno
    1.39
    cli
    1.36
    aden
    1.35
    comfort
    1.35
    gency
    1.33
    Act Density 0.004%

    No Known Activations