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

    Neuronpedia

    INDEX
    Explanations

    links or URLs related to websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.18
    2:0.04
    3:0.06
    4:0.02
    5:0.13
    6:0.05
    7:0.03
    8:0.05
    9:0.10
    10:0.07
    11:0.08
    Negative Logits
     TAMADRA
    -1.55
     Parables
    -1.42
     Pigs
    -1.42
     Thrones
    -1.40
     merits
    -1.40
     faces
    -1.40
     Isles
    -1.39
     BALL
    -1.39
     sided
    -1.37
     Bucks
    -1.35
    POSITIVE LOGITS
    emp
    2.07
    export
    1.83
    open
    1.81
    reference
    1.80
    free
    1.79
    tf
    1.78
    git
    1.72
    unc
    1.70
    syn
    1.70
    average
    1.69
    Act Density 0.003%

    No Known Activations