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

    Neuronpedia

    INDEX
    Explanations

    the article "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.06
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     newsp
    -2.77
     graveyard
    -2.64
    ◼
    -2.61
    iversary
    -2.53
    mbuds
    -2.48
     footnote
    -2.41
     Sprite
    -2.37
     parity
    -2.35
     congratulated
    -2.33
     remnant
    -2.33
    POSITIVE LOGITS
     Rent
    3.13
     Salmon
    3.06
    Balt
    2.95
    Alt
    2.85
    Thu
    2.82
    Der
    2.80
     Bulgar
    2.67
    Ore
    2.66
     Ort
    2.65
    Wed
    2.65
    Act Density 0.000%

    No Known Activations