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

    Neuronpedia

    INDEX
    Explanations

    words indicating some form of regular or repetitive action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.53
    7:0.04
    8:0.03
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     intersections
    -1.50
     intersection
    -1.41
    POL
    -1.29
    DragonMagazine
    -1.28
     adolesc
    -1.27
     ILCS
    -1.22
     unequ
    -1.21
    ortment
    -1.21
    omew
    -1.20
    Bloom
    -1.19
    POSITIVE LOGITS
    TPPStreamerBot
    1.85
    lesi
    1.58
    si
    1.47
    ciating
    1.43
    Si
    1.37
    fecture
    1.37
    li
    1.32
    ti
    1.28
    repeat
    1.27
    idal
    1.26
    Act Density 0.031%

    No Known Activations