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

    Neuronpedia

    INDEX
    Explanations

    prominent names and identifiers within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.07
    2:0.03
    3:0.04
    4:0.03
    5:0.36
    6:0.03
    7:0.01
    8:0.06
    9:0.15
    10:0.10
    11:0.04
    Negative Logits
     EVE
    -1.45
    ‑
    -1.38
     Grape
    -1.33
     Quake
    -1.29
     ogre
    -1.29
    bound
    -1.23
     Ubuntu
    -1.21
     raining
    -1.20
     vanilla
    -1.19
    Lex
    -1.18
    POSITIVE LOGITS
    enegger
    2.21
     testified
    1.64
    ItemImage
    1.45
     Parables
    1.45
     Cosponsors
    1.43
    owship
    1.42
    ideos
    1.41
    igham
    1.38
    owsky
    1.36
     recounted
    1.33
    Act Density 0.164%

    No Known Activations