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

    Neuronpedia

    INDEX
    Explanations

    references to popular media and entertainment successes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.06
    3:0.05
    4:0.03
    5:0.05
    6:0.10
    7:0.10
    8:0.09
    9:0.04
    10:0.07
    11:0.29
    Negative Logits
    grain
    -1.32
     detachment
    -1.31
     mitigating
    -1.29
     Pastebin
    -1.28
     explan
    -1.25
     terminating
    -1.25
     fid
    -1.24
     Shard
    -1.15
     suspended
    -1.14
     disconnected
    -1.13
    POSITIVE LOGITS
    eatures
    1.50
    busters
    1.38
     blockbuster
    1.36
    genre
    1.34
    ovie
    1.30
    alloween
    1.30
    DragonMagazine
    1.25
    AIDS
    1.23
    ixties
    1.20
    budget
    1.19
    Act Density 0.016%

    No Known Activations