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

    Neuronpedia

    INDEX
    Explanations

    terminology related to retro aesthetics and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.05
    5:0.03
    6:0.42
    7:0.05
    8:0.04
    9:0.04
    10:0.11
    11:0.04
    Negative Logits
     totality
    -1.52
    vv
    -1.35
    azy
    -1.34
     Kaf
    -1.33
     unmarked
    -1.31
     precincts
    -1.30
    hap
    -1.29
    ibaba
    -1.25
     Saiyan
    -1.22
     Nig
    -1.21
    POSITIVE LOGITS
    ®,
    1.40
    911
    1.35
    rencies
    1.34
    serial
    1.34
    ®
    1.33
    ommel
    1.31
    lete
    1.30
    naissance
    1.30
    graph
    1.29
    depend
    1.28
    Act Density 0.001%

    No Known Activations