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

    Neuronpedia

    INDEX
    Explanations

    expressions of nostalgia or significant reflections on the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.10
    3:0.28
    4:0.08
    5:0.04
    6:0.06
    7:0.06
    8:0.05
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
    MpServer
    -1.94
    "))
    -1.89
    ":"/
    -1.88
    KK
    -1.71
    SIGN
    -1.65
    onga
    -1.63
    rift
    -1.63
    )))
    -1.63
    estamp
    -1.58
    auri
    -1.58
    POSITIVE LOGITS
     morbid
    1.65
     myths
    1.52
     tho
    1.52
     deserts
    1.51
     lyr
    1.47
     jealous
    1.47
     gloss
    1.46
     Pharaoh
    1.45
     Scare
    1.43
     VERY
    1.42
    Act Density 0.000%

    No Known Activations