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

    Neuronpedia

    INDEX
    Explanations

    descriptions of and events in various scenes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    repeated instances or mentions of scenes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.11
    3:0.06
    4:0.03
    5:0.07
    6:0.04
    7:0.04
    8:0.07
    9:0.27
    10:0.09
    11:0.04
    Negative Logits
    ForgeModLoader
    -1.80
    fml
    -1.43
    pees
    -1.35
    覚醒
    -1.32
    iband
    -1.29
    steen
    -1.28
    �
    -1.28
    hemy
    -1.27
    tein
    -1.26
     lact
    -1.24
    POSITIVE LOGITS
     Kubrick
    1.51
     Herod
    1.40
     Foley
    1.32
     Grape
    1.28
     Henri
    1.28
     Veter
    1.26
     Johns
    1.24
     Marina
    1.24
     blurred
    1.23
     Oswald
    1.23
    Act Density 0.032%

    No Known Activations