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

    Neuronpedia

    INDEX
    Explanations

    references to binge-watching and streaming activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.06
    3:0.05
    4:0.05
    5:0.02
    6:0.19
    7:0.27
    8:0.03
    9:0.04
    10:0.13
    11:0.08
    Negative Logits
    エ
    -1.60
    iae
    -1.39
    NAME
    -1.31
    カ
    -1.30
     direction
    -1.28
     Headquarters
    -1.27
    Title
    -1.25
    DERR
    -1.25
    soType
    -1.23
     TODAY
    -1.23
    POSITIVE LOGITS
     binge
    1.45
     consuming
    1.43
     consume
    1.43
     snacks
    1.41
    tics
    1.35
     consumes
    1.34
     Frenzy
    1.33
     consumption
    1.32
    stasy
    1.32
    odic
    1.30
    Act Density 0.000%

    No Known Activations