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

    Neuronpedia

    INDEX
    Explanations

    large groups of people and their interactions in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.29
    1:0.02
    2:0.16
    3:0.12
    4:0.02
    5:0.09
    6:0.03
    7:0.05
    8:0.03
    9:0.02
    10:0.09
    11:0.01
    Negative Logits
     shortcuts
    -2.85
     leases
    -2.63
     manuals
    -2.61
     patents
    -2.45
     directories
    -2.42
     codes
    -2.41
     firmware
    -2.38
     shortcut
    -2.35
     lease
    -2.34
    eport
    -2.32
    POSITIVE LOGITS
     amph
    3.45
     spectators
    3.41
     crowd
    3.34
     cheering
    3.33
    rowd
    3.32
     applause
    3.20
     audience
    3.15
     chanting
    3.13
     chants
    2.98
     attendance
    2.92
    Act Density 0.064%

    No Known Activations