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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terms of service and usage policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.09
    3:0.08
    4:0.06
    5:0.04
    6:0.12
    7:0.27
    8:0.03
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
     coffers
    -1.60
     benches
    -1.56
    isSpecialOrderable
    -1.54
     polls
    -1.54
     cabinets
    -1.51
     backlog
    -1.50
     bins
    -1.45
     ledger
    -1.43
     councillors
    -1.42
    OGR
    -1.41
    POSITIVE LOGITS
     Compliance
    1.84
    claimer
    1.80
    Privacy
    1.80
    lov
    1.56
     Host
    1.48
    Thumbnail
    1.46
    Host
    1.46
    Site
    1.45
    Trust
    1.44
    Bre
    1.43
    Act Density 0.001%

    No Known Activations