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

    Neuronpedia

    INDEX
    Explanations

    phrases related to surveillance and privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.20
    3:0.13
    4:0.06
    5:0.05
    6:0.02
    7:0.06
    8:0.07
    9:0.09
    10:0.11
    11:0.11
    Negative Logits
    issance
    -1.42
    �
    -1.38
    ּ
    -1.34
     Lifetime
    -1.33
    etric
    -1.30
    soever
    -1.23
     Badge
    -1.22
    ishable
    -1.21
    Mesh
    -1.18
     Exhibition
    -1.15
    POSITIVE LOGITS
     complain
    1.55
     blame
    1.45
    untled
    1.43
    livious
    1.40
     boycot
    1.35
     themselves
    1.34
     disagree
    1.34
     boycott
    1.32
    their
    1.31
     misled
    1.30
    Act Density 0.352%

    No Known Activations