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

    Neuronpedia

    INDEX
    Explanations

    themes related to control and surveillance in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sede
    -0.14
    cesso
    -0.14
     precis
    -0.14
    adar
    -0.14
    LEC
    -0.14
     subtitle
    -0.14
    raj
    -0.13
     syndrome
    -0.13
     préc
    -0.13
     Syndrome
    -0.13
    POSITIVE LOGITS
     actions
    0.26
     ACTIONS
    0.25
     physical
    0.22
     deed
    0.21
     Actions
    0.21
     action
    0.21
    actions
    0.21
     deeds
    0.21
     ACTION
    0.21
     acts
    0.20
    Act Density 0.055%

    No Known Activations