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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding societal norms and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysl
    -0.15
    _deinit
    -0.15
    raw
    -0.14
    idenav
    -0.14
     Seeder
    -0.13
    hawk
    -0.13
     dwar
    -0.13
    raci
    -0.13
    yyy
    -0.13
    æ¹
    -0.13
    POSITIVE LOGITS
     conventions
    0.24
     conventional
    0.24
     convention
    0.22
     established
    0.20
     conformity
    0.18
     society
    0.18
     traditional
    0.17
     Establishment
    0.17
     establishment
    0.17
     norms
    0.17
    Act Density 0.194%

    No Known Activations