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

    Neuronpedia

    INDEX
    Explanations

    references to criticism and scrutiny of actions, particularly related to personal or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gu
    -0.15
    roken
    -0.15
    avage
    -0.15
     подÑģ
    -0.15
     Wass
    -0.15
    eah
    -0.14
    cen
    -0.14
    549
    -0.14
    itra
    -0.14
    ENCH
    -0.14
    POSITIVE LOGITS
    MBER
    0.15
    ause
    0.15
     GIR
    0.14
    ARIO
    0.14
    CTL
    0.14
    istrovstvÃŃ
    0.14
    Invoker
    0.14
     Elliott
    0.13
    Db
    0.13
    idge
    0.13
    Act Density 0.263%

    No Known Activations