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

    Neuronpedia

    INDEX
    Explanations

    statements that challenge or critique the actions of public officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [__
    -0.17
    оби
    -0.17
    otate
    -0.16
    ardless
    -0.16
    atural
    -0.15
    //{{
    -0.15
    hei
    -0.14
    ChangeEvent
    -0.14
    ãĤĤãģªãģĦ
    -0.14
    oot
    -0.13
    POSITIVE LOGITS
     indeed
    0.22
     Indeed
    0.17
     sounds
    0.15
    Indeed
    0.15
     sentiments
    0.14
    avou
    0.14
    inde
    0.14
     elsewhere
    0.14
     Else
    0.13
     sounding
    0.13
    Act Density 0.199%

    No Known Activations