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

    Neuronpedia

    INDEX
    Explanations

    affirmative and negative responses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.01
     ?</
    -0.98
    ftagPool
    -0.93
    COUVER
    -0.93
    InjectAttribute
    -0.92
     Paglinawan
    -0.92
     متعلقه
    -0.91
    >
    -0.90
     contextLoads
    -0.90
    HasAnnotation
    -0.89
    POSITIVE LOGITS
    ,
    1.05
    .
    0.71
    !
    0.59
    ;
    0.57
     ,
    0.43
    :
    0.42
    )
    0.40
     –
    0.40
     then
    0.40
     верно
    0.40
    Act Density 0.088%

    No Known Activations