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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people or informal addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caufe
    -0.80
     CreateTagHelper
    -0.80
     defire
    -0.77
     pleaſure
    -0.76
    SpringBootTest
    -0.74
     cauſe
    -0.74
     stepmother
    -0.73
     fevere
    -0.72
     Muri
    -0.72
     Tampoco
    -0.71
    POSITIVE LOGITS
     yourselves
    0.76
    Gentlemen
    0.73
     folks
    0.72
     vocês
    0.70
     guys
    0.70
    selves
    0.67
     gentlemen
    0.67
     members
    0.64
     team
    0.63
     Gentlemen
    0.62
    Act Density 0.052%

    No Known Activations