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

    Neuronpedia

    INDEX
    Explanations

    references to diversity in educational settings and discussions surrounding affirmative action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ണ്
    -0.39
    Originally
    -0.39
    fancy
    -0.39
     cade
    -0.38
     check
    -0.38
    大事
    -0.37
     mor
    -0.37
     Stamm
    -0.37
    新聞
    -0.37
     Zuw
    -0.36
    POSITIVE LOGITS
    uxxxx
    0.86
     presence
    0.79
     présence
    0.75
    HideFlags
    0.74
     Presence
    0.74
     surla
    0.69
    HasForeignKey
    0.69
     presenza
    0.69
    المشاركات
    0.68
     Paglinawan
    0.66
    Act Density 0.618%

    No Known Activations