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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs referring to actions taken or speculated by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    pronouns used in contexts involving actions or decisions by groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bai
    -0.66
    geries
    -0.65
    GMT
    -0.63
    td
    -0.63
     Karin
    -0.62
     Bar
    -0.62
     Danish
    -0.60
    manship
    -0.59
     Additional
    -0.58
     Bangl
    -0.57
    POSITIVE LOGITS
    selves
    0.89
    govtrack
    0.81
    ÃĥÃĤ
    0.77
    awaru
    0.72
     preferably
    0.70
    're
    0.66
    arte
    0.66
    ldon
    0.65
    thora
    0.64
    zees
    0.64
    Act Density 0.674%

    No Known Activations