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

    Neuronpedia

    INDEX
    Explanations

    pronouns like "anyone," "their," "who" and "that" along with action verbs like "force," "were," "do," and "have."

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and auxiliary verbs indicating existence or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imar
    -0.58
     understandably
    -0.58
     enormously
    -0.56
     now
    -0.54
    APTER
    -0.54
     Trop
    -0.52
     immensely
    -0.51
     Bigfoot
    -0.51
     then
    -0.51
     thanked
    -0.50
    POSITIVE LOGITS
    Else
    1.09
    abouts
    1.03
    depending
    0.83
     equivalent
    0.82
    acle
    0.81
    nam
    0.80
    phans
    0.73
    chard
    0.71
    odox
    0.70
    Downloadha
    0.70
    Act Density 0.271%

    No Known Activations