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

    Neuronpedia

    INDEX
    Explanations

    the word "quite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "quite" followed by "a"

    np_acts-logits-general · gemini-2.0-flash

    quite a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quoque
    -0.69
     quæ
    -0.67
     siis
    -0.59
     ſhould
    -0.58
    eseorang
    -0.57
     enää
    -0.56
    fjspx
    -0.56
     Jefus
    -0.56
     muſt
    -0.54
     ſtill
    -0.54
    POSITIVE LOGITS
     frankly
    0.82
     literally
    0.77
     possibly
    0.68
     awhile
    0.66
     rightly
    0.65
     alright
    0.64
    literally
    0.64
     honestly
    0.62
     Literally
    0.61
     often
    0.60
    Act Density 0.044%

    No Known Activations