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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives describing the degree or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing significance or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.69
    ¬¼
    -0.63
    çļ
    -0.61
    etts
    -0.58
    }}}
    -0.58
    mberg
    -0.57
    ritz
    -0.57
    sembly
    -0.55
    odor
    -0.54
    osate
    -0.54
    POSITIVE LOGITS
     than
    2.43
    than
    2.29
     Than
    1.91
    Th
    0.89
     TH
    0.85
     then
    0.78
    then
    0.76
     THEN
    0.76
    worldly
    0.72
     besides
    0.66
    Act Density 0.521%

    No Known Activations