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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the word "reference to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "reference" in relation to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DH
    -0.91
    hered
    -0.72
    natureconservancy
    -0.70
    tails
    -0.69
    rio
    -0.69
    ires
    -0.68
    herer
    -0.66
    ivities
    -0.65
    ether
    -0.65
    LI
    -0.64
    POSITIVE LOGITS
     antiquity
    0.66
     commence
    0.66
     ensure
    0.65
     accompany
    0.65
    asted
    0.64
     commemorate
    0.64
     perfection
    0.63
    othy
    0.63
     whichever
    0.62
     unsub
    0.62
    Act Density 0.128%

    No Known Activations