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

    Neuronpedia

    INDEX
    Explanations

    words related to existing, persistence, or something being in place already

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "exist" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interpre
    -0.69
    BY
    -0.64
     cha
    -0.62
     treasure
    -0.61
     Medal
    -0.60
     medal
    -0.59
     debug
    -0.59
    bon
    -0.58
     Andersen
    -0.58
     states
    -0.57
    POSITIVE LOGITS
    isting
    4.42
    isted
    2.35
    ists
    1.62
    istence
    1.55
    istance
    1.54
    ist
    1.47
    IST
    1.34
    istent
    1.33
    istant
    1.31
    pected
    1.27
    Act Density 0.009%

    No Known Activations