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

    Neuronpedia

    INDEX
    Explanations

    names of places or people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.82
    ongyang
    -0.82
     citiz
    -0.69
    etheless
    -0.66
     resil
    -0.66
     pse
    -0.65
     fundament
    -0.64
     unden
    -0.63
     shenan
    -0.63
     glim
    -0.63
    POSITIVE LOGITS
    phia
    0.73
    nery
    0.69
    phant
    0.69
    ibrary
    0.68
    quin
    0.65
    otide
    0.64
     Towers
    0.64
    steen
    0.63
    gow
    0.63
    bill
    0.62
    Act Density 0.396%

    No Known Activations