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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical elements and compounds, especially ones ending in 'yp' or 'typ'

    oai_token-act-pair · gpt-3.5-turbo

    words related to typology and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ou
    -0.70
     Catalyst
    -0.66
    gaard
    -0.65
    fully
    -0.64
    Va
    -0.63
    FUL
    -0.62
     Templar
    -0.62
    DERR
    -0.62
     ACTION
    -0.62
     Sahara
    -0.62
    POSITIVE LOGITS
    yp
    1.03
    posium
    0.99
    onent
    0.98
    olicy
    0.97
    aired
    0.97
    utic
    0.92
    ocalypse
    0.90
    osite
    0.90
    amph
    0.90
    olit
    0.90
    Act Density 0.005%

    No Known Activations