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

    Neuronpedia

    INDEX
    Explanations

    political entities and geographic regions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    etr
    -0.74
    DragonMagazine
    -0.68
    elo
    -0.66
    Plex
    -0.65
    dylib
    -0.65
    potion
    -0.65
    luck
    -0.64
    agnetic
    -0.64
    ruff
    -0.64
    art
    -0.64
    POSITIVE LOGITS
     elsewhere
    1.70
     abroad
    1.62
     beyond
    1.21
     across
    1.16
     internationally
    1.14
     neighboring
    1.12
     neighbouring
    1.11
     overseas
    1.09
     northwestern
    1.07
     Europe
    1.07
    Act Density 0.146%

    No Known Activations