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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names, potentially related to famous individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rob
    -0.73
     Canary
    -0.71
    Magikarp
    -0.67
     Skydragon
    -0.67
    anguage
    -0.65
     Bei
    -0.62
    ifice
    -0.62
     Alchemist
    -0.62
    entin
    -0.61
    ymph
    -0.61
    POSITIVE LOGITS
    rix
    1.06
    rik
    0.99
    riks
    0.91
    elin
    0.87
    rites
    0.78
    rique
    0.78
    rw
    0.78
    terness
    0.77
    ru
    0.77
    rid
    0.75
    Act Density 0.027%

    No Known Activations