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

    Neuronpedia

    INDEX
    Explanations

    names of politicians

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end-of-text token, indicating a separation between distinct sections or items, possibly for categorizing Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blot
    -0.70
     Mellon
    -0.66
     foul
    -0.66
     Mechdragon
    -0.66
     Bil
    -0.65
     blunt
    -0.65
     hottest
    -0.65
     tips
    -0.64
     Mane
    -0.63
     skim
    -0.63
    POSITIVE LOGITS
    useum
    1.24
    igrant
    1.22
    umbai
    1.21
    ISSION
    1.20
    arijuana
    1.19
    unicip
    1.19
    ixed
    1.19
    otive
    1.19
    ountain
    1.18
    ovies
    1.18
    Act Density 0.057%

    No Known Activations