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

    Neuronpedia

    INDEX
    Explanations

    words related to aesthetics and things that are aesthetically pleasing

    oai_token-act-pair · gpt-3.5-turbo

    words associated with contradictions or paradoxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.74
     Fors
    -0.69
    "},{"
    -0.68
    "}],"
    -0.66
    netflix
    -0.65
    ité
    -0.65
     antiv
    -0.65
    Band
    -0.65
    annels
    -0.65
     channels
    -0.64
    POSITIVE LOGITS
    hetical
    3.30
    hetically
    2.83
     bets
    1.32
    udo
    1.31
    nen
    1.03
     Monroe
    0.97
    heses
    0.94
    hesis
    0.90
     TI
    0.83
     Chrysler
    0.83
    Act Density 0.041%

    No Known Activations