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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing positive qualities or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of moderate to high enthusiasm or positivity about subjects, particularly using the word "pretty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.82
    venant
    -0.80
    APD
    -0.79
     FTA
    -0.73
    arta
    -0.72
    KY
    -0.71
    pent
    -0.69
    HAEL
    -0.68
    jen
    -0.68
    alez
    -0.67
    POSITIVE LOGITS
     darn
    1.26
     nifty
    0.97
     much
    0.89
     damn
    0.87
     tasty
    0.85
     harmless
    0.85
    nice
    0.84
     straightforward
    0.83
     neat
    0.81
     awesome
    0.80
    Act Density 0.019%

    No Known Activations