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

    Neuronpedia

    INDEX
    Explanations

    adjectives like "pretty" with high intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pretty" used for emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venant
    -0.90
    APD
    -0.81
    PLIED
    -0.81
    JV
    -0.78
    uther
    -0.77
    iments
    -0.75
    upon
    -0.75
    iment
    -0.75
    herry
    -0.75
    arta
    -0.72
    POSITIVE LOGITS
     darn
    1.18
     nifty
    0.91
     snipp
    0.85
     damn
    0.84
    nice
    0.79
     harmless
    0.77
    heet
    0.75
     cool
    0.74
     penny
    0.73
     damned
    0.72
    Act Density 0.019%

    No Known Activations