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

    Neuronpedia

    INDEX
    Explanations

    references to video games and software platforms like Steam and lightweight game development engines

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gaze
    -0.83
     hydrogen
    -0.78
     soaking
    -0.78
     wrinkles
    -0.77
     perme
    -0.76
     whiskey
    -0.73
     spir
    -0.73
     swell
    -0.72
     peanut
    -0.72
     watering
    -0.72
    POSITIVE LOGITS
    formerly
    1.49
    includes
    1.43
    feat
    1.38
    optional
    1.32
    Main
    1.31
    Single
    1.31
    2009
    1.30
    2011
    1.30
    ...)
    1.30
    BBC
    1.30
    Act Density 0.097%

    No Known Activations