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

    Neuronpedia

    INDEX
    Explanations

    phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tanz
    -0.75
    kw
    -0.75
     pit
    -0.68
     boarding
    -0.67
    rieved
    -0.66
     kitchens
    -0.66
     whole
    -0.64
     Dull
    -0.62
    robe
    -0.61
     hunted
    -0.59
    POSITIVE LOGITS
     Whilst
    0.91
    /"
    0.87
     Keynes
    0.86
    Firstly
    0.79
    Marx
    0.76
    """
    0.76
    arta
    0.75
    pler
    0.75
    netflix
    0.72
    ablishment
    0.72
    Act Density 0.029%

    No Known Activations