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

    Neuronpedia

    INDEX
    Explanations

    general terms related to a broad collection of items

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to a wide variety of topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walls
    -0.72
    MIT
    -0.71
    $$$$
    -0.69
     Row
    -0.66
     Tycoon
    -0.65
    mit
    -0.65
    prints
    -0.63
     Steal
    -0.63
    nesday
    -0.59
    Slow
    -0.58
    POSITIVE LOGITS
     ranging
    0.87
     imaginable
    0.78
     kinds
    0.76
    efully
    0.75
     of
    0.75
     ranges
    0.73
    ortment
    0.73
    ranging
    0.72
     degrees
    0.70
     facets
    0.70
    Act Density 0.045%

    No Known Activations