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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of a continuous flow or sequence, often related to processes or data streaming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stream" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.78
     misunderstanding
    -0.74
    ailability
    -0.72
     misunder
    -0.71
    nces
    -0.66
     relativity
    -0.64
     Malt
    -0.62
     lockdown
    -0.62
     circumstance
    -0.61
    Downloadha
    -0.60
    POSITIVE LOGITS
    lining
    1.32
    lined
    1.01
    liner
    0.97
    line
    0.95
    lines
    0.95
    stream
    0.95
    flow
    0.86
    keeper
    0.85
    ãĤ§
    0.84
    waters
    0.82
    Act Density 0.020%

    No Known Activations