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

    Neuronpedia

    INDEX
    Explanations

    keywords related to locations in a directional sense, such as upstream and downstream

    oai_token-act-pair · gpt-3.5-turbo

    directional references related to water flow (specifically "upstream" and "downstream")

    oai_token-act-pair · gpt-4-turbo

    terms related to directional flow in processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.79
    itia
    -0.77
     Manson
    -0.75
    ces
    -0.73
    pmwiki
    -0.67
     Patton
    -0.66
    inea
    -0.66
    berman
    -0.65
    orian
    -0.64
    nam
    -0.64
    POSITIVE LOGITS
     downstream
    1.35
     upstream
    1.25
    stream
    0.78
    edIn
    0.72
     propagation
    0.71
    side
    0.71
     watershed
    0.71
    externalActionCode
    0.70
     prelim
    0.70
    layer
    0.69
    Act Density 0.006%

    No Known Activations