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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial direction and physical effort

    oai_token-act-pair · gpt-3.5-turbo

    terms related to directional movement, particularly "upstream" and "downstream."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manson
    -0.81
    itia
    -0.74
    andum
    -0.72
    atton
    -0.69
    BuyableInstoreAndOnline
    -0.68
    nova
    -0.68
    acca
    -0.68
    iasis
    -0.68
    pmwiki
    -0.66
    orian
    -0.66
    POSITIVE LOGITS
     downstream
    1.05
     upstream
    0.96
    side
    0.81
    ward
    0.74
    é¾
    0.72
    wards
    0.70
    stream
    0.70
    stairs
    0.67
    most
    0.65
    edIn
    0.62
    Act Density 0.018%

    No Known Activations