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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃs
    -0.82
    agle
    -0.71
    ONSORED
    -0.70
    edia
    -0.67
    KEN
    -0.67
    ente
    -0.65
    XY
    -0.64
    GREEN
    -0.64
    aste
    -0.64
    iHUD
    -0.63
    POSITIVE LOGITS
     assorted
    1.01
     consequently
    0.78
    markets
    0.77
     redistributed
    0.77
     tiss
    0.76
     other
    0.75
     distribute
    0.73
     warranties
    0.71
     valleys
    0.71
     hence
    0.70
    Act Density 0.398%

    No Known Activations