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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conjunctions or the connection of multiple entities or components

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "along" indicating a connection or relationship between elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateurs
    -0.62
    iens
    -0.60
    odor
    -0.58
    emort
    -0.58
    dom
    -0.57
    nas
    -0.57
    umbo
    -0.57
    rament
    -0.56
    INAL
    -0.55
    NH
    -0.55
    POSITIVE LOGITS
    side
    1.08
     with
    0.88
    with
    0.78
     side
    0.78
    Side
    0.69
    avering
    0.68
    icative
    0.67
    actionDate
    0.66
    cially
    0.66
    oaded
    0.66
    Act Density 0.017%

    No Known Activations