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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusion and connection

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that create connections between ideas or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocrat
    -0.68
    ãĥĩãĤ£
    -0.68
    usha
    -0.62
    illus
    -0.61
    ãĥ¼ãĥ
    -0.61
    ril
    -0.61
    ãĤ·ãĥ£
    -0.60
    Ľ
    -0.59
    ãĤ³
    -0.59
    idae
    -0.58
    POSITIVE LOGITS
     elsewhere
    1.64
     abroad
    1.31
     throughout
    1.16
     across
    1.15
     anywhere
    1.13
     everywhere
    1.13
     beyond
    1.07
     wherever
    1.04
     indoors
    1.03
     in
    1.03
    Act Density 0.461%

    No Known Activations