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

    Neuronpedia

    INDEX
    Explanations

    words related to hubs or central locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hub."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGHTS
    -0.79
    terday
    -0.73
    essee
    -0.73
    esthetic
    -0.73
    issance
    -0.72
    ittee
    -0.72
    DonaldTrump
    -0.71
    chnology
    -0.71
    anguage
    -0.69
    ãĤī
    -0.68
    POSITIVE LOGITS
    bub
    1.49
    bard
    1.18
    ris
    1.07
    hub
    1.06
    lins
    1.03
     hub
    1.00
    lot
    0.99
     Hub
    0.97
    staff
    0.97
    Hub
    0.93
    Act Density 0.024%

    No Known Activations