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

    Neuronpedia

    INDEX
    Explanations

    the word "belong" and its variations

    oai_token-act-pair · gpt-4-turbo

    words related to ownership or affiliation

    oai_token-act-pair · gpt-3.5-turbo

    the concept of belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     striking
    -0.62
     Sweeney
    -0.61
     eye
    -0.61
    =-=-=-=-=-=-=-=-
    -0.61
    airs
    -0.61
    aul
    -0.61
    ork
    -0.60
    olson
    -0.59
    reci
    -0.58
    tall
    -0.57
    POSITIVE LOGITS
     belong
    1.00
     belonged
    0.97
     belongs
    0.93
    ĪĴ
    0.85
    ãĥł
    0.80
     belonging
    0.78
    itialized
    0.77
    REDACTED
    0.76
    ership
    0.73
    istration
    0.73
    Act Density 0.007%

    No Known Activations