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

    Neuronpedia

    INDEX
    Explanations

    references to disc-related activities or items

    oai_token-act-pair · gpt-3.5-turbo

    references to discs, particularly in the context of disc golf or discography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.82
     Haley
    -0.66
     principals
    -0.64
    atory
    -0.64
    akeru
    -0.63
     Ascend
    -0.63
     Holmes
    -0.63
    terday
    -0.61
    \<
    -0.61
     Apost
    -0.61
    POSITIVE LOGITS
    erning
    1.51
    ourses
    1.25
    ription
    1.20
    ursive
    1.11
    ounter
    1.05
    ounters
    1.04
    arding
    1.04
    othe
    1.02
    ontent
    1.02
    ourse
    1.01
    Act Density 0.016%

    No Known Activations