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

    Neuronpedia

    INDEX
    Explanations

    specific medical terms and conditions, particularly those related to organs or body parts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various forms of the word "cul," often relating to cultural or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.67
     marsh
    -0.67
     Blaz
    -0.65
     Franks
    -0.64
     Barkley
    -0.64
    è¦ļéĨĴ
    -0.64
     Pilgrim
    -0.64
     Rule
    -0.62
    die
    -0.61
     Bever
    -0.60
    POSITIVE LOGITS
    atures
    1.04
    ately
    1.02
    ators
    1.01
    cul
    1.01
    ator
    1.00
    iar
    0.97
    uable
    0.95
    ature
    0.95
    ision
    0.94
    atell
    0.92
    Act Density 0.016%

    No Known Activations