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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Bar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.83
    ãģ¦
    -0.73
    ãģį
    -0.70
     STATES
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.69
    ä
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    士
    -0.68
    ç«
    -0.68
    CRIP
    -0.68
    POSITIVE LOGITS
    becue
    1.21
    itone
    1.13
    riers
    1.11
    rington
    1.07
    celona
    1.06
    bell
    1.05
    bara
    1.04
    keep
    1.01
    rier
    0.99
    rage
    0.99
    Act Density 0.014%

    No Known Activations