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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to the word "Fin" as well as narratives mentioning characters like Fin

    oai_token-act-pair · gpt-3.5-turbo

    references to a character or entity named "Fin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.66
    tan
    -0.64
    theless
    -0.62
     orally
    -0.61
     announcer
    -0.61
    hare
    -0.61
    é¾įå¥ij士
    -0.59
    ĸļ
    -0.58
     Learns
    -0.57
     mechanical
    -0.57
    POSITIVE LOGITS
    isher
    1.15
    ishers
    1.07
    ners
    1.04
    boa
    1.02
    itures
    1.00
    anced
    0.99
    ament
    0.99
    ancing
    0.97
    ishes
    0.96
    ned
    0.95
    Act Density 0.017%

    No Known Activations