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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases denoting exclusivity or special deals

    oai_token-act-pair · gpt-3.5-turbo

    the repeated presence of the prefix "EX"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.80
    kamp
    -0.70
     fool
    -0.66
     Kuh
    -0.66
    tons
    -0.65
    ¿½
    -0.64
    arity
    -0.64
    ¶ħ
    -0.63
     Bolton
    -0.63
    Downloadha
    -0.62
    POSITIVE LOGITS
    CEPT
    1.22
    CLUS
    1.21
    TERN
    1.20
    PORT
    1.19
    PER
    1.10
    PRESS
    1.07
    ACT
    1.01
    ERC
    1.01
    ICO
    1.00
    POS
    0.99
    Act Density 0.006%

    No Known Activations