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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leadership positions and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enden
    -0.17
    yc
    -0.16
    ekk
    -0.16
    ycop
    -0.16
    INCREMENT
    -0.15
    481
    -0.15
    ALCHEMY
    -0.15
    .twig
    -0.15
    idas
    -0.15
    -face
    -0.14
    POSITIVE LOGITS
    ship
    0.23
    ships
    0.16
     Bene
    0.16
    hi
    0.15
    kaç
    0.14
     Koh
    0.14
     of
    0.14
     dise
    0.14
    ially
    0.14
    /
    0.14
    Act Density 0.037%

    No Known Activations