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

    Neuronpedia

    INDEX
    Explanations

    references to personal achievements and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieve
    -0.17
    ếp
    -0.15
    erged
    -0.15
    733
    -0.14
    ield
    -0.14
    hee
    -0.14
    alfa
    -0.14
    ucht
    -0.14
     Verfüg
    -0.14
    yb
    -0.14
    POSITIVE LOGITS
     indeed
    0.21
    Indeed
    0.19
     eventually
    0.18
     Indeed
    0.18
     ultimately
    0.18
    UCCEEDED
    0.16
    ecc
    0.15
    æŀľ
    0.15
    ãĤ¤ãĥ¤
    0.15
    aven
    0.14
    Act Density 0.287%

    No Known Activations