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

    Neuronpedia

    INDEX
    Explanations

    references to specific game scores and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zac
    -0.16
    engo
    -0.15
    еп
    -0.15
    olith
    -0.15
    ariat
    -0.14
    emplace
    -0.14
     RegExp
    -0.14
    aras
    -0.14
     Oswald
    -0.14
    anny
    -0.13
    POSITIVE LOGITS
    pez
    0.16
    blr
    0.15
    aby
    0.14
     huy
    0.14
     away
    0.14
     ca
    0.14
    ively
    0.14
    ating
    0.14
     against
    0.13
    ogonal
    0.13
    Act Density 0.008%

    No Known Activations