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

    Neuronpedia

    INDEX
    Explanations

    mentions of trophies and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    695
    -0.16
    erness
    -0.15
     Zot
    -0.15
    comings
    -0.15
    ings
    -0.14
    lander
    -0.14
    AKE
    -0.14
    ayet
    -0.14
    modo
    -0.14
    ching
    -0.14
    POSITIVE LOGITS
    raid
    0.16
    oplast
    0.15
    pleted
    0.14
     McLaren
    0.14
    è©ŀ
    0.14
    repos
    0.14
     Seks
    0.14
    gebra
    0.14
    ô
    0.13
    hone
    0.13
    Act Density 0.018%

    No Known Activations