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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal claims and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hei
    -0.16
    angler
    -0.16
    las
    -0.15
    falls
    -0.15
    esc
    -0.15
    ãĥ¼ãĥĹ
    -0.15
    suite
    -0.14
    esser
    -0.14
    kn
    -0.14
    aths
    -0.14
    POSITIVE LOGITS
    IONS
    0.18
    erville
    0.16
    ories
    0.16
    abant
    0.15
    nesty
    0.15
    nown
    0.15
    ĥn
    0.14
    imbus
    0.14
    acle
    0.14
    IGGER
    0.14
    Act Density 0.038%

    No Known Activations