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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated contexts, particularly in legal or formal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pps
    -0.17
    ]={↵
    -0.15
    reau
    -0.14
    /thumb
    -0.14
    god
    -0.14
    aign
    -0.14
    leness
    -0.13
    ело
    -0.13
    ÃŃl
    -0.13
    bum
    -0.13
    POSITIVE LOGITS
    pher
    0.15
    ikon
    0.15
    izzo
    0.14
    anders
    0.14
    acades
    0.14
    oph
    0.14
    ÑĨин
    0.14
    ãģ£ãģį
    0.13
    yle
    0.13
     ace
    0.13
    Act Density 0.007%

    No Known Activations