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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical references in contexts of political or social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.74
    ©¶æ
    -0.73
    iple
    -0.68
    sein
    -0.63
     activ
    -0.62
     barg
    -0.62
     poop
    -0.62
     deed
    -0.62
     sqor
    -0.62
    itus
    -0.61
    POSITIVE LOGITS
     where
    1.36
    where
    1.33
     birthplace
    1.03
     meanwhile
    0.97
     which
    0.95
     whence
    0.90
     Latvia
    0.89
     wherein
    0.88
     whose
    0.83
    population
    0.82
    Act Density 0.175%

    No Known Activations