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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate measurement, units, and mathematical or scientific computations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ж
    -0.20
    inner
    -0.19
    rew
    -0.18
    raw
    -0.18
    .parseFloat
    -0.18
    /devices
    -0.18
    ducted
    -0.18
     doch
    -0.17
    immers
    -0.17
    ump
    -0.17
    POSITIVE LOGITS
    ughter
    0.21
    ãģªãģı
    0.19
    rell
    0.19
    ãģªãģĦ
    0.19
    itian
    0.19
    beat
    0.19
    ughters
    0.18
    .parseDouble
    0.18
    urnal
    0.18
     olsa
    0.18
    Act Density 2.627%

    No Known Activations