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

    Neuronpedia

    INDEX
    Explanations

    terms related to drama and storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rew
    -0.17
    inner
    -0.17
    ж
    -0.17
    /devices
    -0.16
    raw
    -0.16
    ADE
    -0.15
    .parseFloat
    -0.15
    -depth
    -0.15
     doch
    -0.15
    OrDefault
    -0.15
    POSITIVE LOGITS
    ãģªãģĦ
    0.21
    ãģªãģı
    0.20
    itian
    0.19
    urnal
    0.19
    ughter
    0.18
    YNAMIC
    0.18
    iating
    0.18
    itory
    0.18
    IALOG
    0.18
    .parseDouble
    0.18
    Act Density 2.340%

    No Known Activations