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

    Neuronpedia

    INDEX
    Explanations

    direct quotes and attributed speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -0.65
    ніципа
    -0.62
    ⓧ
    -0.60
    RTEX
    -0.58
     snippetHide
    -0.57
    IntoConstraints
    -0.57
    最快更新
    -0.54
     Biôgrafia
    -0.54
    WriteAttribute
    -0.54
    原始内容存档于
    -0.52
    POSITIVE LOGITS
     explains
    1.09
     states
    1.03
     stated
    1.02
     explained
    0.94
     explain
    0.94
     explica
    0.84
     reveals
    0.82
     informs
    0.77
     clarifies
    0.77
     spiega
    0.73
    Act Density 0.377%

    No Known Activations