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

    Neuronpedia

    INDEX
    Explanations

    discussions about extended durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uilder
    -0.18
    ÙĬÙĪÙĨ
    -0.17
    .hm
    -0.15
    edula
    -0.15
    }}],↵
    -0.14
    LError
    -0.14
    oten
    -0.14
    ä¸ĢæŃ¥
    -0.14
    ilon
    -0.14
    ongyang
    -0.14
    POSITIVE LOGITS
     extended
    0.45
    extended
    0.36
     prolonged
    0.35
     Extended
    0.34
    Extended
    0.34
    _extended
    0.30
     pro
    0.30
     periods
    0.29
     sustained
    0.27
     lengths
    0.27
    Act Density 0.066%

    No Known Activations