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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the overall experience or duration of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buz
    -0.16
    кеÑĤ
    -0.14
    rial
    -0.14
     cleared
    -0.14
     clearing
    -0.14
    SEG
    -0.14
    kaar
    -0.14
    alık
    -0.14
    orig
    -0.14
    les
    -0.14
    POSITIVE LOGITS
     throughout
    0.21
    Throughout
    0.19
     Throughout
    0.18
    dock
    0.16
    hots
    0.15
     escorte
    0.15
    oucher
    0.15
    dorf
    0.15
    951
    0.14
    gebn
    0.14
    Act Density 0.088%

    No Known Activations