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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duration or persistence of experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.16
    ãĤµãĤ¤
    -0.15
    å£
    -0.15
    jez
    -0.15
    pra
    -0.14
    pedia
    -0.14
    ýš
    -0.14
    izyon
    -0.14
    agar
    -0.14
    toi
    -0.14
    POSITIVE LOGITS
    chten
    0.18
     Levi
    0.17
    -le
    0.17
    -Le
    0.17
     New
    0.17
     Le
    0.17
    ÑĤÑĢо
    0.16
    νÏĦ
    0.16
    lease
    0.16
    lep
    0.15
    Act Density 0.038%

    No Known Activations