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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and report structures in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦÙħاÙĨ
    -0.17
    nable
    -0.15
    udad
    -0.15
    .sdk
    -0.14
    æ¡Į
    -0.14
    ÑĢоп
    -0.14
    lok
    -0.14
     bonds
    -0.14
    mrt
    -0.13
    elocity
    -0.13
    POSITIVE LOGITS
    DBObject
    0.15
     Jal
    0.15
     sticking
    0.15
    unami
    0.15
     Sole
    0.14
     offsetof
    0.14
    ferred
    0.14
    iali
    0.14
    utral
    0.14
     Craig
    0.14
    Act Density 0.047%

    No Known Activations