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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal progression or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arges
    -0.15
    سب
    -0.15
    _AUD
    -0.14
    åĸ
    -0.14
    èĪĪ
    -0.14
    é¡¿
    -0.14
     ((__
    -0.14
    urm
    -0.14
    .insertBefore
    -0.14
    .quick
    -0.14
    POSITIVE LOGITS
    ëĭ¥
    0.20
    ricks
    0.19
    occan
    0.17
    agem
    0.16
    848
    0.15
    ovny
    0.15
     AFTER
    0.14
    декÑģ
    0.14
    itudes
    0.14
     sext
    0.14
    Act Density 0.096%

    No Known Activations