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

    Neuronpedia

    INDEX
    Explanations

    phrases related to administrative tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preceding
    -0.16
    preced
    -0.16
    iloc
    -0.15
     hereby
    -0.14
     preced
    -0.14
     Beginning
    -0.13
    ssi
    -0.13
    êµ°ìļĶ
    -0.13
    autoreleasepool
    -0.13
    ÅĽnie
    -0.13
    POSITIVE LOGITS
     later
    1.09
    later
    0.90
     Later
    0.85
    Later
    0.83
     später
    0.71
     afterwards
    0.63
     pozdÄĽji
    0.60
     latter
    0.60
     subsequently
    0.55
     afterward
    0.55
    Act Density 0.724%

    No Known Activations