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

    Neuronpedia

    INDEX
    Explanations

    phrases related to management or oversight

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its various usages in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Edited
    -0.66
     summarizes
    -0.62
    illon
    -0.61
     illustrates
    -0.61
     consists
    -0.58
     denotes
    -0.57
    leeve
    -0.57
     refers
    -0.56
     distinguishes
    -0.56
    ornings
    -0.56
    POSITIVE LOGITS
     slightest
    1.21
     same
    1.11
     latter
    1.03
     aforementioned
    0.99
     remainder
    0.97
     entirety
    0.94
     entire
    0.91
     proverbial
    0.90
     rest
    0.89
    ses
    0.89
    Act Density 1.091%

    No Known Activations