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

    Neuronpedia

    INDEX
    Explanations

    numeric information related to measurements such as time and distance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the indefinite article "a" or "an" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jagu
    -0.71
     Vaugh
    -0.69
    evidence
    -0.65
    anism
    -0.62
    iments
    -0.59
    agree
    -0.58
    Edit
    -0.57
     Adin
    -0.57
     eg
    -0.55
    chuk
    -0.54
    POSITIVE LOGITS
     lot
    0.98
     bunch
    0.90
     handful
    0.83
     couple
    0.82
    uras
    0.81
     huge
    0.79
     plethora
    0.78
     glimpse
    0.77
     few
    0.77
     sizable
    0.77
    Act Density 0.702%

    No Known Activations