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

    Neuronpedia

    INDEX
    Explanations

    words related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    articles, specifically the word "a" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.70
     Colors
    -0.68
    Own
    -0.65
    Examples
    -0.65
    Anim
    -0.63
    ãĤ¬
    -0.63
    igators
    -0.63
    âĨ
    -0.63
    nces
    -0.63
    ãĤ¿
    -0.62
    POSITIVE LOGITS
     dozen
    1.45
    dozen
    1.28
     hundred
    1.25
     thousand
    1.15
     decade
    1.14
     handful
    0.99
     century
    0.94
     million
    0.94
     month
    0.91
     couple
    0.90
    Act Density 0.065%

    No Known Activations