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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "enough" in a document

    oai_token-act-pair · gpt-3.5-turbo

    the term "enough" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amon
    -0.78
    eston
    -0.70
    ificate
    -0.69
    desc
    -0.69
    folk
    -0.68
    mist
    -0.67
    ican
    -0.64
    alias
    -0.64
    dad
    -0.63
    Ń·
    -0.63
    POSITIVE LOGITS
     calories
    0.85
     clout
    0.73
     quantities
    0.72
     information
    0.70
    HUD
    0.70
     episodes
    0.70
     doses
    0.69
     helium
    0.68
     ingredients
    0.68
    Items
    0.67
    Act Density 0.025%

    No Known Activations