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

    Neuronpedia

    INDEX
    Explanations

    keywords related to actions or creations, such as bombs, reports, songs, videos, ports, pieces, compositions, tricks, tracks, mistakes, tunes, passes, cards, blows, recipes, promises, films

    oai_token-act-pair · gpt-3.5-turbo

    terms related to creative works and their production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cer
    -0.71
    asus
    -0.62
    026
    -0.60
    \\\\\\\\\\\\\\\\
    -0.60
    ALLY
    -0.60
     Stern
    -0.59
    RY
    -0.59
    tein
    -0.58
     Kov
    -0.57
     Vehicle
    -0.57
    POSITIVE LOGITS
    cape
    1.23
    heet
    1.20
    mith
    1.15
    paces
    1.12
    poons
    1.02
    pring
    1.00
    pace
    1.00
    creen
    0.99
    hip
    0.98
    chool
    0.98
    Act Density 0.363%

    No Known Activations