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

    Neuronpedia

    INDEX
    Explanations

    advanced or expert-level terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "advantage" or contexts related to advantages and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SIZE
    -0.74
    âĶģ
    -0.69
    WOOD
    -0.64
    ··
    -0.64
     corrid
    -0.63
     oper
    -0.62
    BUT
    -0.62
     eleph
    -0.62
    bered
    -0.61
     Dempsey
    -0.61
    POSITIVE LOGITS
    ocate
    1.20
    anced
    1.17
    ancing
    1.05
    ances
    1.00
    adv
    0.96
    Adv
    0.94
    ices
    0.94
    ournals
    0.93
     Advice
    0.90
     Adv
    0.88
    Act Density 0.012%

    No Known Activations