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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types and levels of resistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.23
    inged
    -0.18
    INGS
    -0.17
    izon
    -0.16
    ãĥ£
    -0.16
    ystone
    -0.15
    nger
    -0.15
    tra
    -0.15
    xin
    -0.15
    _ALLOW
    -0.15
    POSITIVE LOGITS
    ive
    0.23
     against
    0.22
     Against
    0.20
    /res
    0.19
    à¸Ĺาà¸Ļ
    0.19
    ances
    0.19
    ively
    0.17
     fighters
    0.17
    eenth
    0.17
    ivity
    0.17
    Act Density 0.023%

    No Known Activations