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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lov
    -0.16
    osen
    -0.14
    ars
    -0.14
    æĬŀ
    -0.14
    atch
    -0.14
    inar
    -0.13
    _interfaces
    -0.13
    rael
    -0.13
    irk
    -0.13
    ats
    -0.13
    POSITIVE LOGITS
     exact
    0.17
    .generated
    0.15
    anggal
    0.15
     asc
    0.14
    ystals
    0.14
    aukee
    0.14
    ovny
    0.14
    exact
    0.14
    StateException
    0.14
    olars
    0.14
    Act Density 0.080%

    No Known Activations