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

    Neuronpedia

    INDEX
    Explanations

    expressions and discussions regarding opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lsi
    -0.19
    orian
    -0.17
    gars
    -0.16
    gow
    -0.16
    chner
    -0.16
    lier
    -0.15
    abet
    -0.15
    cq
    -0.15
    uras
    -0.15
    _FILL
    -0.15
    POSITIVE LOGITS
    aires
    0.22
    ated
    0.20
    naire
    0.20
    /op
    0.19
     polls
    0.17
     expressed
    0.17
     holders
    0.17
    ATED
    0.17
    ster
    0.17
     opinion
    0.17
    Act Density 0.031%

    No Known Activations