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

    Neuronpedia

    INDEX
    Explanations

    common words used to establish connections and references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐłÐĿ
    -0.17
    avar
    -0.15
     Hamp
    -0.14
    olla
    -0.14
    etary
    -0.14
    ava
    -0.14
     kür
    -0.14
    icos
    -0.14
    responsive
    -0.14
    PEND
    -0.14
    POSITIVE LOGITS
    mue
    0.17
    glich
    0.15
    nech
    0.14
     Impossible
    0.14
    oron
    0.14
    ingleton
    0.14
    anggal
    0.14
     simul
    0.14
     listed
    0.14
    Impossible
    0.13
    Act Density 0.000%

    No Known Activations