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

    Neuronpedia

    INDEX
    Explanations

    references to journals and related terms in academic or publication contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fall
    -0.18
    loh
    -0.16
    äter
    -0.16
    olut
    -0.15
    allen
    -0.15
    kker
    -0.15
     any
    -0.14
    uation
    -0.14
    ted
    -0.14
    arr
    -0.14
    POSITIVE LOGITS
    istics
    0.18
    ette
    0.18
    mina
    0.18
    istic
    0.17
    naire
    0.17
    /books
    0.16
    oleÄį
    0.16
    istically
    0.15
    undles
    0.15
    theast
    0.15
    Act Density 0.029%

    No Known Activations