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

    Neuronpedia

    INDEX
    Explanations

    references to prominent animals, specifically tigers and eagles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omo
    -0.16
    orative
    -0.16
    tures
    -0.15
    619
    -0.14
    elay
    -0.14
    mates
    -0.14
     Bryce
    -0.14
     gia
    -0.14
    gae
    -0.14
    omes
    -0.14
    POSITIVE LOGITS
    tail
    0.18
    hawk
    0.18
    innen
    0.17
    zsche
    0.17
    esses
    0.16
     Tales
    0.16
    æ¯Ľ
    0.16
    -shaped
    0.15
    oods
    0.15
    ůž
    0.15
    Act Density 0.091%

    No Known Activations