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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" indicating movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGLE
    -0.15
    oval
    -0.15
    unn
    -0.14
    ingle
    -0.14
    lettes
    -0.14
    nb
    -0.14
    innen
    -0.13
    uv
    -0.13
    gons
    -0.13
    erde
    -0.13
    POSITIVE LOGITS
    roke
    0.17
    elo
    0.17
    acier
    0.15
    CONF
    0.14
    swing
    0.14
    鹿
    0.14
    isify
    0.14
    UTE
    0.14
    iese
    0.14
    erty
    0.13
    Act Density 0.012%

    No Known Activations