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

    Neuronpedia

    INDEX
    Explanations

    references to specific categories or tags of content, often in a structured or formatted manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollar
    -0.18
    ault
    -0.18
    eve
    -0.15
     Grimm
    -0.15
    ehler
    -0.15
    eeper
    -0.14
    egas
    -0.14
    ’
    -0.14
    ickle
    -0.14
    iddy
    -0.14
    POSITIVE LOGITS
    achten
    0.17
    ÑĨенÑĤÑĢа
    0.15
     Yuk
    0.15
    azio
    0.14
    etu
    0.14
    кÑĥÑĢ
    0.14
    andi
    0.14
    actionDate
    0.14
    mbH
    0.14
    uet
    0.14
    Act Density 0.055%

    No Known Activations