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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that relate to various forms of importance and classification in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.17
    apy
    -0.16
    pio
    -0.16
    assi
    -0.15
    alls
    -0.15
    ÑĮогоднÑĸ
    -0.15
    ocate
    -0.15
    fore
    -0.14
    alling
    -0.14
    agn
    -0.14
    POSITIVE LOGITS
     S
    0.28
    .getS
    0.17
     abstraction
    0.17
    erton
    0.16
     BT
    0.16
    nict
    0.15
    BT
    0.15
    immel
    0.15
    Äįas
    0.15
    anto
    0.15
    Act Density 0.030%

    No Known Activations