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

    Neuronpedia

    INDEX
    Explanations

    integral expressions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ìĥ
    -0.17
    ÙĨداÙĨ
    -0.17
     оп
    -0.16
    oit
    -0.16
    ough
    -0.16
    oted
    -0.15
    aghan
    -0.15
    otos
    -0.15
    otland
    -0.15
    rieg
    -0.14
    POSITIVE LOGITS
    orno
    0.15
    brig
    0.14
    pson
    0.14
     Terrorism
    0.14
     Danger
    0.14
    -react
    0.13
    ansson
    0.13
    cker
    0.13
    ist
    0.13
    erton
    0.13
    Act Density 0.016%

    No Known Activations