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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes in connectivity or status in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.17
    лиÑĨ
    -0.17
    733
    -0.15
    757
    -0.15
    achs
    -0.14
     tick
    -0.14
    iaux
    -0.14
    çŁ¢
    -0.13
    anga
    -0.13
    RELEASE
    -0.13
    POSITIVE LOGITS
    CTR
    0.15
    traction
    0.15
    nish
    0.14
    erral
    0.14
     XT
    0.14
    ifu
    0.14
    ace
    0.14
    ACE
    0.14
    rence
    0.14
    ictor
    0.14
    Act Density 0.226%

    No Known Activations