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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asje
    -0.17
    ctal
    -0.15
    ncy
    -0.15
    rome
    -0.14
    wstring
    -0.14
    ledge
    -0.14
    اشÛĮ
    -0.14
    chat
    -0.13
    elia
    -0.13
    ÑĢеменно
    -0.13
    POSITIVE LOGITS
    geries
    0.20
    aland
    0.17
     purposes
    0.16
    mlin
    0.15
     sake
    0.15
    аÑĢ
    0.15
    uard
    0.15
    bones
    0.14
    tl
    0.14
    继
    0.14
    Act Density 0.003%

    No Known Activations