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

    Neuronpedia

    INDEX
    Explanations

    mentions of foil or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erd
    -0.16
    lint
    -0.16
    zd
    -0.15
     Rim
    -0.15
    astr
    -0.15
     Sent
    -0.14
    ilight
    -0.14
    UST
    -0.14
    gers
    -0.14
    æĨ¶
    -0.14
    POSITIVE LOGITS
    ìĭ¸
    0.15
    WARDS
    0.15
    thouse
    0.15
    icina
    0.14
    EAR
    0.14
    emand
    0.14
    aturas
    0.14
    عا
    0.14
    ACITY
    0.14
    tran
    0.14
    Act Density 0.005%

    No Known Activations