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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating participation or involvement in activities or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mans
    -0.16
    Å¡ÃŃm
    -0.15
    MBED
    -0.15
    é½
    -0.14
    amera
    -0.14
    cobra
    -0.14
    iyi
    -0.14
    patch
    -0.14
    .Destroy
    -0.14
    LOUR
    -0.14
    POSITIVE LOGITS
    agher
    0.16
     Depths
    0.14
    ederland
    0.14
    çķĻ
    0.14
     inf
    0.14
    ืà¹ī
    0.14
    izzo
    0.13
     Zot
    0.13
    IVO
    0.13
     Hindered
    0.13
    Act Density 0.042%

    No Known Activations