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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to various forms of abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rei
    -0.18
    amura
    -0.15
    uida
    -0.15
    reich
    -0.15
    apsed
    -0.15
    ická
    -0.14
    ference
    -0.14
    appa
    -0.14
    cheng
    -0.14
    ë
    -0.14
    POSITIVE LOGITS
     Dhabi
    0.19
    fulness
    0.17
    ulent
    0.16
    fully
    0.16
    erland
    0.16
    /add
    0.16
     dụng
    0.15
    anas
    0.15
    antium
    0.14
    tual
    0.14
    Act Density 0.008%

    No Known Activations