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

    Neuronpedia

    INDEX
    Explanations

    mentions of email and login-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лÑİÑĩ
    -0.15
    incare
    -0.15
    urd
    -0.15
    aval
    -0.15
     progress
    -0.14
     Geb
    -0.14
    à¸ļาย
    -0.14
     Dark
    -0.14
    eda
    -0.14
    bounds
    -0.14
    POSITIVE LOGITS
     protected
    0.24
    elman
    0.19
    protected
    0.17
    _address
    0.15
     Protected
    0.15
     address
    0.15
    rella
    0.15
    HasBeen
    0.14
    loor
    0.14
    alara
    0.14
    Act Density 0.002%

    No Known Activations