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

    Neuronpedia

    INDEX
    Explanations

    references to scams and phishing attempts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icho
    -0.18
    ernet
    -0.17
    _UPLOAD
    -0.15
    ichel
    -0.15
    Advertisement
    -0.14
    uml
    -0.14
    RSS
    -0.14
    opsy
    -0.14
     selfish
    -0.14
    éŀ
    -0.14
    POSITIVE LOGITS
     legitimacy
    0.24
     legitimate
    0.23
     legit
    0.20
     Victims
    0.20
     purported
    0.19
     legitim
    0.18
    wire
    0.18
     pur
    0.18
     victims
    0.17
    Susp
    0.17
    Act Density 0.054%

    No Known Activations