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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and digital security awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukan
    -0.14
    à¸Ńส
    -0.14
    -redux
    -0.14
     tweeted
    -0.14
    ếu
    -0.13
     Retro
    -0.13
    åĢĴ
    -0.13
     RET
    -0.13
    ivas
    -0.13
    arehouse
    -0.13
    POSITIVE LOGITS
     parental
    0.30
     safety
    0.28
     Safety
    0.27
    Safety
    0.26
     parents
    0.25
     Parent
    0.25
     Parents
    0.23
     parent
    0.23
     child
    0.23
     children
    0.22
    Act Density 0.007%

    No Known Activations