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

    Neuronpedia

    INDEX
    Explanations

    references to social media interactions and websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Griffith
    -0.17
     McCabe
    -0.15
    yr
    -0.15
    eb
    -0.14
    Insets
    -0.14
    rest
    -0.14
    ätz
    -0.14
     Jur
    -0.14
    hood
    -0.13
     sensitive
    -0.13
    POSITIVE LOGITS
     Stam
    0.18
    Lux
    0.16
    lux
    0.16
    iasm
    0.16
    bast
    0.16
    odÃŃ
    0.15
    uve
    0.15
    BASH
    0.15
    AXB
    0.15
    ÏĩεδÏĮν
    0.15
    Act Density 0.028%

    No Known Activations