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

    Neuronpedia

    INDEX
    Explanations

    references to prisons and incarceration-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zan
    -0.17
    elah
    -0.15
    -headed
    -0.15
     Destiny
    -0.14
     Powered
    -0.13
    اة
    -0.13
    nestjs
    -0.13
    اغ
    -0.13
    YNAMIC
    -0.13
    owitz
    -0.13
    POSITIVE LOGITS
    (LP
    0.15
    pector
    0.15
     Nobel
    0.14
    èĿ
    0.14
    rysler
    0.14
    ADM
    0.14
     sembl
    0.14
    nas
    0.14
    _ASSUME
    0.14
     volatile
    0.13
    Act Density 0.007%

    No Known Activations