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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulations and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alvarez
    -0.16
    ahlen
    -0.15
    RD
    -0.14
    ä¹ħ
    -0.13
    affles
    -0.13
    olumbia
    -0.13
     Philipp
    -0.13
    ushman
    -0.13
     US
    -0.13
     https
    -0.13
    POSITIVE LOGITS
    BERS
    0.16
    /slick
    0.15
    UBLE
    0.14
    raquo
    0.14
    jective
    0.14
    HeaderCode
    0.14
    alloca
    0.14
    ospace
    0.14
    enu
    0.14
    .fake
    0.13
    Act Density 0.002%

    No Known Activations