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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or approval by others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è³¢
    -0.18
    ToProps
    -0.16
    addock
    -0.15
    groundColor
    -0.15
    beros
    -0.15
    æĦ
    -0.14
    positor
    -0.14
    LOBAL
    -0.14
    км
    -0.14
    ulis
    -0.14
    POSITIVE LOGITS
    uppe
    0.15
     Vega
    0.14
    ãĥĹãĥ©
    0.14
    è¡Ĺ
    0.14
    iver
    0.14
    163
    0.14
    ÏĦι
    0.14
    87
    0.13
    /Dk
    0.13
    ابت
    0.13
    Act Density 0.112%

    No Known Activations