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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feedback and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    宿
    -0.16
    aniel
    -0.15
    имеÑĢ
    -0.14
    pei
    -0.14
    ĶĦ
    -0.14
     Dort
    -0.14
     Ipsum
    -0.14
    -kit
    -0.14
    кÑĥÑĤ
    -0.14
    otron
    -0.14
    POSITIVE LOGITS
    lla
    0.15
    icas
    0.15
    CADE
    0.15
    erdale
    0.15
    rette
    0.15
    jac
    0.15
    ISTA
    0.14
    DDS
    0.14
    /false
    0.14
    chw
    0.14
    Act Density 0.003%

    No Known Activations