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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unj
    -0.15
    icket
    -0.14
    ube
    -0.14
     yum
    -0.14
     turb
    -0.14
    ield
    -0.14
     Nam
    -0.14
    ynet
    -0.14
    imson
    -0.14
    ifica
    -0.14
    POSITIVE LOGITS
    ãĤ«ãĥ¼
    0.18
    ETS
    0.16
    оÑĢож
    0.15
    .djang
    0.15
    ;element
    0.15
    aru
    0.14
    awy
    0.14
    üstü
    0.14
    udeau
    0.14
     Bylo
    0.14
    Act Density 0.195%

    No Known Activations