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

    Neuronpedia

    INDEX
    Explanations

    phrases related to congratulations or celebratory expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.19
    conf
    -0.16
    ÑĪев
    -0.15
    lopen
    -0.14
    ipes
    -0.14
    oxy
    -0.14
     -*-č↵
    -0.14
    uw
    -0.14
    berger
    -0.14
    ansi
    -0.14
    POSITIVE LOGITS
    rats
    0.32
    estion
    0.29
    regation
    0.26
     Cong
    0.25
    Cong
    0.23
    rat
    0.20
    ested
    0.19
    erville
    0.17
     cong
    0.17
    ole
    0.17
    Act Density 0.007%

    No Known Activations